version 1.225, 2011/02/14 14:41:12
|
version 1.230, 2011/03/07 14:08:07
|
Line 85 class MpdlXmlTextServer(SimpleItem):
|
Line 85 class MpdlXmlTextServer(SimpleItem):
|
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&optionToggle=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,optionToggle,characterNormalization)) |
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) |
hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
logging.debug("PUREXML :%s"%(serializeNode(pagenode))) |
#logging.debug("PUREXML :%s"%(serializeNode(pagenode))) |
return serializeNode(pagenode) |
return serializeNode(pagenode) |
if (queryType=="fulltextMorph"): |
if (queryType=="fulltextMorph"): |
pagedivs = pagedom.xpath("//div[@class='queryResult']") |
pagedivs = pagedom.xpath("//div[@class='queryResult']") |
Line 130 class MpdlXmlTextServer(SimpleItem):
|
Line 130 class MpdlXmlTextServer(SimpleItem):
|
return serializeNode(pagenode) |
return serializeNode(pagenode) |
return "no text here" |
return "no text here" |
|
|
|
|
def getGisPlaces(self, docinfo=None, pageinfo=None): |
def getGisPlaces(self, docinfo=None, pageinfo=None): |
""" Show all Gis Places of whole Page""" |
""" Show all Gis Places of whole Page""" |
xpath='//place' |
xpath='//place' |
Line 151 class MpdlXmlTextServer(SimpleItem):
|
Line 150 class MpdlXmlTextServer(SimpleItem):
|
href= hrefNode.nodeValue |
href= hrefNode.nodeValue |
hrefList.append(href) |
hrefList.append(href) |
myList = ",".join(hrefList) |
myList = ",".join(hrefList) |
logging.debug("getGisPlaces :%s"%(myList)) |
#logging.debug("getGisPlaces :%s"%(myList)) |
return myList |
return myList |
|
|
def getAllGisPlaces (self, docinfo=None, pageinfo=None): |
def getAllGisPlaces (self, docinfo=None, pageinfo=None): |
Line 172 class MpdlXmlTextServer(SimpleItem):
|
Line 171 class MpdlXmlTextServer(SimpleItem):
|
href= hrefNode.nodeValue |
href= hrefNode.nodeValue |
hrefList.append(href) |
hrefList.append(href) |
myList = ",".join(hrefList) |
myList = ",".join(hrefList) |
logging.debug("getALLGisPlaces :%s"%(myList)) |
#logging.debug("getALLGisPlaces :%s"%(myList)) |
return myList |
return myList |
|
|
|
|
def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None): |
def getTextPage(self, mode="text_dict", pn=1, docinfo=None, pageinfo=None): |
"""returns single page from fulltext""" |
"""returns single page from fulltext""" |
docpath = docinfo['textURLPath'] |
docpath = docinfo['textURLPath'] |
path = docinfo['textURLPath'] |
path = docinfo['textURLPath'] |
url = docinfo.get('url',None) |
url = docinfo.get('url',None) |
name = docinfo.get('name',None) |
name = docinfo.get('name',None) |
pn =pageinfo['current'] |
pn =pageinfo['current'] |
viewMode= pageinfo['viewMode'] |
|
sn = pageinfo['sn'] |
sn = pageinfo['sn'] |
highlightQuery = pageinfo['highlightQuery'] |
highlightQuery = pageinfo['highlightQuery'] |
#mode = pageinfo ['viewMode'] |
#mode = pageinfo ['viewMode'] |
Line 202 class MpdlXmlTextServer(SimpleItem):
|
Line 200 class MpdlXmlTextServer(SimpleItem):
|
|
|
pagexml = self.getServerData("page-fragment.xql",textParam) |
pagexml = self.getServerData("page-fragment.xql",textParam) |
dom = Parse(pagexml) |
dom = Parse(pagexml) |
|
|
#original Pages |
#original Pages |
pagedivs = dom.xpath("//div[@class='pageNumberOrig']") |
pagedivs = dom.xpath("//div[@class='pageNumberOrig']") |
if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"): |
"""if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"): |
if len(pagedivs)>0: |
if len(pagedivs)>0: |
docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0]) |
docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0]) |
logging.debug("ORIGINAL PAGES: %s"%(docinfo['pageNumberOrig'])) |
logging.debug("ORIGINAL PAGE: %s"%(docinfo['pageNumberOrig'])) |
|
|
|
#original Pages Norm |
|
pagedivs = dom.xpath("//div[@class='pageNumberOrigNorm']") |
|
if pagedivs == dom.xpath("//div[@class='pageNumberOrigNorm']"): |
|
if len(pagedivs)>0: |
