Mercurial > hg > documentViewer
changeset 473:74e9e74277e9 elementtree
smaller improvements
| author | casties |
|---|---|
| date | Fri, 05 Aug 2011 11:24:42 +0200 |
| parents | 9705161bc888 |
| children | 0bc4a153863a |
| files | MpdlXmlTextServer.py documentViewer.py |
| diffstat | 2 files changed, 15 insertions(+), 9 deletions(-) [+] |
line wrap: on
line diff
--- a/MpdlXmlTextServer.py Thu Aug 04 18:13:13 2011 +0200 +++ b/MpdlXmlTextServer.py Fri Aug 05 11:24:42 2011 +0200 @@ -228,6 +228,11 @@ """processes page info divs from dom and stores in docinfo and pageinfo""" # assume first second level div is pageMeta alldivs = dom.find("div") + + if alldivs is None or alldivs.get('class', '') != 'pageMeta': + logging.error("processPageInfo: pageMeta div not found!") + return + for div in alldivs: dc = div.get('class') @@ -264,7 +269,8 @@ pageinfo['numgroups'] = int(np / pageinfo['groupsize']) if np % pageinfo['groupsize'] > 0: pageinfo['numgroups'] += 1 - + + #logging.debug("processPageInfo: pageinfo=%s"%repr(pageinfo)) return @@ -291,8 +297,8 @@ characterNormalization = pageinfo.get('characterNormalization', None) selfurl = docinfo['viewerUrl'] - if mode == "dict": - # text_dict is called textPollux in the backend + if mode == "dict" or mode == "text_dict": + # dict is called textPollux in the backend textmode = "textPollux" elif not mode: # default is text @@ -323,7 +329,7 @@ # plain text mode if mode == "text": - if pagediv: + if pagediv is not None: links = pagediv.findall(".//a") for l in links: href = l.get('href') @@ -335,7 +341,7 @@ # text-with-links mode elif mode == "text_dict": - if pagediv: + if pagediv is not None: # check all a-tags links = pagediv.findall(".//a") for l in links: @@ -365,18 +371,18 @@ # xml mode elif mode == "xml": - if pagediv: + if pagediv is not None: return serialize(pagediv) # pureXml mode elif mode == "pureXml": - if pagediv: + if pagediv is not None: return serialize(pagediv) # gis mode elif mode == "gis": name = docinfo['name'] - if pagediv: + if pagediv is not None: # check all a-tags links = pagediv.findall(".//a") for l in links:
--- a/documentViewer.py Thu Aug 04 18:13:13 2011 +0200 +++ b/documentViewer.py Fri Aug 05 11:24:42 2011 +0200 @@ -461,7 +461,7 @@ docinfo['documentUrl'] = docUrl # process index.meta contents - if metaDom is not None: + if metaDom is not None and metaDom.tag == 'resource': # document directory name and path resource = self.metadataService.getResourceData(dom=metaDom) if resource: