|
|
| version 1.50, 2010/10/05 10:53:05 | version 1.199, 2010/10/26 14:44:55 |
|---|---|
| Line 38 class MpdlXmlTextServer(SimpleItem): | Line 38 class MpdlXmlTextServer(SimpleItem): |
| url = self.serverUrl+method | url = self.serverUrl+method |
| return documentViewer.getHttpData(url,data,timeout=self.timeout) | return documentViewer.getHttpData(url,data,timeout=self.timeout) |
| def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None): | def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None, characterNormalization=None): |
| """get search list""" | """get search list""" |
| docpath = docinfo['textURLPath'] | docpath = docinfo['textURLPath'] |
| url = docinfo['url'] | url = docinfo['url'] |
| logging.debug("documentViewer (gettoc) docpath: %s"%(docpath)) | |
| logging.debug("documentViewer (gettoc) url: %s"%(url)) | |
| pagesize = pageinfo['queryPageSize'] | pagesize = pageinfo['queryPageSize'] |
| pn = pageinfo['searchPN'] | pn = pageinfo['searchPN'] |
| sn = pageinfo['sn'] | sn = pageinfo['sn'] |
| Line 56 class MpdlXmlTextServer(SimpleItem): | Line 54 class MpdlXmlTextServer(SimpleItem): |
| tocPN = pageinfo['tocPN'] | tocPN = pageinfo['tocPN'] |
| selfurl = self.absolute_url() | selfurl = self.absolute_url() |
| data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,urllib.quote(highlightQuery))) | data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&characterNormalization=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization ,urllib.quote(highlightQuery))) |
| #page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False) | #page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False) |
| pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url) | pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url) |
| Line 118 class MpdlXmlTextServer(SimpleItem): | Line 116 class MpdlXmlTextServer(SimpleItem): |
| return serializeNode(pagenode) | return serializeNode(pagenode) |
| return "no text here" | return "no text here" |
| def getNumPages(self, docinfo): | """def getNumPages(self, docinfo): |
| """get list of pages from fulltext and put in docinfo""" | ""get list of pages from fulltext and put in docinfo"" |
| if 'numPages' in docinfo: | if 'numPages' in docinfo: |
| # already there | # already there |
| return docinfo | return docinfo |
| Line 127 class MpdlXmlTextServer(SimpleItem): | Line 125 class MpdlXmlTextServer(SimpleItem): |
| text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) | text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) |
| docinfo['numPages'] = text.count("<pb ") | docinfo['numPages'] = text.count("<pb ") |
| return docinfo | return docinfo |
| """ | |
| def getNumTextPages (self, docinfo): | def getNumTextPages (self, docinfo): |
| """get list of pages from fulltext (texts without images) and put in docinfo""" | """get list of pages from fulltext (texts without images) and put in docinfo""" |
| if 'numPages' in docinfo: | if 'numPages' in docinfo: |
| Line 135 class MpdlXmlTextServer(SimpleItem): | Line 133 class MpdlXmlTextServer(SimpleItem): |
| return docinfo | return docinfo |
| xpath ='/count(//pb)' | xpath ='/count(//pb)' |
| text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'], xpath)) | text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'], xpath)) |
| logging.debug("documentViewer (text) text: %s"%(text)) | dom = Parse(text) |
| #docinfo['numPages']=text('resultPage') | result= dom.xpath("//result/resultPage") |
| pagedom = Parse(text) | docinfo['numPages']=int(getTextFromNode(result[0])) |
| docinfo['numPages']= pagedom.xpath("//resultPage") | |
| logging.debug("documentViewer (characterNormalization) docinfo['numPages']: %s"%(docinfo['numPages'])) | |
| return docinfo | return docinfo |
| def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=""): | def getGisPlaces(self, docinfo=None, pageinfo=None): |
| """ Show all Gis Places of whole Page""" | |
| xpath='//place' | |
| docpath = docinfo['textURLPath'] | |
| url = docinfo['url'] | |
| selfurl = self.absolute_url() | |
| pn = pageinfo['current'] | |
| hrefList=[] | |
| myList= "" | |
| text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn)) | |