|
docinfo['pageNumberOrigNorm']= getTextFromNode(pagedivs[0]) |
|
logging.debug("ORIGINAL PAGE NORM: %s"%(docinfo['pageNumberOrigNorm'])) |
|
""" |
#figureEntries |
#figureEntries |
pagedivs = dom.xpath("//div[@class='countFigureEntries']") |
pagedivs = dom.xpath("//div[@class='countFigureEntries']") |
if pagedivs == dom.xpath("//div[@class='countFigureEntries']"): |
if pagedivs == dom.xpath("//div[@class='countFigureEntries']"): |
Line 219 class MpdlXmlTextServer(SimpleItem):
|
Line 223 class MpdlXmlTextServer(SimpleItem):
|
if s=='0': |
if s=='0': |
try: |
try: |
docinfo['countFigureEntries'] = int(s) |
docinfo['countFigureEntries'] = int(s) |
logging.debug("FIGURE ENTRIES: %s"%(s)) |
|
except: |
except: |
docinfo['countFigureEntries'] = 0 |
docinfo['countFigureEntries'] = 0 |
else: |
else: |
s1 = int(s)/30+1 |
s1 = int(s)/30+1 |
try: |
try: |
docinfo['countFigureEntries'] = int(s1) |
docinfo['countFigureEntries'] = int(s1) |
logging.debug("FIGURE ENTRIES: %s"%(s1)) |
|
except: |
except: |
docinfo['countFigureEntries'] = 0 |
docinfo['countFigureEntries'] = 0 |
|
|
Line 238 class MpdlXmlTextServer(SimpleItem):
|
Line 240 class MpdlXmlTextServer(SimpleItem):
|
s = getTextFromNode(pagedivs[0]) |
s = getTextFromNode(pagedivs[0]) |
try: |
try: |
docinfo['countPlaces'] = int(s) |
docinfo['countPlaces'] = int(s) |
logging.debug("PLACES HERE: %s"%(s)) |
|
except: |
except: |
docinfo['countPlaces'] = 0 |
docinfo['countPlaces'] = 0 |
|
|
Line 251 class MpdlXmlTextServer(SimpleItem):
|
Line 252 class MpdlXmlTextServer(SimpleItem):
|
if s=='0': |
if s=='0': |
try: |
try: |
docinfo['countTocEntries'] = int(s) |
docinfo['countTocEntries'] = int(s) |
logging.debug("TEXT ENTRIES: %s"%(s)) |
|
except: |
except: |
docinfo['countTocEntries'] = 0 |
docinfo['countTocEntries'] = 0 |
else: |
else: |
s1 = int(s)/30+1 |
s1 = int(s)/30+1 |
try: |
try: |
docinfo['countTocEntries'] = int(s1) |
docinfo['countTocEntries'] = int(s1) |
logging.debug("TEXT ENTRIES: %s"%(s1)) |
|
except: |
except: |
docinfo['countTocEntries'] = 0 |
docinfo['countTocEntries'] = 0 |
|
|
Line 271 class MpdlXmlTextServer(SimpleItem):
|
Line 270 class MpdlXmlTextServer(SimpleItem):
|
|
|
try: |
try: |
docinfo['numPages'] = int(s) |
docinfo['numPages'] = int(s) |
logging.debug("PAGE NUMBER: %s"%(s)) |
#logging.debug("PAGE NUMBER: %s"%(s)) |
|
|
np = docinfo['numPages'] |
np = docinfo['numPages'] |
pageinfo['end'] = min(pageinfo['end'], np) |
pageinfo['end'] = min(pageinfo['end'], np) |
Line 288 class MpdlXmlTextServer(SimpleItem):
|
Line 287 class MpdlXmlTextServer(SimpleItem):
|
docinfo['countPlaces'] = 0 |
docinfo['countPlaces'] = 0 |
docinfo['countTocEntries'] = 0 |
docinfo['countTocEntries'] = 0 |
docinfo['numPages'] = 0 |
docinfo['numPages'] = 0 |
|
docinfo['pageNumberOrigNorm'] = 0 |
#return docinfo |
#return docinfo |
|
|
# plain text mode |
# plain text mode |
Line 302 class MpdlXmlTextServer(SimpleItem):
|
Line 302 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#note-"%(url,viewMode,tocMode,tocPN,pn)) |
hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=text&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,tocMode,tocPN,pn)) |
return serializeNode(pagenode) |
return serializeNode(pagenode) |
if mode == "xml": |
if mode == "xml": |
# first div contains text |
# first div contains text |
Line 334 class MpdlXmlTextServer(SimpleItem):
|
Line 334 class MpdlXmlTextServer(SimpleItem):
|
# text-with-links mode |
# text-with-links mode |
if mode == "text_dict": |
if mode == "text_dict": |
# first div contains text |
# first div contains text |
|
#mode = pageinfo ['viewMode'] |
pagedivs = dom.xpath("/div") |
pagedivs = dom.xpath("/div") |
if len(pagedivs) > 0: |
if len(pagedivs) > 0: |
pagenode = pagedivs[0] |
pagenode = pagedivs[0] |
Line 360 class MpdlXmlTextServer(SimpleItem):
|
Line 361 class MpdlXmlTextServer(SimpleItem):
|
l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") |
l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") |
