|
|
| version 1.56, 2010/05/20 14:19:31 | version 1.69.2.3, 2010/06/16 18:27:04 |
|---|---|
| Line 13 from Ft.Xml import EMPTY_NAMESPACE, Pars | Line 13 from Ft.Xml import EMPTY_NAMESPACE, Pars |
| from xml.dom.minidom import parse, parseString | from xml.dom.minidom import parse, parseString |
| from extraFunction import * | |
| import Ft.Xml.XPath | import Ft.Xml.XPath |
| Line 65 def getParentDir(path): | Line 66 def getParentDir(path): |
| return '/'.join(path.split('/')[0:-1]) | return '/'.join(path.split('/')[0:-1]) |
| def getHttpData(url, data=None, num_tries=3, timeout=10): | |
| """returns result from url+data HTTP request""" | |
| # we do GET (by appending data to url) | |
| if isinstance(data, str) or isinstance(data, unicode): | |
| # if data is string then append | |
| url = "%s?%s"%(url,data) | |
| elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): | |
| # urlencode | |
| url = "%s?%s"%(url,urllib.urlencode(data)) | |
| response = None | |
| errmsg = None | |
| for cnt in range(num_tries): | |
| try: | |
| logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) | |
| if sys.version_info < (2, 6): | |
| # set timeout on socket -- ugly :-( | |
| import socket | import socket |
| def urlopen(url,timeout=2): | |
| """urlopen mit timeout""" | |
| socket.setdefaulttimeout(timeout) | socket.setdefaulttimeout(timeout) |
| ret=urllib.urlopen(url) | response = urllib2.urlopen(url) |
| socket.setdefaulttimeout(5) | else: |
| return ret | response = urllib2.urlopen(url,timeout=float(timeout)) |
| # check result? | |
| break | |
| except urllib2.HTTPError, e: | |
| logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) | |
| errmsg = str(e) | |
| # stop trying | |
| break | |
| except urllib2.URLError, e: | |
| logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) | |
| errmsg = str(e) | |
| # stop trying | |
| #break | |
| if response is not None: | |
| data = response.read() | |
| response.close() | |
| return data | |
| raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) | |
| #return None | |
| ## | ## |
| Line 80 def urlopen(url,timeout=2): | Line 116 def urlopen(url,timeout=2): |
| ## | ## |
| class documentViewer(Folder): | class documentViewer(Folder): |
| """document viewer""" | """document viewer""" |
| #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" | |
| meta_type="Document viewer" | meta_type="Document viewer" |
| security=ClassSecurityInfo() | security=ClassSecurityInfo() |
| Line 102 class documentViewer(Folder): | Line 136 class documentViewer(Folder): |
| 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()) |
| thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) | thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
| security.declareProtected('View management screens','changeDocumentViewerForm') | security.declareProtected('View management screens','changeDocumentViewerForm') |
| changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
| Line 121 class documentViewer(Folder): | Line 156 class documentViewer(Folder): |
| #self['template'] = templateFolder # Zope-2.12 style | #self['template'] = templateFolder # Zope-2.12 style |
| self._setObject('template',templateFolder) # old style | self._setObject('template',templateFolder) # old style |
| try: | try: |
| from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy | import MpdlXmlTextServer |
| xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False) | textServer = MpdlXmlTextServer(id='fulltextclient') |
| #templateFolder['fulltextclient'] = xmlRpcClient | #templateFolder['fulltextclient'] = xmlRpcClient |
| templateFolder._setObject('fulltextclient',xmlRpcClient) | templateFolder._setObject('fulltextclient',textServer) |
| except Exception, e: | except Exception, e: |
| logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e)) | logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
| try: | try: |
| from Products.zogiLib.zogiLib import zogiLib | from Products.zogiLib.zogiLib import zogiLib |
| zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") | zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
| Line 136 class documentViewer(Folder): | Line 171 class documentViewer(Folder): |
| logging.error("Unable to create zogiLib for zogilib: "+str(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 getQuery(self, **args): | |
