--- documentViewer/MpdlXmlTextServer.py 2010/10/26 14:44:55 1.199 +++ documentViewer/MpdlXmlTextServer.py 2010/12/23 17:13:01 1.221 @@ -38,7 +38,7 @@ class MpdlXmlTextServer(SimpleItem): url = self.serverUrl+method return documentViewer.getHttpData(url,data,timeout=self.timeout) - def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None, characterNormalization=None): + def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None, characterNormalization=None, optionToggle=None): """get search list""" docpath = docinfo['textURLPath'] url = docinfo['url'] @@ -51,10 +51,11 @@ class MpdlXmlTextServer(SimpleItem): viewMode= pageinfo['viewMode'] tocMode = pageinfo['tocMode'] characterNormalization = pageinfo['characterNormalization'] + optionToggle = pageinfo['optionToggle'] tocPN = pageinfo['tocPN'] 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&characterNormalization=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization ,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&optionToggle=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization,optionToggle ,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) pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url) @@ -70,7 +71,7 @@ class MpdlXmlTextServer(SimpleItem): 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,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN)) + pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&optionToggle=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,optionToggle,characterNormalization)) hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) return serializeNode(pagenode) if (queryType=="fulltextMorph"): @@ -84,7 +85,7 @@ class MpdlXmlTextServer(SimpleItem): 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,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN)) + pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&optionToggle=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,optionToggle,characterNormalization)) hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) if href.startswith('../lt/lemma.xql'): hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl)) @@ -102,7 +103,7 @@ class MpdlXmlTextServer(SimpleItem): 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)) + hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&optionToggle=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,optionToggle,characterNormalization)) if href.startswith('../lt/lex.xql'): hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl) l.setAttributeNS(None, 'target', '_blank') @@ -116,32 +117,43 @@ class MpdlXmlTextServer(SimpleItem): return serializeNode(pagenode) return "no text here" - """def getNumPages(self, docinfo): - ""get list of pages from fulltext and put in docinfo"" - if 'numPages' in docinfo: - # already there - return docinfo - xquery = '//pb' - text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) - docinfo['numPages'] = text.count("0: + docinfo['numPages']= int(getTextFromNode(pagedivs[0])) + return docinfo + + def getTocEntries (self, docinfo=None): + """ number of text entries""" + docinfo = self.getInfoFromPage(docinfo) + logging.debug("gettocentries: docinfo=%s"%docinfo) + return docinfo['tocEntries'] + + def getFigureEntries (self, docinfo=None): + """ number of figure entries""" + docinfo = self.getInfoFromPage(docinfo) + return docinfo['figureEntries'] + def getGisPlaces(self, docinfo=None, pageinfo=None): """ Show all Gis Places of whole Page""" xpath='//place' - docpath = docinfo['textURLPath'] + docpath = docinfo.get('textURLPath',None) + if not docpath: + return None + url = docinfo['url'] selfurl = self.absolute_url() pn = pageinfo['current'] @@ -170,6 +182,7 @@ class MpdlXmlTextServer(SimpleItem): 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 @@ -177,11 +190,12 @@ class MpdlXmlTextServer(SimpleItem): 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'] + docpath = docinfo.get('textURLPath',None) + if not docpath: + return None selfurl = self.absolute_url() pn =pageinfo['current'] @@ -189,14 +203,58 @@ class MpdlXmlTextServer(SimpleItem): 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): + def getAllPlaces (self, docinfo=None): + """Show all Places if no places than 0""" + docinfo = self.getInfoFromPage(docinfo) + return docinfo['allPlaces'] + + def getInfoFromPage(self, docinfo=None): + """ extract diverse info from page-fragment""" + docpath = docinfo['textURLPath'] + if 'allPlaces' in docinfo: + # allredy there + return docinfo + + if (docpath is not None): + text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath'])) + dom = Parse(text) + # figureEntries + pagedivs = dom.xpath("//div[@class='countFigureEntries']") + s = getTextFromNode(pagedivs[0]) + try: + docinfo['figureEntries'] = int(s) + except: + docinfo['figureEntries'] = 0 + # tocEntries + pagedivs = dom.xpath("//div[@class='countTocEntries']") + s = getTextFromNode(pagedivs[0]) + try: + docinfo['tocEntries'] = int(s) + except: + docinfo['tocEntries'] = 0 + # allPlaces + pagedivs = dom.xpath("//div[@class='countPlaces']") + s = getTextFromNode(pagedivs[0]) + try: + docinfo['allPlaces'] = int(s) + except: + docinfo['allPlaces'] = 0 + + else: + # no full text -- init to 0 + docinfo['figureEntries'] = 0 + docinfo['tocEntries'] = 0 + docinfo['allPlaces'] = 0 + + return docinfo + + + def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization="reg", highlightQuery=None, sn=None, optionToggle=None): """returns single page from fulltext""" docpath = docinfo['textURLPath'] path = docinfo['textURLPath'] @@ -316,7 +374,7 @@ class MpdlXmlTextServer(SimpleItem): #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query))) return data - def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1): + def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionToggle=None): """number of""" docpath = docinfo['textURLPath'] pagesize = pageinfo['queryPageSize'] @@ -331,10 +389,62 @@ class MpdlXmlTextServer(SimpleItem): pagedom = Parse(pagexml) numdivs = pagedom.xpath("//div[@class='queryResultHits']") tocSearch = int(getTextFromNode(numdivs[0])) + logging.debug("documentViewer (gettoc) tocSearch: %s"%(tocSearch)) tc=int((tocSearch/10)+1) logging.debug("documentViewer (gettoc) tc: %s"%(tc)) return tc + def getQueryResultHits(self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionsClose=None): + + """number of hits in Search mode""" + docpath = docinfo['textURLPath'] + pagesize = pageinfo['queryPageSize'] + pn = pageinfo['searchPN'] + query =pageinfo['query'] + queryType =pageinfo['queryType'] + tocSearch = 0 + tocDiv = None + + pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn)) + #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) + return tc + + def getQueryResultHitsText(self, docinfo=None, pageinfo=None): + """number of hits in Text of Contents mode""" + selfurl = self.absolute_url() + docpath = docinfo['textURLPath'] + viewMode= pageinfo['viewMode'] + text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text')) + dom =Parse(text) + pagedivs = dom.xpath("//div[@class='countTocEntries']") + logging.debug ("pagedivs=%s"%(pagedivs)) + if len(pagedivs)>0: + originalPage= (getTextFromNode(pagedivs[0])) + tc = int (originalPage) + tc1 =tc/30+1 + return tc1 + + def getQueryResultHitsFigures(self, docinfo=None, pageinfo=None): + """number of hits in Text of Figures mode""" + + selfurl = self.absolute_url() + docpath = docinfo['textURLPath'] + viewMode= pageinfo['viewMode'] + text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text')) + dom =Parse(text) + pagedivs = dom.xpath("//div[@class='countFigureEntries']") + logging.debug ("pagedivs=%s"%(pagedivs)) + if len(pagedivs)>0: + originalPage= (getTextFromNode(pagedivs[0])) + tc = int (originalPage) + tc1 =tc/30+1 + return tc1 + + def getToc(self, mode="text", docinfo=None): """loads table of contents and stores in docinfo""" logging.debug("documentViewer (gettoc) mode: %s"%(mode)) @@ -382,11 +492,12 @@ class MpdlXmlTextServer(SimpleItem): selfurl = self.absolute_url() viewMode= pageinfo['viewMode'] characterNormalization = pageinfo ['characterNormalization'] + optionToggle =pageinfo ['optionToggle'] tocMode = pageinfo['tocMode'] tocPN = pageinfo['tocPN'] - data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=%s"%(docpath,queryType, pagesize, pn,characterNormalization)) - page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN)) + data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm&optionToggle=1"%(docpath,queryType, pagesize, pn)) + page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&optionToggle=1'%(selfurl,url, viewMode, tocMode, tocPN)) text = page.replace('mode=image','mode=texttool') logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization)) #logging.debug("documentViewer (characterNormalization) text: %s"%(text))