documentViewer/MpdlXmlTextServer.py - diff

Return to MpdlXmlTextServer.py CVS log

Up to [Repository] / documentViewer

Diff for /documentViewer/MpdlXmlTextServer.py between versions 1.221 and 1.235

version 1.221, 2010/12/23 17:13:01	version 1.235, 2011/04/28 09:58:39
Line 3 from OFS.SimpleItem import SimpleItem	Line 3 from OFS.SimpleItem import SimpleItem
from Products.PageTemplates.PageTemplateFile import PageTemplateFile	from Products.PageTemplates.PageTemplateFile import PageTemplateFile
from Ft.Xml import EMPTY_NAMESPACE, Parse	from Ft.Xml import EMPTY_NAMESPACE, Parse

	import md5
import sys	import sys
import logging	import logging
import urllib	import urllib
Line 19 class MpdlXmlTextServer(SimpleItem):	Line 20 class MpdlXmlTextServer(SimpleItem):

manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals())	manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals())

def __init__(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):	def __init__(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):
	#def __init__(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/", serverName=None, timeout=40):

"""constructor"""	"""constructor"""
self.id=id	self.id=id
self.title=title	self.title=title
Line 38 class MpdlXmlTextServer(SimpleItem):	Line 41 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, characterNormalization=None, optionToggle=None):	def getSearch(self, pageinfo=None, docinfo=None):
"""get search list"""	"""get search list"""
docpath = docinfo['textURLPath']	docpath = docinfo['textURLPath']
url = docinfo['url']	url = docinfo['url']
pagesize = pageinfo['queryPageSize']	pagesize = pageinfo['queryPageSize']
pn = pageinfo['searchPN']	pn = pageinfo.get('searchPN',1)
sn = pageinfo['sn']	sn = pageinfo['sn']
highlightQuery = pageinfo['highlightQuery']	highlightQuery = pageinfo['highlightQuery']
query =pageinfo['query']	query =pageinfo['query']
Line 54 class MpdlXmlTextServer(SimpleItem):	Line 57 class MpdlXmlTextServer(SimpleItem):
optionToggle = pageinfo['optionToggle']	optionToggle = pageinfo['optionToggle']
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&characterNormalization=%s&optionToggle=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization,optionToggle ,urllib.quote(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&optionToggle=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization,optionToggle ,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)

pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)	pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
pagedom = Parse(pagexml)	pagedom = Parse(pagexml)

	"""
	pagedivs = pagedom.xpath("//div[@class='queryResultHits']")
	if (pagedivs == pagedom.xpath("//div[@class='queryResultHits']")):
	if len(pagedivs)>0:
	docinfo['queryResultHits'] = int(getTextFromNode(pagedivs[0]))
	s = getTextFromNode(pagedivs[0])
	s1 = int(s)/10+1
	try:
	docinfo['queryResultHits'] = int(s1)
	logging.debug("SEARCH ENTRIES: %s"%(s1))
	except:
	docinfo['queryResultHits'] = 0
	"""
if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):	if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
pagedivs = pagedom.xpath("//div[@class='queryResultPage']")	pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
if len(pagedivs)>0:	if len(pagedivs)>0:
Line 73 class MpdlXmlTextServer(SimpleItem):	Line 87 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)))
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 88 class MpdlXmlTextServer(SimpleItem):	Line 103 class MpdlXmlTextServer(SimpleItem):
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)
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_query'%(selfurl))
l.setAttributeNS(None, 'target', '_blank')	l.setAttributeNS(None, 'target', '_blank')
l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")	l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
l.setAttributeNS(None, 'onClick', 'popupWin.focus();')	l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")	pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
return serializeNode(pagenode)	return serializeNode(pagenode)
if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):	if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
Line 105 class MpdlXmlTextServer(SimpleItem):	Line 120 class MpdlXmlTextServer(SimpleItem):
href = hrefNode.nodeValue	href = hrefNode.nodeValue
hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&optionToggle=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,optionToggle,characterNormalization))	hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&optionToggle=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,optionToggle,characterNormalization))
if href.startswith('../lt/lex.xql'):	if href.startswith('../lt/lex.xql'):
hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)	hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_lex'%selfurl)
l.setAttributeNS(None, 'target', '_blank')	l.setAttributeNS(None, 'target', '_blank')
l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")	l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
l.setAttributeNS(None, 'onClick', 'popupWin.focus();')	l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
if href.startswith('../lt/lemma.xql'):	if href.startswith('../lt/lemma.xql'):
hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl)	hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%(selfurl))
l.setAttributeNS(None, 'target', '_blank')	l.setAttributeNS(None, 'target', '_blank')
l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")	l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
l.setAttributeNS(None, 'onClick', 'popupWin.focus();')	l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
return serializeNode(pagenode)	return serializeNode(pagenode)
return "no text here"	return "no text here"