| """get query""" | |
| return self.template.fulltextclient.getQuery(**args) | |
| def getSearch(self, **args): | |
| """get search""" | |
| return self.template.fulltextclient.getSearch(**args) | |
| def getNumPages(self, **args): | |
| """get numpages""" | |
| return self.template.fulltextclient.getNumPages(**args) | |
| def getTranslate(self, **args): | |
| """get translate""" | |
| return self.template.fulltextclient.getTranslate(**args) | |
| def getLemma(self, **args): | |
| """get lemma""" | |
| return self.template.fulltextclient.getLemma(**args) | |
| def getToc(self, **args): | |
| """get toc""" | |
| return self.template.fulltextclient.getToc(**args) | |
| def getTocPage(self, **args): | |
| """get tocpage""" | |
| return self.template.fulltextclient.getTocPage(**args) | |
| security.declareProtected('View','thumbs_rss') | security.declareProtected('View','thumbs_rss') |
| def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): |
| ''' | ''' |
| Line 195 class documentViewer(Folder): | Line 264 class documentViewer(Folder): |
| # get table of contents | # get table of contents |
| docinfo = self.getToc(mode=tocMode, docinfo=docinfo) | docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
| pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) | |
| if viewMode=="auto": # automodus gewaehlt | if viewMode=="auto": # automodus gewaehlt |
| if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert | if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert |
| viewMode="text" | viewMode="text_dict" |
| else: | else: |
| viewMode="images" | viewMode="images" |
| pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) | |
| pt = getattr(self.template, 'viewer_main') | pt = getattr(self.template, 'viewer_main') |
| return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
| Line 222 class documentViewer(Folder): | Line 291 class documentViewer(Folder): |
| url = self.template.zogilib.getDLBaseUrl() | url = self.template.zogilib.getDLBaseUrl() |
| return url | return url |
| def getDocumentViewerURL(self): | |
| """returns the URL of this instance""" | |
| return self.absolute_url() | |
| def getStyle(self, idx, selected, style=""): | def getStyle(self, idx, selected, style=""): |
| """returns a string with the given style and append 'sel' if path == selected.""" | """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)) | #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
| Line 260 class documentViewer(Folder): | Line 333 class documentViewer(Folder): |
| params[param] = str(val) | params[param] = str(val) |
| # quote values and assemble into query string | # quote values and assemble into query string |
| logging.info("XYXXXXX: %s"%repr(params.items())) | logging.debug("XYXXXXX: %s"%repr(params.items())) |
| ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
| url=self.REQUEST['URL1']+"?"+ps | url=self.REQUEST['URL1']+"?"+ps |
| return url | return url |
| Line 279 class documentViewer(Folder): | Line 352 class documentViewer(Folder): |
| 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) |
| logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) | logging.debug("documentViewer (accessOK) access type %s"%access) |
| if access is not None and access == 'free': | if access is not None and access == 'free': |
| logger("documentViewer (accessOK)", logging.INFO, "access is free") | logging.debug("documentViewer (accessOK) access is free") |
| return True | return True |
| elif access is None or access in self.authgroups: | elif access is None or access in self.authgroups: |
| # only local access -- only logged in users | # only local access -- only logged in users |
| Line 292 class documentViewer(Folder): | Line 365 class documentViewer(Folder): |
| else: | else: |
| return False | return False |
| logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) | logging.debug("documentViewer (accessOK) unknown access type %s"%access) |
| return False | return False |
| def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): | def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
| """gibt param von dlInfo aus""" | """gibt param von dlInfo aus""" |
| num_retries = 3 | |
| if docinfo is None: | if docinfo is None: |
