version 1.25, 2010/08/24 13:27:07
|
version 1.198, 2010/10/25 12:23:42
|
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, query, pagesize, pn, sn, viewMode,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 72 class MpdlXmlTextServer(SimpleItem):
|
Line 70 class MpdlXmlTextServer(SimpleItem):
|
href = hrefNode.nodeValue |
href = hrefNode.nodeValue |
if href.startswith('page-fragment.xql'): |
if href.startswith('page-fragment.xql'): |
selfurl = self.absolute_url() |
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,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'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN)) |
hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
return serializeNode(pagenode) |
return serializeNode(pagenode) |
if (queryType=="fulltextMorph"): |
if (queryType=="fulltextMorph"): |
Line 86 class MpdlXmlTextServer(SimpleItem):
|
Line 84 class MpdlXmlTextServer(SimpleItem):
|
href = hrefNode.nodeValue |
href = hrefNode.nodeValue |
if href.startswith('page-fragment.xql'): |
if href.startswith('page-fragment.xql'): |
selfurl = self.absolute_url() |
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,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'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN)) |
hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
if href.startswith('../lt/lemma.xql'): |
if href.startswith('../lt/lemma.xql'): |
hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl)) |
hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl)) |
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 |
|
|
xquery = '//pb' |
xquery = '//pb' |
text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) |
text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) |
#text = self.template.fulltextclient.eval("/mpdl/interface/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): |
|
"""get list of pages from fulltext (texts without images) and put in docinfo""" |
|
if 'numPages' in docinfo: |
|
# allredy there |
|
return docinfo |
|
xpath ='/count(//pb)' |
|
text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'], xpath)) |
|
dom = Parse(text) |
|
result= dom.xpath("//result/resultPage") |
|
docinfo['numPages']=int(getTextFromNode(result[0])) |
|
return docinfo |
|
|
|
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'] |
|
|
def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=""): |
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=""): |
"""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 144 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"%(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"%(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 165 class MpdlXmlTextServer(SimpleItem):
|
Line 236 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 249 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/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name) |
|
l.setAttributeNS(None, 'target', '_blank') |
return serializeNode(pagenode) |
return serializeNode(pagenode) |
|
|
if mode == "pureXml": |
if mode == "pureXml": |
Line 247 class MpdlXmlTextServer(SimpleItem):
|
Line 326 class MpdlXmlTextServer(SimpleItem):
|
tocSearch = 0 |
tocSearch = 0 |
tocDiv = None |
tocDiv = None |
|
|
pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn)) |
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) |
#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) |
pagedom = Parse(pagexml) |
numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
numdivs = pagedom.xpath("//div[@class='queryResultHits']") |