def getNumTextPages (self, docinfo=None):
"""get list of pages from fulltext (texts without images) and put in docinfo"""
logging.debug("getNumTextPages")
docpath = docinfo['textURLPath']
selfurl = self.absolute_url()
#viewMode= pageinfo['viewMode']
if 'numPages' in docinfo:
# allredy there
return docinfo

text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
dom =Parse(text)
pagedivs = dom.xpath("//div[@class='countPages']")
logging.debug ("pagedivs=%s"%(pagedivs))
if len(pagedivs)>0:
docinfo['numPages']= int(getTextFromNode(pagedivs[0]))
return docinfo

def getTocEntries (self, docinfo=None):
""" number of text entries"""
docinfo = self.getInfoFromPage(docinfo)
logging.debug("gettocentries: docinfo=%s"%docinfo)
return docinfo['tocEntries']

def getFigureEntries (self, docinfo=None):
""" number of figure entries"""
docinfo = self.getInfoFromPage(docinfo)
return docinfo['figureEntries']

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 167 class MpdlXmlTextServer(SimpleItem):	Line 152 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 188 class MpdlXmlTextServer(SimpleItem):	Line 173 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 getOrigPages (self, docinfo=None, pageinfo=None):
"""Show original page """	def getTextPage(self, mode="text_dict", pn=1, docinfo=None, pageinfo=None):
docpath = docinfo.get('textURLPath',None)	"""returns single page from fulltext"""
if not docpath:	docpath = docinfo['textURLPath']
return None	path = docinfo['textURLPath']
selfurl = self.absolute_url()	url = docinfo.get('url',None)
	name = docinfo.get('name',None)
pn =pageinfo['current']	pn =pageinfo['current']
	sn = pageinfo['sn']
	optionToggle =pageinfo ['optionToggle']
	highlightQuery = pageinfo['highlightQuery']
	#mode = pageinfo ['viewMode']
	tocMode = pageinfo['tocMode']
	characterNormalization=pageinfo['characterNormalization']
	tocPN = pageinfo['tocPN']
	selfurl = self.absolute_url()
	if mode == "text_dict":
	textmode = "textPollux"
	else:
	textmode = mode

viewMode= pageinfo['viewMode']	textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s&optionToggle=%s"%(docpath,textmode,pn,characterNormalization,optionToggle)
text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text', pn))	if highlightQuery is not None:
dom =Parse(text)	textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)

	pagexml = self.getServerData("page-fragment.xql",textParam)
	dom = Parse(pagexml)
	#original Pages
pagedivs = dom.xpath("//div[@class='pageNumberOrig']")	pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
	"""if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"):
if len(pagedivs)>0:	if len(pagedivs)>0:
originalPage= getTextFromNode(pagedivs[0])	docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0])
#return docinfo['originalPage']	logging.debug("ORIGINAL PAGE: %s"%(docinfo['pageNumberOrig']))
return originalPage

def getAllPlaces (self, docinfo=None):
"""Show all Places if no places than 0"""
docinfo = self.getInfoFromPage(docinfo)
return docinfo['allPlaces']