| docinfo = {} | docinfo = {} |
| Line 308 class documentViewer(Folder): | Line 380 class documentViewer(Folder): |
| infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path | infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
| logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) | logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) |
| for cnt in range(num_retries): | txt = getHttpData(infoUrl) |
| try: | if txt is None: |
| # dom = NonvalidatingReader.parseUri(imageUrl) | |
| txt=urllib.urlopen(infoUrl).read() | |
| dom = Parse(txt) | |
| break | |
| except: | |
| logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) | |
| else: | |
| raise IOError("Unable to get dir-info from %s"%(infoUrl)) | raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
| dom = Parse(txt) | |
| sizes=dom.xpath("//dir/size") | sizes=dom.xpath("//dir/size") |
| logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) | logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) |
| if sizes: | if sizes: |
| docinfo['numPages'] = int(getTextFromNode(sizes[0])) | docinfo['numPages'] = int(getTextFromNode(sizes[0])) |
| Line 336 class documentViewer(Folder): | Line 402 class documentViewer(Folder): |
| def getIndexMeta(self, url): | def getIndexMeta(self, url): |
| """returns dom of index.meta document at url""" | """returns dom of index.meta document at url""" |
| num_retries = 3 | |
| dom = None | dom = None |
| metaUrl = None | metaUrl = None |
| if url.startswith("http://"): | if url.startswith("http://"): |
| Line 348 class documentViewer(Folder): | Line 413 class documentViewer(Folder): |
| metaUrl=server+url.replace("/mpiwg/online","") | metaUrl=server+url.replace("/mpiwg/online","") |
| if not metaUrl.endswith("index.meta"): | if not metaUrl.endswith("index.meta"): |
| metaUrl += "/index.meta" | metaUrl += "/index.meta" |
| logging.debug("METAURL: %s"%metaUrl) | |
| for cnt in range(num_retries): | |
| try: | |
| # patch dirk encoding fehler treten dann nicht mehr auf | |
| # dom = NonvalidatingReader.parseUri(metaUrl) | |
| txt=urllib.urlopen(metaUrl).read() | |
| dom = Parse(txt) | |
| break | |
| except: | |
| logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) | |
| if dom is None: | logging.debug("(getIndexMeta): METAURL: %s"%metaUrl) |
| txt=getHttpData(metaUrl) | |
| if txt is None: | |
| raise IOError("Unable to read index meta from %s"%(url)) | raise IOError("Unable to read index meta from %s"%(url)) |
| dom = Parse(txt) | |
| return dom | return dom |
| def getPresentationInfoXML(self, url): | def getPresentationInfoXML(self, url): |
| """returns dom of info.xml document at url""" | """returns dom of info.xml document at url""" |
| num_retries = 3 | |
| dom = None | dom = None |
| metaUrl = None | metaUrl = None |
| if url.startswith("http://"): | if url.startswith("http://"): |
| Line 377 class documentViewer(Folder): | Line 434 class documentViewer(Folder): |
| server=self.digilibBaseUrl+"/servlet/Texter?fn=" | server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
| metaUrl=server+url.replace("/mpiwg/online","") | metaUrl=server+url.replace("/mpiwg/online","") |
| for cnt in range(num_retries): | txt=getHttpData(metaUrl) |
| try: | if txt is None: |
| # patch dirk encoding fehler treten dann nicht mehr auf | |
| # dom = NonvalidatingReader.parseUri(metaUrl) | |
| txt=urllib.urlopen(metaUrl).read() | |
| dom = Parse(txt) | |
| break | |
| except: | |
| logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) | |
| if dom is None: | |
| raise IOError("Unable to read infoXMLfrom %s"%(url)) | raise IOError("Unable to read infoXMLfrom %s"%(url)) |
| dom = Parse(txt) | |
| return dom | return dom |
| def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): | def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
| """gets authorization info from the index.meta file at path or given by dom""" | """gets authorization info from the index.meta file at path or given by dom""" |
| logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) | logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) |
| access = None | access = None |
| Line 471 class documentViewer(Folder): | Line 520 class documentViewer(Folder): |
| 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)) | logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) |
