|
|
| version 1.2, 2005/12/23 14:01:29 | version 1.175.2.23, 2011/08/10 19:18:03 |
|---|---|
| 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 | try: |
| return rc | nav = ua[string.find(ua, '('):] |
| nav1=ua[string.find(ua,')'):] | |
| import socket | nav2=nav1[string.find(nav1,'('):] |
| nav3=nav2[string.find(nav2,')'):] | |
| def urlopen(url): | ie = string.split(nav, "; ")[1] |
| """urlopen mit timeout""" | ie1 =string.split(nav1, " ")[2] |
| socket.setdefaulttimeout(2) | ie2 =string.split(nav3, " ")[1] |
| ret=urllib.urlopen(url) | ie3 =string.split(nav3, " ")[2] |
| socket.setdefaulttimeout(5) | if string.find(ie3, "Safari") >-1: |
| return ret | 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 getParentPath(path, cnt=1): | |
| """returns pathname shortened by cnt""" | |
| # make sure path doesn't end with / | |
| path = path.rstrip('/') | |
| # split by /, shorten, and reassemble | |
| return '/'.join(path.split('/')[0:-cnt]) | |
| ## | |
| ## documentViewer class | |
| ## | |
| class documentViewer(Folder): | |
| """document viewer""" | |
| meta_type="Document viewer" | |
| def getParamFromDigilib(path,param): | security=ClassSecurityInfo() |
| """gibt param von dlInfo aus""" | manage_options=Folder.manage_options+( |
| imageUrl=genericDigilib+"/dlInfo-xml.jsp?fn="+path | {'label':'main config','action':'changeDocumentViewerForm'}, |
| ) | |
| try: | metadataService = None |
| dom = NonvalidatingReader.parseUri(imageUrl) | """MetaDataFolder instance""" |
| except: | |
| return None | |
| # 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_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()) | |
| params=dom.xpath("//document-parameters/parameter[@name='%s']/@value"%param) | |
| if params: | thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
| return params[0].value | |
| def parseUrlTextTool(url): | |
| """parse index meta""" | |
| 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: | try: |
| dom = NonvalidatingReader.parseUri(url) | import MpdlXmlTextServer |
| except: | textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
| zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) | #templateFolder['fulltextclient'] = xmlRpcClient |
| return (None,None,None) | templateFolder._setObject('fulltextclient',textServer) |
| except Exception, e: | |
| logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) | |
| archivePaths=dom.xpath("//resource/archive-path") | 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)) | |
| if archivePaths and (len(archivePaths)>0): | try: |
| archivePath=getTextFromNode(archivePaths[0]) | # assume MetaDataFolder instance is called metadata |
| else: | self.metadataService = getattr(self, 'metadata') |
| archivePath=None | except Exception, e: |
| logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| if digilibBaseUrl is not None: | |
| self.digilibBaseUrl = digilibBaseUrl | |
| images=dom.xpath("//texttool/image") | |
| if images and (len(images)>0): | # proxy text server methods to fulltextclient |
| image=getTextFromNode(images[0]) | def getTextPage(self, **args): |
| else: | """get page""" |
| image=None | return self.template.fulltextclient.getTextPage(**args) |
| if image and archivePath: | def getOrigPages(self, **args): |
| image=os.path.join(archivePath,image) | """get page""" |
| image=image.replace("/mpiwg/online",'') | return self.template.fulltextclient.getOrigPages(**args) |
| pt=getParamFromDigilib(image,'pt') | |
| else: | def getOrigPagesNorm(self, **args): |
| image=None | """get page""" |
| return self.template.fulltextclient.getOrigPagesNorm(**args) | |
| viewerUrls=dom.xpath("//texttool/digiliburlprefix") | def getQuery(self, **args): |
| """get query in search""" | |
| return self.template.fulltextclient.getQuery(**args) | |
| if viewerUrls and (len(viewerUrls)>0): | def getSearch(self, **args): |
| viewerUrl=getTextFromNode(viewerUrls[0]) | """get search""" |
| else: | return self.template.fulltextclient.getSearch(**args) |
| viewerUrl=None | |
| def getGisPlaces(self, **args): | |
| """get gis places""" | |
| return self.template.fulltextclient.getGisPlaces(**args) | |
| textUrls=dom.xpath("//texttool/text") | def getAllGisPlaces(self, **args): |
| """get all gis places """ | |
| return self.template.fulltextclient.getAllGisPlaces(**args) | |
| if textUrls and (len(textUrls)>0): | def getTranslate(self, **args): |
| textUrl=getTextFromNode(textUrls[0]) | """get translate""" |
| else: | return self.template.fulltextclient.getTranslate(**args) |
| textUrl=None | |
| return viewerUrl,(image,pt),textUrl | |
| def getLemma(self, **args): | |
| """get lemma""" | |
| return self.template.fulltextclient.getLemma(**args) | |
| class documentViewer(ZopePageTemplate): | def getLemmaQuery(self, **args): |
| """document viewer""" | """get query""" |
| return self.template.fulltextclient.getLemmaQuery(**args) | |
| meta_type="Document viewer" | def getLex(self, **args): |
| """get lex""" | |
| return self.template.fulltextclient.getLex(**args) | |
| security=ClassSecurityInfo() | def getToc(self, **args): |
| manage_options=ZopePageTemplate.manage_options+( | """get toc""" |
| {'label':'main config','action':'changeDocumentViewerForm'}, | return self.template.fulltextclient.getToc(**args) |
| ) | |
| _default_content_fn = os.path.join(package_home(globals()),'zpt','documentViewer_template.zpt') | def getTocPage(self, **args): |
| """get tocpage""" | |
| return self.template.fulltextclient.getTocPage(**args) | |
| def __init__(self,id,imageViewerUrl,title=""): | |
| """init document viewer""" | |
| self.id=id | |
| self.title=title | |
| self.imageViewerUrl=imageViewerUrl | |
| security.declareProtected('View management screens','changeDocumentViewerForm') | security.declareProtected('View','thumbs_rss') |
| def changeDocumentViewerForm(self): | def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): |
| """change it""" | ''' |
| pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','changeDocumentViewer.zpt')).__of__(self) | view it |
| return pt() | @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") | |
| logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) | |
| def changeDocumentViewer(self,imageViewerUrl,title="",RESPONSE=None): | if not hasattr(self, 'template'): |
| """init document viewer""" | # create template folder if it doesn't exist |
| self.title=title | self.manage_addFolder('template') |
| self.imageViewerUrl=imageViewerUrl | |
| 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: | |
| viewMode="images" | |
| if RESPONSE is not None: | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
| RESPONSE.redirect('manage_main') | |
| security.declareProtected('View','index_html') | |
| def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1): | |
| """ | |
| view page | |
| @param url: url which contains display information | |
| @param mode: defines how to access the document behind url | |
| @param viewMode: 'images': display images, 'text': display text, default is 'auto' | |
| @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text' | |
| @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) | |
| """ | |
| logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewType=%s start=%s pn=%s"%(mode,url,viewMode,viewType,start,pn)) | |
| def imageLink(self,nr): | if not hasattr(self, 'template'): |
| """link hinter den images""" | # this won't work |
| paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING']) | logging.error("template folder missing!") |
| params={} | return "ERROR: template folder missing!" |
| for x in paramsTmp.iteritems(): | |
| params[x[0]]=x[1][0] | if not getattr(self, 'digilibBaseUrl', None): |
| self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" | |
| params['pn']=nr | |
| newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params) | docinfo = self.getDocinfo(mode=mode,url=url) |
| return newUrl | |
| if tocMode != "thumbs": | |
| # get table of contents | |
| docinfo = self.getToc(mode=tocMode, docinfo=docinfo) | |
| # auto viewMode: text if there is a text else images | |
| if viewMode=="auto": | |
| if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): | |
| viewMode = "text" | |
| viewType = "dict" | |
| else: | |
| viewMode = "images" | |
| elif viewMode == "text_dict": | |
| # legacy fix | |
| viewMode = "text" | |
| viewType = "dict" | |
| # stringify viewType | |
| if isinstance(viewType, list): | |
| viewType = ','.join([t for t in viewType if t]) | |
| pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode) | |
| # get template /template/viewer_$viewMode | |
| pt = getattr(self.template, 'viewer_%s'%viewMode, None) | |
| if pt is None: | |