def getInfoFromPage(self, docinfo=None):	#original Pages Norm
""" extract diverse info from page-fragment"""	pagedivs = dom.xpath("//div[@class='pageNumberOrigNorm']")
docpath = docinfo['textURLPath']	if pagedivs == dom.xpath("//div[@class='pageNumberOrigNorm']"):
if 'allPlaces' in docinfo:	if len(pagedivs)>0:
# allredy there	docinfo['pageNumberOrigNorm']= getTextFromNode(pagedivs[0])
return docinfo	logging.debug("ORIGINAL PAGE NORM: %s"%(docinfo['pageNumberOrigNorm']))
	"""
if (docpath is not None):
text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
dom = Parse(text)
# figureEntries	# figureEntries
pagedivs = dom.xpath("//div[@class='countFigureEntries']")	pagedivs = dom.xpath("//div[@class='countFigureEntries']")
	if pagedivs == dom.xpath("//div[@class='countFigureEntries']"):
	if len(pagedivs)>0:
	docinfo['countFigureEntries'] = getTextFromNode(pagedivs[0])
s = getTextFromNode(pagedivs[0])	s = getTextFromNode(pagedivs[0])
	if s=='0':
try:	try:
docinfo['figureEntries'] = int(s)	docinfo['countFigureEntries'] = int(s)
except:	except:
docinfo['figureEntries'] = 0	docinfo['countFigureEntries'] = 0
# tocEntries	else:
pagedivs = dom.xpath("//div[@class='countTocEntries']")	s1 = int(s)/30+1
s = getTextFromNode(pagedivs[0])
try:	try:
docinfo['tocEntries'] = int(s)	docinfo['countFigureEntries'] = int(s1)
except:	except:
docinfo['tocEntries'] = 0	docinfo['countFigureEntries'] = 0

# allPlaces	# allPlaces
pagedivs = dom.xpath("//div[@class='countPlaces']")	pagedivs = dom.xpath("//div[@class='countPlaces']")
	if pagedivs == dom.xpath("//div[@class='countPlaces']"):
	if len(pagedivs)>0:
	docinfo['countPlaces']= getTextFromNode(pagedivs[0])
s = getTextFromNode(pagedivs[0])	s = getTextFromNode(pagedivs[0])
try:	try:
docinfo['allPlaces'] = int(s)	docinfo['countPlaces'] = int(s)
except:	except:
docinfo['allPlaces'] = 0	docinfo['countPlaces'] = 0

	#tocEntries
	pagedivs = dom.xpath("//div[@class='countTocEntries']")
	if pagedivs == dom.xpath("//div[@class='countTocEntries']"):
	if len(pagedivs)>0:
	docinfo['countTocEntries'] = int(getTextFromNode(pagedivs[0]))
	s = getTextFromNode(pagedivs[0])
	if s=='0':
	try:
	docinfo['countTocEntries'] = int(s)
	except:
	docinfo['countTocEntries'] = 0
else:	else:
# no full text -- init to 0	s1 = int(s)/30+1
docinfo['figureEntries'] = 0	try:
docinfo['tocEntries'] = 0	docinfo['countTocEntries'] = int(s1)
docinfo['allPlaces'] = 0	except:
	docinfo['countTocEntries'] = 0

return docinfo	#numTextPages
	pagedivs = dom.xpath("//div[@class='countPages']")
	if pagedivs == dom.xpath("//div[@class='countPages']"):
	if len(pagedivs)>0:
	docinfo['numPages'] = getTextFromNode(pagedivs[0])
	s = getTextFromNode(pagedivs[0])

	try:
	docinfo['numPages'] = int(s)
	#logging.debug("PAGE NUMBER: %s"%(s))

def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization="reg", highlightQuery=None, sn=None, optionToggle=None):	np = docinfo['numPages']
"""returns single page from fulltext"""	pageinfo['end'] = min(pageinfo['end'], np)
docpath = docinfo['textURLPath']	pageinfo['numgroups'] = int(np / pageinfo['groupsize'])
path = docinfo['textURLPath']	if np % pageinfo['groupsize'] > 0:
url = docinfo['url']	pageinfo['numgroups'] += 1
name = docinfo['name']	except:
viewMode= pageinfo['viewMode']	docinfo['numPages'] = 0
sn = pageinfo['sn']
highlightQuery = pageinfo['highlightQuery']