l.setAttributeNS(None, 'onClick', 'popupWin.focus();') |
l.setAttributeNS(None, 'onClick', 'popupWin.focus();') |
if href.startswith('#note-'): |
if href.startswith('#note-'): |
hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) |
hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=text_dict&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,tocMode,tocPN,pn)) |
return serializeNode(pagenode) |
return serializeNode(pagenode) |
return "no text here" |
return "no text here" |
|
|
def getText(self, mode="text", pn=1, docinfo=None, pageinfo=None): |
def getOrigPages(self, docinfo=None, pageinfo=None): |
data = self.getTextPage(mode="text", pn=1 ,docinfo=docinfo, pageinfo=pageinfo) |
docpath = docinfo['textURLPath'] |
logging.debug("TEXT ALL data: %s"%(data)) |
pn =pageinfo['current'] |
return data |
selfurl = self.absolute_url() |
|
pagexml = self.getServerData("page-fragment.xql","document=%s&pn=%s"%(docpath, pn)) |
|
dom = Parse(pagexml) |
|
pagedivs = dom.xpath("//div[@class='pageNumberOrig']") |
|
if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"): |
|
if len(pagedivs)>0: |
|
docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0]) |
|
return docinfo['pageNumberOrig'] |
|
|
def getXML(self, mode="xml", pn=1, docinfo=None, pageinfo=None): |
def getOrigPagesNorm(self, docinfo=None, pageinfo=None): |
data = self.getTextPage(mode="xml", pn=1 ,docinfo=docinfo, pageinfo=pageinfo) |
docpath = docinfo['textURLPath'] |
logging.debug("TEXT ALL data: %s"%(data)) |
pn =pageinfo['current'] |
return data |
selfurl = self.absolute_url() |
|
pagexml = self.getServerData("page-fragment.xql","document=%s&pn=%s"%(docpath, pn)) |
|
dom = Parse(pagexml) |
|
pagedivs = dom.xpath("//div[@class='pageNumberOrigNorm']") |
|
if pagedivs == dom.xpath("//div[@class='pageNumberOrigNorm']"): |
|
if len(pagedivs)>0: |
|
docinfo['pageNumberOrigNorm']= getTextFromNode(pagedivs[0]) |
|
return docinfo['pageNumberOrigNorm'] |
|
|
def getDictionary(self, mode="text_dict", pn=1, docinfo=None, pageinfo=None): |
|
data = self.getTextPage(mode="text_dict", pn=1 ,docinfo=docinfo, pageinfo=pageinfo) |
|
logging.debug("TEXT ALL data: %s"%(data)) |
|
return data |
|
|
|
def getTranslate(self, query=None, language=None): |
def getTranslate(self, query=None, language=None): |
"""translate into another languages""" |
"""translate into another languages""" |
Line 411 class MpdlXmlTextServer(SimpleItem):
|
Line 422 class MpdlXmlTextServer(SimpleItem):
|
pagedom = Parse(pagexml) |
pagedom = Parse(pagexml) |
numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
tocSearch = int(getTextFromNode(numdivs[0])) |
tocSearch = int(getTextFromNode(numdivs[0])) |
logging.debug("documentViewer (gettoc) tocSearch: %s"%(tocSearch)) |
|
tc=int((tocSearch/10)+1) |
tc=int((tocSearch/10)+1) |
logging.debug("documentViewer (gettoc) tc: %s"%(tc)) |
|
return tc |
return tc |
|
|
def getToc(self, mode="text", docinfo=None): |
def getToc(self, mode="text", docinfo=None): |
"""loads table of contents and stores in docinfo""" |
"""loads table of contents and stores in docinfo""" |
logging.debug("documentViewer (gettoc) mode: %s"%(mode)) |
|
if mode == "none": |
if mode == "none": |
return docinfo |
return docinfo |
if 'tocSize_%s'%mode in docinfo: |
if 'tocSize_%s'%mode in docinfo: |
Line 470 class MpdlXmlTextServer(SimpleItem):
|
Line 478 class MpdlXmlTextServer(SimpleItem):
|
data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm&optionToggle=1"%(docpath,queryType, pagesize, pn)) |
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)) |
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') |
text = page.replace('mode=image','mode=texttool') |
#logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization)) |
|
logging.debug("TEXT %s"%(text)) |
|
return text |
return text |
|
|
def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None): |
def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None): |