| logging.error("No template for viewMode=%s!"%viewMode) | |
| # TODO: error page? | |
| return "No template for viewMode=%s!"%viewMode | |
| def thumbruler(self,cols,rows,start,maximum): | # and execute with parameters |
| """ruler for thumbs""" | return pt(docinfo=docinfo, pageinfo=pageinfo) |
| 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 | |
| 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 | return ret |
| 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] | def getBrowser(self): |
| """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 | |
| pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','thumbs.zpt')).__of__(self) | def getDocumentViewerURL(self): |
| return pt(imageUrl=imageUrl,pt=imagepath[1],start=start) | """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 getParams(self, param=None, val=None, params=None): | |
| """returns dict with URL parameters. | |
| def imagePathThumb(self,path,start=0): | Takes URL parameters and additionally param=val or dict params. |
| """path ist the path to the images it is assumes that the index.meta file is one level higher.""" | Deletes key if value is None.""" |
| # copy existing request params | |
| newParams=self.REQUEST.form.copy() | |
| # change single param | |
| if param is not None: | |
| if val is None: | |
| if newParams.has_key(param): | |
| del newParams[param] | |
| else: | |
| newParams[param] = str(val) | |
| path=path.replace("/mpiwg/online","") | # change more params |
| pt=getParamFromDigilib(path,'pt') | if params is not None: |
| imageUrl=genericDigilib+"/servlet/Scaler?fn=%s"%path | for k in params.keys(): |
| v = params[k] | |
| if v is None: | |
| # val=None removes param | |
| if newParams.has_key(k): | |
| del newParams[k] | |
| pageT=PageTemplateFile(os.path.join(package_home(globals()),'zpt','thumbs.zpt')).__of__(self) | else: |
| return pageT(imageUrl=imageUrl,pt=pt,start=start) | newParams[k] = v |
| def headerFromIndexMeta(self,path): | return newParams |
| """gibt header from index meta out""" | |
| metaData=self.metadata.main.meta.bib | def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'): |
| server="http://foxridge.mpiwg-berlin.mpg.de" | """returns URL to documentviewer with parameter param set to val or from dict params""" |
| path="/".join(path.split("/")[0:-1]) | urlParams = self.getParams(param=param, val=val, params=params) |
| metaUrl=server+path+"/index.meta" | # quote values and assemble into query string (not escaping '/') |
| ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()]) | |
| if baseUrl is None: | |
| baseUrl = self.getDocumentViewerURL() | |
| dom = NonvalidatingReader.parseUri(metaUrl) | url = "%s?%s"%(baseUrl, ps) |
| type=dom.xpath("//bib/@type") | return url |
| if type and (len(type)>0): | |
| type=type[0].value | def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None): |
| """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 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 == '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: | else: |
| type="generic" | return False |
| type=type.replace("-"," ")# wrong typesiin index meta "-" instead of " " | |
| hash=metaData.generateMappingForType(type) | |
| author=getTextFromNode(dom.xpath("//bib/%s"%hash['author'][0])[0]) | logging.error("documentViewer (accessOK) unknown access type %s"%access) |
| title=getTextFromNode(dom.xpath("//bib/%s"%hash['title'][0])[0]) | return False |
| year=getTextFromNode(dom.xpath("//bib/%s"%hash['year'][0])[0]) | |
| return author,title,year | |
| def text(self,mode,url,pn): | |
| """give text""" | |
| if mode=="texttool": #index.meta with texttool information | |
| (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) | |
| print textpath | def getDocinfo(self, mode, url): |
| try: | """returns docinfo depending on mode""" |
| dom = NonvalidatingReader.parseUri(textpath) | logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) |
| except: | # look for cached docinfo in session |
| return None | 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', None) == mode and docinfo.get('url', None) == url: | |
| logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
| return docinfo | |
| # new docinfo | |
| docinfo = {'mode': mode, 'url': url} | |
| # add self url | |
| docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