| if docinfo is None: | if docinfo is None: |
| docinfo = {} | docinfo = {} |
| if docinfo.get('lang', None) is None: | if docinfo.get('lang', None) is None: |
| Line 486 class documentViewer(Folder): | Line 535 class documentViewer(Folder): |
| if archiveNames and (len(archiveNames) > 0): | if archiveNames and (len(archiveNames) > 0): |
| archiveName = getTextFromNode(archiveNames[0]) | archiveName = getTextFromNode(archiveNames[0]) |
| else: | else: |
| logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url)) | logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) |
| archivePaths = dom.xpath("//resource/archive-path") | archivePaths = dom.xpath("//resource/archive-path") |
| if archivePaths and (len(archivePaths) > 0): | if archivePaths and (len(archivePaths) > 0): |
| Line 498 class documentViewer(Folder): | Line 547 class documentViewer(Folder): |
| archivePath += "/" + archiveName | archivePath += "/" + archiveName |
| else: | else: |
| # try to get archive-path from url | # try to get archive-path from url |
| logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url)) | logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url)) |
| if (not url.startswith('http')): | if (not url.startswith('http')): |
| archivePath = url.replace('index.meta', '') | archivePath = url.replace('index.meta', '') |
| Line 590 class documentViewer(Folder): | Line 639 class documentViewer(Folder): |
| def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): | 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.""" | """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
| logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) | logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) |
| if docinfo is None: | if docinfo is None: |
| docinfo = {} | docinfo = {} |
| path=path.replace("/mpiwg/online","") | path=path.replace("/mpiwg/online","") |
| Line 600 class documentViewer(Folder): | Line 649 class documentViewer(Folder): |
| pathorig=path | pathorig=path |
| for x in range(cut): | for x in range(cut): |
| path=getParentDir(path) | path=getParentDir(path) |
| logging.error("PATH:"+path) | logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) |
| imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path | imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
| docinfo['imageURL'] = imageUrl | docinfo['imageURL'] = imageUrl |
| Line 612 class documentViewer(Folder): | Line 661 class documentViewer(Folder): |
| def getDocinfo(self, mode, url): | def getDocinfo(self, mode, url): |
| """returns docinfo depending on mode""" | """returns docinfo depending on mode""" |
| logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) | logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) |
| # look for cached docinfo in session | # look for cached docinfo in session |
| if self.REQUEST.SESSION.has_key('docinfo'): | if self.REQUEST.SESSION.has_key('docinfo'): |
| docinfo = self.REQUEST.SESSION['docinfo'] | docinfo = self.REQUEST.SESSION['docinfo'] |
| # check if its still current | # check if its still current |
| if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: |
| logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) | logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) |
| return docinfo | return docinfo |
| # new docinfo | # new docinfo |
| docinfo = {'mode': mode, 'url': url} | docinfo = {'mode': mode, 'url': url} |
| Line 629 class documentViewer(Folder): | Line 678 class documentViewer(Folder): |
| elif mode=="filepath": | elif mode=="filepath": |
| docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) | docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
| else: | else: |
| logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") | logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
| raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
| logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) | logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
| self.REQUEST.SESSION['docinfo'] = docinfo | self.REQUEST.SESSION['docinfo'] = docinfo |
| return docinfo | return docinfo |
| def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): | def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): |
