Mercurial > hg > documentViewer
changeset 478:cd37d6f8d5e8 elementtree
more cleanup
author | casties |
---|---|
date | Fri, 12 Aug 2011 16:41:39 +0200 |
parents | 17f0290b2327 |
children | fe5b0e4ac5f2 |
files | MpdlXmlTextServer.py documentViewer.py |
diffstat | 2 files changed, 42 insertions(+), 43 deletions(-) [+] |
line wrap: on
line diff
--- a/MpdlXmlTextServer.py Wed Aug 10 21:18:03 2011 +0200 +++ b/MpdlXmlTextServer.py Fri Aug 12 16:41:39 2011 +0200 @@ -89,7 +89,7 @@ url = docinfo['url'] pagesize = pageinfo['queryPageSize'] pn = pageinfo.get('searchPN',1) - sn = pageinfo['sn'] + sn = pageinfo.get('sn',None) #TODO: is this s now? highlightQuery = pageinfo['highlightQuery'] query =pageinfo['query'] queryType =pageinfo['queryType'] @@ -269,7 +269,7 @@ def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None): """returns single page from fulltext""" logging.debug("getTextPage mode=%s, pn=%s"%(mode,pn)) - # check for cached text -- but this shouldn't be called twice + # check for cached text -- but ideally this shouldn't be called twice if pageinfo.has_key('textPage'): logging.debug("getTextPage: using cached text") return pageinfo['textPage'] @@ -287,7 +287,8 @@ tocMode = pageinfo.get('tocMode', None) tocPN = pageinfo.get('tocPN',None) characterNormalization = pageinfo.get('characterNormalization', None) - selfurl = docinfo['viewerUrl'] + + selfurl = docinfo['viewerUrl'] if mode == "dict" or mode == "text_dict": # dict is called textPollux in the backend @@ -322,12 +323,14 @@ # plain text mode if mode == "text": + # get full url assuming documentViewer is parent + selfurl = self.getLink() if pagediv is not None: links = pagediv.findall(".//a") for l in links: href = l.get('href') if href and href.startswith('#note-'): - href = href.replace('#note-',"?mode=%s&url=%s&viewMode=text&tocMode=%s&tocPN=%s&pn=%s#note-"%(urlmode,url,tocMode,tocPN,pn)) + href = href.replace('#note-',"%s#note-"%selfurl) l.set('href', href) return serialize(pagediv) @@ -335,6 +338,8 @@ # text-with-links mode elif mode == "dict": if pagediv is not None: + viewerurl = docinfo['viewerUrl'] + selfurl = self.getLink() # check all a-tags links = pagediv.findall(".//a") for l in links: @@ -343,14 +348,13 @@ if href: # is link with href if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql'): - # is pollux link - selfurl = self.absolute_url() - # change href - l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql','%s/head_main_voc'%selfurl)) - # add target + # is dictionary link - change href (keeping parameters) + l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql','%s/template/viewer_wordinfo'%viewerurl)) + # add target to open new page l.set('target', '_blank') - if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql'): + # TODO: is this needed? + if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql'): selfurl = self.absolute_url() l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql','%s/head_main_lemma'%selfurl)) l.set('target', '_blank') @@ -358,7 +362,8 @@ l.set('ondblclick', 'popupWin.focus();') if href.startswith('#note-'): - l.set('href', href.replace('#note-',"?mode=%s&url=%s&viewMode=text_dict&tocMode=%s&tocPN=%s&pn=%s#note-"%(urlmode,url,tocMode,tocPN,pn))) + # note link + l.set('href', href.replace('#note-',"%s#note-"%selfurl)) return serialize(pagediv) @@ -389,28 +394,10 @@ return "no text here" - # WTF: is this needed? - def getOrigPages(self, docinfo=None, pageinfo=None): - logging.debug("CALLED: getOrigPages!") - if not pageinfo.has_key('pageNumberOrig'): - logging.warning("getOrigPages: not in pageinfo!") - return None - - return pageinfo['pageNumberOrig'] - - # WTF: is this needed? - def getOrigPagesNorm(self, docinfo=None, pageinfo=None): - logging.debug("CALLED: getOrigPagesNorm!") - if not pageinfo.has_key('pageNumberOrigNorm'): - logging.warning("getOrigPagesNorm: not in pageinfo!") - return None - - return pageinfo['pageNumberOrigNorm'] - # TODO: should be getWordInfo - def getTranslate(self, word=None, language=None): - """translate into another languages""" - data = self.getServerData("lt/wordInfo.xql","language="+str(language)+"&word="+urllib.quote(word)+"&output=html") + def getWordInfo(self, word='', language='', display=''): + """show information (like dictionaries) about word""" + data = self.getServerData("lt/wordInfo.xql","language=%s&word=%s&display=%s&output=html"%(language,urllib.quote(word),urllib.quote(display))) return data # WTF: what does this do?
--- a/documentViewer.py Wed Aug 10 21:18:03 2011 +0200 +++ b/documentViewer.py Fri Aug 12 16:41:39 2011 +0200 @@ -209,9 +209,9 @@ """get all gis places """ return self.template.fulltextclient.getAllGisPlaces(**args) - def getTranslate(self, **args): + def getWordInfo(self, **args): """get translate""" - return self.template.fulltextclient.getTranslate(**args) + return self.template.fulltextclient.getWordInfo(**args) def getLemma(self, **args): """get lemma""" @@ -310,6 +310,7 @@ # stringify viewType if isinstance(viewType, list): + logging.debug("index_html: viewType is list:%s"%viewType) viewType = ','.join([t for t in viewType if t]) pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode) @@ -358,7 +359,7 @@ else: return style - def getParams(self, param=None, val=None, params=None): + def getParams(self, param=None, val=None, params=None, duplicates=None): """returns dict with URL parameters. Takes URL parameters and additionally param=val or dict params. @@ -375,8 +376,7 @@ # change more params if params is not None: - for k in params.keys(): - v = params[k] + for (k, v) in params.items(): if v is None: # val=None removes param if newParams.has_key(k): @@ -384,12 +384,23 @@ else: newParams[k] = v - + + if duplicates: + # eliminate lists (coming from duplicate keys) + for (k,v) in newParams.items(): + if isinstance(v, list): + if duplicates == 'comma': + # make comma-separated list of non-empty entries + newParams[k] = ','.join([t for t in v if t]) + elif duplicates == 'first': + # take first non-empty entry + newParams[k] = [t for t in v if t][0] + return newParams - def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'): + def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): """returns URL to documentviewer with parameter param set to val or from dict params""" - urlParams = self.getParams(param=param, val=val, params=params) + urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates) # 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: @@ -398,9 +409,9 @@ url = "%s?%s"%(baseUrl, ps) return url - def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None): + def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): """link to documentviewer with parameter param set to val""" - return self.getLink(param, val, params, baseUrl, '&') + return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&', duplicates=duplicates) def getInfo_xml(self,url,mode): @@ -686,8 +697,9 @@ return docinfo - def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None): + def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None): """returns pageinfo with the given parameters""" + logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewType=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewType,tocMode)) pageinfo = {} pageinfo['viewMode'] = viewMode pageinfo['viewType'] = viewType