tocMode = pageinfo['tocMode']
characterNormalization=pageinfo['characterNormalization']
tocPN = pageinfo['tocPN']
selfurl = self.absolute_url()
if mode == "text_dict":
textmode = "textPollux"
else:	else:
textmode = mode	#no full text -- init to 0
#logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))	docinfo['pageNumberOrig'] = 0
textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)	docinfo['countFigureEntries'] = 0
if highlightQuery is not None:	docinfo['countPlaces'] = 0
textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)	docinfo['countTocEntries'] = 0
#logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))	docinfo['numPages'] = 0
pagexml = self.getServerData("page-fragment.xql",textParam)	docinfo['pageNumberOrigNorm'] = 0
logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))	#return docinfo
#pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)

pagedom = Parse(pagexml)
# plain text mode	# plain text mode
if mode == "text":	if mode == "text":
# first div contains text	# first div contains text
pagedivs = pagedom.xpath("/div")	pagedivs = dom.xpath("/div")
if len(pagedivs) > 0:	if len(pagedivs) > 0:
pagenode = pagedivs[0]	pagenode = pagedivs[0]
links = pagenode.xpath("//a")	links = pagenode.xpath("//a")
Line 294 class MpdlXmlTextServer(SimpleItem):	Line 305 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
pagedivs = pagedom.xpath("/div")	pagedivs = dom.xpath("/div")
if len(pagedivs) > 0:	if len(pagedivs) > 0:
pagenode = pagedivs[0]	pagenode = pagedivs[0]
return serializeNode(pagenode)	return serializeNode(pagenode)
if mode == "gis":	if mode == "gis":
# first div contains text	# first div contains text
pagedivs = pagedom.xpath("/div")	pagedivs = dom.xpath("/div")
if len(pagedivs) > 0:	if len(pagedivs) > 0:
pagenode = pagedivs[0]	pagenode = pagedivs[0]
links =pagenode.xpath("//a")	links =pagenode.xpath("//a")
Line 319 class MpdlXmlTextServer(SimpleItem):	Line 330 class MpdlXmlTextServer(SimpleItem):

if mode == "pureXml":	if mode == "pureXml":
# first div contains text	# first div contains text
pagedivs = pagedom.xpath("/div")	pagedivs = dom.xpath("/div")
if len(pagedivs) > 0:	if len(pagedivs) > 0:
pagenode = pagedivs[0]	pagenode = pagedivs[0]
return serializeNode(pagenode)	return serializeNode(pagenode)
# text-with-links mode	# text-with-links mode
if mode == "text_dict":	if mode == "text_dict":
# first div contains text	# first div contains text
pagedivs = pagedom.xpath("/div")	#mode = pageinfo ['viewMode']
	pagedivs = dom.xpath("/div")
if len(pagedivs) > 0:	if len(pagedivs) > 0:
pagenode = pagedivs[0]	pagenode = pagedivs[0]
# check all a-tags	# check all a-tags
Line 336 class MpdlXmlTextServer(SimpleItem):	Line 348 class MpdlXmlTextServer(SimpleItem):
if hrefNode:	if hrefNode:
# is link with href	# is link with href
href = hrefNode.nodeValue	href = hrefNode.nodeValue
if href.startswith('lt/lex.xql'):	if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql'):
# is pollux link	# is pollux link
selfurl = self.absolute_url()	selfurl = self.absolute_url()
# change href	# change href
hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)	hrefNode.nodeValue = href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql','%s/head_main_voc'%selfurl)
# add target	# add target
l.setAttributeNS(None, 'target', '_blank')	l.setAttributeNS(None, 'target', '_blank')
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, 'InfoWindow', 'menubar=no, location,width=500,height=600,top=180, left=700, toolbar=no, scrollbars=1'); return false;")
l.setAttributeNS(None, 'onClick', 'popupWin.focus();')	l.setAttributeNS(None, "onDblclick", "popupWin.focus();")
if href.startswith('lt/lemma.xql'):	#window.open("this.href, 'InfoWindow', 'menubar=no, location,width=500,height=600,top=180, left=700, toolbar=yes, scrollbars=1'"); return false;")