| """returns pageinfo with the given parameters""" | """returns pageinfo with the given parameters""" |
| pageinfo = {} | pageinfo = {} |
| Line 658 class documentViewer(Folder): | Line 706 class documentViewer(Folder): |
| pageinfo['numgroups'] = int(np / grpsize) | pageinfo['numgroups'] = int(np / grpsize) |
| if np % grpsize > 0: | if np % grpsize > 0: |
| pageinfo['numgroups'] += 1 | pageinfo['numgroups'] += 1 |
| pageinfo['viewMode'] = viewMode | pageinfo['viewMode'] = viewMode |
| pageinfo['tocMode'] = tocMode | pageinfo['tocMode'] = tocMode |
| pageinfo['query'] = self.REQUEST.get('query',' ') | pageinfo['query'] = self.REQUEST.get('query',' ') |
| pageinfo['queryType'] = self.REQUEST.get('queryType',' ') | pageinfo['queryType'] = self.REQUEST.get('queryType',' ') |
| pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') | pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
| pageinfo['textPN'] = self.REQUEST.get('textPN','1') | pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
| pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') | pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
| pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') | pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
| Line 678 class documentViewer(Folder): | Line 723 class documentViewer(Folder): |
| tocSize = int(docinfo['tocSize_%s'%tocMode]) | tocSize = int(docinfo['tocSize_%s'%tocMode]) |
| tocPageSize = int(pageinfo['tocPageSize']) | tocPageSize = int(pageinfo['tocPageSize']) |
| # cached toc | # cached toc |
| if tocSize%tocPageSize>0: | if tocSize%tocPageSize>0: |
| tocPages=tocSize/tocPageSize+1 | tocPages=tocSize/tocPageSize+1 |
| else: | else: |
| tocPages=tocSize/tocPageSize | tocPages=tocSize/tocPageSize |
| pageinfo['tocPN'] = min (tocPages,toc) | pageinfo['tocPN'] = min (tocPages,toc) |
| pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') | pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
| pageinfo['sn'] =self.REQUEST.get('sn','1') | pageinfo['sn'] =self.REQUEST.get('sn','') |
| return pageinfo | return pageinfo |
| def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None): | |
| """get search list""" | |
| docpath = docinfo['textURLPath'] | |
| url = docinfo['url'] | |
| logging.debug("documentViewer (gettoc) docpath: %s"%(docpath)) | |
| logging.debug("documentViewer (gettoc) url: %s"%(url)) | |
| pagesize = pageinfo['queryPageSize'] | |
| pn = pageinfo['searchPN'] | |
| sn = pageinfo['sn'] | |
| highlightQuery = pageinfo['highlightQuery'] | |
| query =pageinfo['query'] | |
| queryType =pageinfo['queryType'] | |
| viewMode= pageinfo['viewMode'] | |
| tocMode = pageinfo['tocMode'] | |
| tocPN = pageinfo['tocPN'] | |
| selfurl = self.absolute_url() | |
| # logging.debug("documentViewer (gettoc) /mpdl/interface/doc-query.xql?document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode)) | |
| page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False) | |
| pagexml = page.replace('?document=%s'%str(docpath),'?url=%s'%url) | |
| pagedom = Parse(pagexml) | |
| if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"): | |
| pagedivs = pagedom.xpath("//div[@class='queryResultPage']") | |
| if len(pagedivs)>0: | |
| pagenode=pagedivs[0] | |
| links=pagenode.xpath("//a") | |
| for l in links: | |
| hrefNode = l.getAttributeNodeNS(None, u"href") | |
| if hrefNode: | |
| href = hrefNode.nodeValue | |
| if href.startswith('page-fragment.xql'): | |
| selfurl = self.absolute_url() | |
| #l.setAttributeNS(None, "span class = 'hit highlight'", "background-color: #77DD77;") | |
| pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN)) | |
| hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) | |
| l.setAttributeNS(None, "onClick", "id='highlighting'") | |
| logging.debug("documentViewer (gettoc) highlightQuery: %s"%(highlightQuery)) | |
| l.setAttributeNS(None, highlightQuery, "id='highlighting'") | |
| return serializeNode(pagenode) | |
| if (queryType=="fulltextMorph"): | |
| pagedivs = pagedom.xpath("//div[@class='queryResult']") | |
| if len(pagedivs)>0: | |
| pagenode=pagedivs[0] | |
| links=pagenode.xpath("//a") | |
| for l in links: | |
| hrefNode = l.getAttributeNodeNS(None, u"href") | |
| if hrefNode: | |
| href = hrefNode.nodeValue | |
| if href.startswith('page-fragment.xql'): | |
| selfurl = self.absolute_url() | |
| pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN)) | |
| hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) | |
| if href.startswith('../lt/lemma.xql'): | |
| selfurl = self.absolute_url() | |
| hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) | |
| l.setAttributeNS(None, 'target', '_blank') | |
| l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") | |
| l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
| return serializeNode(pagenode) | |
| if (queryType=="ftIndex")or(queryType=="ftIndexMorph"): | |
| pagedivs= pagedom.xpath("//div[@class='queryResultPage']") | |
| if len(pagedivs)>0: | |
| pagenode=pagedivs[0] | |
| links=pagenode.xpath("//a") | |
| for l in links: | |
| hrefNode = l.getAttributeNodeNS(None, u"href") | |
| if hrefNode: | |
| href = hrefNode.nodeValue | |
| hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn)) | |
| if href.startswith('../lt/lex.xql'): | |
| # selfurl = self.absolute_url() | |
| hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl) | |
| l.setAttributeNS(None, 'target', '_blank') | |
| l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") | |
| l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
| if href.startswith('../lt/lemma.xql'): | |
| #selfurl = self.absolute_url() | |
| hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl) | |
| l.setAttributeNS(None, 'target', '_blank') | |
| l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") | |
| l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
| return serializeNode(pagenode) | |
| return "no text here" | |
| def getNumPages(self,docinfo=None): | |
| """get list of pages from fulltext and put in docinfo""" | |
| 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 | |
| def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None,): | |
| """returns single page from fulltext""" | |
| docpath = docinfo['textURLPath'] | |
| if mode == "text_dict": | |
| textmode = "textPollux" | |
| else: | |
| textmode = mode | |
| #selfurl = self.absolute_url() | |
| #viewMode= pageinfo['viewMode'] | |
| #tocMode = pageinfo['tocMode'] | |
| #tocPN = pageinfo['tocPN'] | |
| pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False) | |
| # post-processing downloaded xml | |
| pagedom = Parse(pagexml) | |
| # plain text mode | |
| if mode == "text": | |
| # first div contains text | |
| pagedivs = pagedom.xpath("/div") | |
| #queryResultPage | |
| if len(pagedivs) > 0: | |
| pagenode = pagedivs[0] | |
| links = pagenode.xpath("//a") | |
| for l in links: | |
| hrefNode = l.getAttributeNodeNS(None, u"href") | |
| if hrefNode: | |
| href= hrefNode.nodeValue | |
| if href.startswith('#note-0006-01'): | |
| selfurl = self.absolute_url() | |
| hrefNode.nodeValue = href.replace("href='#note-'",'xaxa/%s/'%selfurl) | |
| return serializeNode(pagenode) | |
| if mode == "xml": | |
| # first div contains text | |
| pagedivs = pagedom.xpath("/div") | |
| if len(pagedivs) > 0: | |
| pagenode = pagedivs[0] | |
| return serializeNode(pagenode) | |
| # text-with-links mode | |
| if mode == "text_dict": | |
| # first div contains text | |
| pagedivs = pagedom.xpath("/div") | |
| if len(pagedivs) > 0: | |
| pagenode = pagedivs[0] | |
| # check all a-tags | |
| links = pagenode.xpath("//a") | |
| for l in links: | |
| hrefNode = l.getAttributeNodeNS(None, u"href") | |
| if hrefNode: | |
| # is link with href | |
| href = hrefNode.nodeValue | |
| if href.startswith('lt/lex.xql'): | |
| # is pollux link | |
| selfurl = self.absolute_url() | |
| # change href | |
| hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl) | |
| # add target | |
| l.setAttributeNS(None, 'target', '_blank') | |
| l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") | |
| l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
| if href.startswith('lt/lemma.xql'): | |
| selfurl = self.absolute_url() | |
| hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) | |
| l.setAttributeNS(None, 'target', '_blank') | |
| l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") | |
| l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
| return serializeNode(pagenode) | |
| return "no text here" | |
| def getTranslate(self, query=None, language=None): | |