| docinfo['digilibBaseUrl'] = self.digilibBaseUrl | |
| # get index.meta DOM | |
| docUrl = None | |
| metaDom = None | |
| if mode=="texttool": | |
| # url points to document dir or index.meta | |
| metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
| docUrl = url.replace('/index.meta', '') | |
| if metaDom is None: | |
| raise IOError("Unable to find index.meta for mode=texttool!") | |
| list=[] | elif mode=="imagepath": |
| nodes=dom.xpath("//pb") | # url points to folder with images, index.meta optional |
| # asssume index.meta in parent dir | |
| docUrl = getParentPath(url) | |
| metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| elif mode=="filepath": | |
| # url points to image file, index.meta optional | |
| # asssume index.meta is two path segments up | |
| docUrl = getParentPath(url, 2) | |
| metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| node=nodes[int(pn)-1] | else: |
| logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
| raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
| p=node | docinfo['documentUrl'] = docUrl |
| # process index.meta contents | |
| if metaDom is not None and metaDom.tag == 'resource': | |
| # document directory name and path | |
| resource = self.metadataService.getResourceData(dom=metaDom) | |
| if resource: | |
| docinfo = self.getDocinfoFromResource(docinfo, resource) | |
| # texttool info | |
| texttool = self.metadataService.getTexttoolData(dom=metaDom) | |
| if texttool: | |
| docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
| # bib info | |
| bib = self.metadataService.getBibData(dom=metaDom) | |
| if bib: | |
| docinfo = self.getDocinfoFromBib(docinfo, bib) | |
| else: | |
| # no bib - try info.xml | |
| docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) | |
| while p.tagName!="p": | # auth info |
| p=p.parentNode | access = self.metadataService.getAccessData(dom=metaDom) |
| if access: | |
| docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| # attribution info | |
| attribution = self.metadataService.getAttributionData(dom=metaDom) | |
| if attribution: | |
| logging.debug("getDocinfo: attribution=%s"%repr(attribution)) | |
| docinfo['attribution'] = attribution | |
| #docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| # copyright info | |
| copyright = self.metadataService.getCopyrightData(dom=metaDom) | |
| if copyright: | |
| logging.debug("getDocinfo: copyright=%s"%repr(copyright)) | |
| docinfo['copyright'] = copyright | |
| #docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| # image path | |
| if mode != 'texttool': | |
| # override image path from texttool with url | |
| docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1) | |
| endNode=nodes[int(pn)] | |
| # number of images from digilib | |
| if docinfo.get('imagePath', None): | |
| docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath'] | |
| docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath']) | |
| 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 getDocinfoFromResource(self, docinfo, resource): | |
| """reads contents of resource element into docinfo""" | |
| docName = resource.get('name', None) | |
| docinfo['documentName'] = docName | |
| docPath = resource.get('archive-path', None) | |
| if docPath: | |
| # clean up document path | |
| if docPath[0] != '/': | |
| docPath = '/' + docPath | |
| e=endNode | if docName and (not docPath.endswith(docName)): |
| docPath += "/" + docName | |
| else: | |
| # use docUrl as docPath | |
| docUrl = docinfo['documentURL'] | |
| if not docUrl.startswith('http:'): | |
| docPath = docUrl | |
| if docPath: | |
| # fix URLs starting with /mpiwg/online | |
| docPath = docPath.replace('/mpiwg/online', '', 1) | |
| docinfo['documentPath'] = docPath | |
| return docinfo | |
| def getDocinfoFromTexttool(self, docinfo, texttool): | |
| """reads contents of texttool element into docinfo""" | |
| # image dir | |
| imageDir = texttool.get('image', None) | |
| docPath = docinfo.get('documentPath', None) | |
| if imageDir and docPath: | |
| #print "image: ", imageDir, " archivepath: ", archivePath | |
| imageDir = os.path.join(docPath, imageDir) | |
| imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
| docinfo['imagePath'] = imageDir | |
| # old style text URL | |
| textUrl = texttool.get('text', None) | |
| if textUrl and docPath: | |