| dom = Parse(text) | |
| result = dom.xpath("//result/resultPage/place") | |
| for l in result: | |
| hrefNode= l.getAttributeNodeNS(None, u"id") | |
| href= hrefNode.nodeValue | |
| hrefList.append(href) | |
| myList = ",".join(hrefList) | |
| logging.debug("getGisPlaces :%s"%(myList)) | |
| return myList | |
| def getAllGisPlaces (self, docinfo=None, pageinfo=None): | |
| """Show all Gis Places of whole Book """ | |
| xpath ='//echo:place' | |
| docpath =docinfo['textURLPath'] | |
| url = docinfo['url'] | |
| selfurl =self.absolute_url() | |
| pn =pageinfo['current'] | |
| hrefList=[] | |
| myList="" | |
| text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath)) | |
| dom =Parse(text) | |
| result = dom.xpath("//result/resultPage/place") | |
| for l in result: | |
| hrefNode = l.getAttributeNodeNS(None, u"id") | |
| href= hrefNode.nodeValue | |
| hrefList.append(href) | |
| myList = ",".join(hrefList) | |
| logging.debug("getALLGisPlaces :%s"%(myList)) | |
| return myList | |
| def getOrigPages (self, docinfo=None, pageinfo=None): | |
| """Show original page """ | |
| docpath = docinfo['textURLPath'] | |
| #url = docinfo['url'] | |
| selfurl = self.absolute_url() | |
| pn =pageinfo['current'] | |
| viewMode= pageinfo['viewMode'] | |
| text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text', pn)) | |
| dom =Parse(text) | |
| pagedivs = dom.xpath("//div[@class='pageNumberOrig']") | |
| logging.debug("YYYYYYpagedivs :%s"%(pagedivs)) | |
| if len(pagedivs)>0: | |
| originalPage= getTextFromNode(pagedivs[0]) | |
| #return docinfo['originalPage'] | |
| return originalPage | |
| def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization="", highlightQuery=None, sn=None): | |
| """returns single page from fulltext""" | """returns single page from fulltext""" |
| docpath = docinfo['textURLPath'] | docpath = docinfo['textURLPath'] |
| path = docinfo['textURLPath'] | path = docinfo['textURLPath'] |
| url = docinfo['url'] | url = docinfo['url'] |
| name = docinfo['name'] | |
| viewMode= pageinfo['viewMode'] | viewMode= pageinfo['viewMode'] |
| sn = pageinfo['sn'] | |
| highlightQuery = pageinfo['highlightQuery'] | |
| tocMode = pageinfo['tocMode'] | tocMode = pageinfo['tocMode'] |
| characterNormalization=pageinfo['characterNormalization'] | characterNormalization=pageinfo['characterNormalization'] |
| tocPN = pageinfo['tocPN'] | tocPN = pageinfo['tocPN'] |
| Line 156 class MpdlXmlTextServer(SimpleItem): | Line 214 class MpdlXmlTextServer(SimpleItem): |
| textmode = "textPollux" | textmode = "textPollux" |
| else: | else: |
| textmode = mode | textmode = mode |
| #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization)) | #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery)) |
| textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization) | textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization) |
| if highlightQuery is not None: | if highlightQuery is not None: |
| textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn) | textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn) |
| #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery)) | |
| pagexml = self.getServerData("page-fragment.xql",textParam) | pagexml = self.getServerData("page-fragment.xql",textParam) |
| logging.debug("documentViewer highlightQuery: %s"%(highlightQuery)) | |
| #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False) | #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False) |
| pagedom = Parse(pagexml) | pagedom = Parse(pagexml) |
| Line 196 class MpdlXmlTextServer(SimpleItem): | Line 255 class MpdlXmlTextServer(SimpleItem): |
| if hrefNode: | if hrefNode: |
| href=hrefNode.nodeValue | href=hrefNode.nodeValue |
| if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'): | if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'): |
| hrefNode.nodeValue =href.replace('chinagis_REST','chinagis') | hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name) |
| l.setAttributeNS(None, 'target', '_blank') | l.setAttributeNS(None, 'target', '_blank') |
| return serializeNode(pagenode) | return serializeNode(pagenode) |