| """translate into another languages""" | |
| pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) | |
| return pagexml | |
| def getLemma(self, lemma=None, language=None): | |
| """simular words lemma """ | |
| pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) | |
| #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False) | |
| return pagexml | |
| def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1): | |
| """number of""" | |
| docpath = docinfo['textURLPath'] | |
| pagesize = pageinfo['queryPageSize'] | |
| pn = pageinfo['searchPN'] | |
| query =pageinfo['query'] | |
| queryType =pageinfo['queryType'] | |
| tocSearch = 0 | |
| tocDiv = None | |
| pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False) | |
| pagedom = Parse(pagexml) | |
| numdivs = pagedom.xpath("//div[@class='queryResultHits']") | |
| tocSearch = int(getTextFromNode(numdivs[0])) | |
| tc=int((tocSearch/10)+1) | |
| logging.debug("documentViewer (gettoc) tc: %s"%(tc)) | |
| return tc | |
| def getToc(self, mode="text", docinfo=None): | |
| """loads table of contents and stores in docinfo""" | |
| logging.debug("documentViewer (gettoc) mode: %s"%(mode)) | |
| if 'tocSize_%s'%mode in docinfo: | |
| # cached toc | |
| return docinfo | |
| docpath = docinfo['textURLPath'] | |
| # we need to set a result set size | |
| pagesize = 1000 | |
| pn = 1 | |
| if mode == "text": | |
| queryType = "toc" | |
| else: | |
| queryType = mode | |
| # number of entries in toc | |
| tocSize = 0 | |
| tocDiv = None | |
| pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False) | |
| # post-processing downloaded xml | |
| pagedom = Parse(pagexml) | |
| # get number of entries | |
| numdivs = pagedom.xpath("//div[@class='queryResultHits']") | |
| if len(numdivs) > 0: | |
| tocSize = int(getTextFromNode(numdivs[0])) | |
| # div contains text | |
| #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") | |
| #if len(pagedivs) > 0: | |
| # tocDiv = pagedivs[0] | |
| docinfo['tocSize_%s'%mode] = tocSize | |
| #docinfo['tocDiv_%s'%mode] = tocDiv | |
| return docinfo | |
| def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None): | |
| """returns single page from the table of contents""" | |
| # TODO: this should use the cached TOC | |
| if mode == "text": | |
| queryType = "toc" | |
| else: | |
| queryType = mode | |
| docpath = docinfo['textURLPath'] | |
| path = docinfo['textURLPath'] | |
| #logging.debug("documentViewer (gettoc) pathNomer: %s"%(pathNomer)) | |
| pagesize = pageinfo['tocPageSize'] | |
| pn = pageinfo['tocPN'] | |
| url = docinfo['url'] | |
| selfurl = self.absolute_url() | |
| viewMode= pageinfo['viewMode'] | |
| tocMode = pageinfo['tocMode'] | |
| tocPN = pageinfo['tocPN'] | |
| pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False) | |
| page = pagexml.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN)) | |
| text = page.replace('mode=image','mode=texttool') | |
| return text | |
| # post-processing downloaded xml | |
| #pagedom = Parse(text) | |
| # div contains text | |
| #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") | |
| #if len(pagedivs) > 0: | |
| # pagenode = pagedivs[0] | |
| # return serializeNode(pagenode) | |
| #else: | |
| # return "No TOC!" | |
| def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): | def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
| """init document viewer""" | """init document viewer""" |
| self.title=title | self.title=title |
| Line 963 class documentViewer(Folder): | Line 742 class documentViewer(Folder): |
| if RESPONSE is not None: | if RESPONSE is not None: |
| RESPONSE.redirect('manage_main') | RESPONSE.redirect('manage_main') |
| 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) |
| Line 978 def manage_AddDocumentViewer(self,id,ima | Line 755 def manage_AddDocumentViewer(self,id,ima |
| if RESPONSE is not None: | if RESPONSE is not None: |
| RESPONSE.redirect('manage_main') | RESPONSE.redirect('manage_main') |
| ## | |
| ## DocumentViewerTemplate class | ## DocumentViewerTemplate class |
| ## | |
| class DocumentViewerTemplate(ZopePageTemplate): | class DocumentViewerTemplate(ZopePageTemplate): |
| """Template for document viewer""" | """Template for document viewer""" |
| meta_type="DocumentViewer Template" | meta_type="DocumentViewer Template" |