| if urlparse.urlparse(textUrl)[0] == "": #keine url | |
| textUrl = os.path.join(docPath, textUrl) | |
| docinfo['textURL'] = textUrl | |
| # new style text-url-path | |
| textUrl = texttool.get('text-url-path', None) | |
| if textUrl: | |
| docinfo['textURLPath'] = textUrl | |
| # page flow | |
| docinfo['pageFlow'] = texttool.get('page-flow', 'ltr') | |
| # odd pages are left | |
| docinfo['oddPage'] = texttool.get('odd-scan-position', 'left') | |
| # number of title page (0: not defined) | |
| docinfo['titlePage'] = texttool.get('title-scan-no', 0) | |
| # old presentation stuff | |
| presentation = texttool.get('presentation', None) | |
| if presentation and docPath: | |
| if presentation.startswith('http:'): | |
| docinfo['presentationUrl'] = presentation | |
| else: | |
| docinfo['presentationUrl'] = os.path.join(docPath, presentation) | |
| while e.tagName!="p": | |
| e=e.parentNode | |
| return docinfo | |
| next=node.parentNode | def getDocinfoFromBib(self, docinfo, bib): |
| """reads contents of bib element into docinfo""" | |
| logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) | |
| # put all raw bib fields in dict "bib" | |
| docinfo['bib'] = bib | |
| bibtype = bib.get('@type', None) | |
| docinfo['bibType'] = bibtype | |
| # also store DC metadata for convenience | |
| dc = self.metadataService.getDCMappedData(bib) | |
| docinfo['creator'] = dc.get('creator',None) | |
| docinfo['title'] = dc.get('title',None) | |
| docinfo['date'] = dc.get('date',None) | |
| return docinfo | |
| def getDocinfoFromAccess(self, docinfo, acc): | |
| """reads contents of access element into docinfo""" | |
| #TODO: also read resource type | |
| logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) | |
| try: | |
| acctype = acc['@attr']['type'] | |
| if acctype: | |
| access=acctype | |
| if access in ['group', 'institution']: | |
| access = acc['name'].lower() | |
| #sammle s | docinfo['accessType'] = access |
| while next and (next!=endNode.parentNode): | |
| list.append(next) | |
| next=next.nextSibling | |
| list.append(endNode.parentNode) | |
| if p==e:# beide im selben paragraphen | except: |
| pass | pass |
| # else: | |
| # next=p | |
| # while next!=e: | |
| # print next,e | |
| # list.append(next) | |
| # next=next.nextSibling | |
| # | |
| # for x in list: | |
| # PrettyPrint(x) | |
| # | |
| # return list | |
| # | |
| def image(self,mode,url,pn): | |
| """give image out""" | |
| if mode=="texttool": #index.meta with texttool information | |
| (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) | |
| if not viewerUrl: | |
| viewerUrl=self.imageViewerUrl | |
| url=viewerUrl+"pn=%s&fn=%s"%(pn,imagepath[0]) | |
| ret="""<iframe height="100%%" width="100%%" src="%s"/>"""%url | |
| return url | |
| elif mode=="imagepath": | |
| url=url.replace("/mpiwg/online","") | |
| url=self.imageViewerUrl+"pn=%s&fn=%s"%(pn,url) | |
| ret="""<iframe height="100%%" width="100%%" src="%s"/>"""%url | |
| return url | |
| return docinfo | |
| def thumbs(self,mode,url,start): | def getDocinfoFromDigilib(self, docinfo, path): |
| """give thumbs out""" | infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
| if mode=="texttool": #index.meta with texttool information | # fetch data |
| return self.textToolThumb(url,int(start)) | txt = getHttpData(infoUrl) |
| elif mode=="imagepath": | if not txt: |
| return self.imagePathThumb(url,int(start)) | logging.error("Unable to get dir-info from %s"%(infoUrl)) |
| return docinfo | |
| dom = ET.fromstring(txt) | |
| size = getText(dom.find("size")) | |
| logging.debug("getDocinfoFromDigilib: size=%s"%size) | |
| if size: | |
| docinfo['numPages'] = int(size) | |
| else: | |
| docinfo['numPages'] = 0 | |
| security.declareProtected('View','index_html') | # TODO: produce and keep list of image names and numbers |
| return docinfo | |
| def index_html(self,mode,url,start=0,pn=1): | def getDocinfoFromPresentationInfoXml(self,docinfo): |
| ''' | """gets DC-like bibliographical information from the presentation entry in texttools""" |
| view it | url = docinfo.get('presentationUrl', None) |
| @param mode: defines which type of document is behind url | if not url: |
| @param url: url which contains display information | logging.error("getDocinfoFromPresentation: no URL!") |
| ''' | return docinfo |
| dom = None | |
