version 1.24, 2010/08/24 13:15:59
|
version 1.28, 2010/09/21 10:21:33
|
Line 130 class MpdlXmlTextServer(SimpleItem):
|
Line 130 class MpdlXmlTextServer(SimpleItem):
|
docinfo['numPages'] = text.count("<pb ") |
docinfo['numPages'] = text.count("<pb ") |
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=None): |
def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=""): |
"""returns single page from fulltext""" |
"""returns single page from fulltext""" |
docpath = docinfo['textURLPath'] |
docpath = docinfo['textURLPath'] |
path = docinfo['textURLPath'] |
path = docinfo['textURLPath'] |
Line 145 class MpdlXmlTextServer(SimpleItem):
|
Line 145 class MpdlXmlTextServer(SimpleItem):
|
else: |
else: |
textmode = mode |
textmode = mode |
#logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization)) |
#logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization)) |
textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn) |
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"%(highlightQuery,sn) |
textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn) |
|
|
Line 165 class MpdlXmlTextServer(SimpleItem):
|
Line 165 class MpdlXmlTextServer(SimpleItem):
|
if hrefNode: |
if hrefNode: |
href= hrefNode.nodeValue |
href= hrefNode.nodeValue |
if href.startswith('#note-'): |
if href.startswith('#note-'): |
hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&characterNormalization=%s#note-"%(url,viewMode,tocMode,tocPN,pn,characterNormalization)) |
hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) |
return serializeNode(pagenode) |
return serializeNode(pagenode) |
if mode == "xml": |
if mode == "xml": |
# first div contains text |
# first div contains text |
Line 178 class MpdlXmlTextServer(SimpleItem):
|
Line 178 class MpdlXmlTextServer(SimpleItem):
|
pagedivs = pagedom.xpath("/div") |
pagedivs = pagedom.xpath("/div") |
if len(pagedivs) > 0: |
if len(pagedivs) > 0: |
pagenode = 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('http://chinagis.mpiwg-berlin.mpg.de'): |
|
hrefNode.nodeValue =href.replace('chinagis_REST','chinagis') |
return serializeNode(pagenode) |
return serializeNode(pagenode) |
|
|
if mode == "pureXml": |
if mode == "pureXml": |
Line 237 class MpdlXmlTextServer(SimpleItem):
|
Line 244 class MpdlXmlTextServer(SimpleItem):
|
#pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query))) |
#pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query))) |
return data |
return data |
|
|
|
def getGis (self, mode="gis", pn=1, pageinfo=None, docinfo=None): |
|
docpath = docinfo['textURLPath'] |
|
path = docinfo['textURLPath'] |
|
pagesize = pageinfo['tocPageSize'] |
|
pn = pageinfo['tocPN'] |
|
url = docinfo['url'] |
|
selfurl = self.absolute_url() |
|
viewMode= pageinfo['viewMode'] |
|
tocMode = pageinfo['tocMode'] |
|
tocPN = pageinfo['tocPN'] |
|
data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn)) |
|
page =data.replace("http://chinagis.mpiwg-berlin.mpg.de/chinagis_REST/REST/","http://chinagis.mpiwg-berlin.mpg.de/chinagis/REST/") |
|
return page |
|
|
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): |
"""number of""" |
"""number of""" |
docpath = docinfo['textURLPath'] |
docpath = docinfo['textURLPath'] |