| metaUrl = None | |
| if url.startswith("http://"): | |
| # real URL | |
| metaUrl = url | |
| else: | |
| # online path | |
| server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| metaUrl=server+url | |
| pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','documentViewer_template.zpt')).__of__(self) | txt=getHttpData(metaUrl) |
| return pt(mode=mode,url=url,start=start,pn=pn) | if txt is None: |
| logging.error("Unable to read info.xml from %s"%(url)) | |
| return docinfo | |
| dom = ET.fromstring(txt) | |
| docinfo['creator']=getText(dom.find(".//author")) | |
| docinfo['title']=getText(dom.find(".//title")) | |
| docinfo['date']=getText(dom.find(".//date")) | |
| return docinfo | |
| def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None): | |
| """returns pageinfo with the given parameters""" | |
| pageinfo = {} | |
| pageinfo['viewMode'] = viewMode | |
| pageinfo['viewType'] = viewType | |
| pageinfo['tocMode'] = tocMode | |
| 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 | |
| # is start is empty use one around current | |
| start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) | |
| # int(current / grpsize) * grpsize +1)) | |
| pageinfo['start'] = start | |
| pn = self.REQUEST.get('pn','1') | |
| pageinfo['pn'] = pn | |
| np = int(docinfo.get('numPages', 0)) | |
| if np == 0: | |
| # numPages unknown - maybe we can get it from text page | |
| if docinfo.get('textURLPath', None): | |
| # cache text page as well | |
| pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=pn, docinfo=docinfo, pageinfo=pageinfo) | |
| np = int(docinfo.get('numPages', 0)) | |
| pageinfo['numgroups'] = int(np / grpsize) | |
| if np % grpsize > 0: | |
| pageinfo['numgroups'] += 1 | |
| pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' | |
| oddScanLeft = docinfo.get('oddPage', 'left') != 'right' | |
| # add zeroth page for two columns | |
| pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) | |
| pageinfo['pageZero'] = pageZero | |
| pageinfo['pageList'] = self.getPageList(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np) | |
| pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') | |
| pageinfo['query'] = self.REQUEST.get('query','') | |
| pageinfo['queryType'] = self.REQUEST.get('queryType','') | |
| pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') | |
| pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') | |
| pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) | |
| pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10)) | |
| pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1')) | |
| pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1')) | |
| # limit tocPN | |
| if 'tocSize_%s'%tocMode in docinfo: | |
| tocSize = docinfo['tocSize_%s'%tocMode] | |
| tocPageSize = pageinfo['tocPageSize'] | |
| # cached toc | |
| if tocSize%tocPageSize>0: | |
| tocPages=tocSize/tocPageSize+1 | |
| else: | |
| tocPages=tocSize/tocPageSize | |
| pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN']) | |
| return pageinfo | |
| # security.declareProtected('View management screens','renameImageForm') | |
| def getPageList(self, start=None, rows=None, cols=None, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0): | |
| """returns array of page informations for one screenfull of thumbnails""" | |
| if maxIdx == 0: | |
| maxIdx = start + rows * cols | |
| pages = [] | |
| if pageZero and start == 1: | |
| # correct beginning | |
| idx = 0 | |
| else: | |
| idx = start | |
| for r in range(rows): | |
| row = [] | |
| for c in range(cols): | |
| if idx < minIdx or idx > maxIdx: | |
| page = {'idx':None} | |
| else: | |
| page = {'idx':idx} | |
| idx += 1 | |
| if pageFlowLtr: | |
| row.append(page) | |
| else: | |
| row.insert(0, page) | |
| pages.append(row) | |
| logging.debug("getPageList returns=%s"%(pages)) | |
| return pages | |
| security.declareProtected('View management screens','changeDocumentViewerForm') | |
| changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 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(',')] | |
| try: | |
| # assume MetaDataFolder instance is called metadata | |
| self.metadataService = getattr(self, 'metadata') | |
| except Exception, e: | |
| logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 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 '' | |