	if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql'):
selfurl = self.absolute_url()	selfurl = self.absolute_url()
hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)	hrefNode.nodeValue = href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql','%s/head_main_lemma'%selfurl)
l.setAttributeNS(None, 'target', '_blank')	l.setAttributeNS(None, 'target', '_blank')
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, 'InfoWindow', 'menubar=no, location,width=500,height=600,top=180, left=700, toolbar=no, scrollbars=1'); return false;")
l.setAttributeNS(None, 'onClick', 'popupWin.focus();')	l.setAttributeNS(None, 'onDblclick', '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 getTranslate(self, query=None, language=None):	def getOrigPages(self, docinfo=None, pageinfo=None):
	docpath = docinfo['textURLPath']
	pn =pageinfo['current']
	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 getOrigPagesNorm(self, docinfo=None, pageinfo=None):
	docpath = docinfo['textURLPath']
	pn =pageinfo['current']
	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 getTranslate(self, word=None, language=None):
"""translate into another languages"""	"""translate into another languages"""
data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))	data = self.getServerData("lt/wordInfo.xql","language="+str(language)+"&word="+urllib.quote(word)+"&output=html")
#pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))	#pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
return data	return data

def getLemma(self, lemma=None, language=None):	def getLemma(self, lemma=None, language=None):
"""simular words lemma """	"""simular words lemma """
data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))	data = self.getServerData("lt/lemma.xql","language="+str(language)+"&lemma="+urllib.quote(lemma)+"&output=html")
#pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
return data	return data

def getLemmaNew(self, query=None, language=None):	def getLemmaQuery(self, query=None, language=None):
"""simular words lemma """	"""simular words lemma """
data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))	data = self.getServerData("lt/lemma.xql","language="+str(language)+"&query="+urllib.quote(query)+"&output=html")
#pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
return data	return data

def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionToggle=None):	def getLex(self, query=None, language=None):
"""number of"""	#simular words lemma
docpath = docinfo['textURLPath']	data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
pagesize = pageinfo['queryPageSize']	return data
pn = pageinfo['searchPN']
query =pageinfo['query']
queryType =pageinfo['queryType']
tocSearch = 0
tocDiv = None

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)
pagedom = Parse(pagexml)
numdivs = pagedom.xpath("//div[@class='queryResultHits']")
tocSearch = int(getTextFromNode(numdivs[0]))
logging.debug("documentViewer (gettoc) tocSearch: %s"%(tocSearch))
tc=int((tocSearch/10)+1)
logging.debug("documentViewer (gettoc) tc: %s"%(tc))
return tc

def getQueryResultHits(self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionsClose=None):

"""number of hits in Search mode"""	def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionToggle=None):
	#number of
docpath = docinfo['textURLPath']	docpath = docinfo['textURLPath']
pagesize = pageinfo['queryPageSize']	pagesize = pageinfo['queryPageSize']
pn = pageinfo['searchPN']	pn = pageinfo['searchPN']
Line 406 class MpdlXmlTextServer(SimpleItem):	Line 428 class MpdlXmlTextServer(SimpleItem):
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, urllib.quote(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)
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]))
tc=int((tocSearch/10)+1)	tc=int((tocSearch/10)+1)
return tc	return tc

def getQueryResultHitsText(self, docinfo=None, pageinfo=None):
"""number of hits in Text of Contents mode"""
selfurl = self.absolute_url()
docpath = docinfo['textURLPath']
viewMode= pageinfo['viewMode']
text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text'))
dom =Parse(text)
pagedivs = dom.xpath("//div[@class='countTocEntries']")
logging.debug ("pagedivs=%s"%(pagedivs))
if len(pagedivs)>0:
originalPage= (getTextFromNode(pagedivs[0]))
tc = int (originalPage)
tc1 =tc/30+1
return tc1

def getQueryResultHitsFigures(self, docinfo=None, pageinfo=None):
"""number of hits in Text of Figures mode"""

selfurl = self.absolute_url()
docpath = docinfo['textURLPath']
viewMode= pageinfo['viewMode']
text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text'))
dom =Parse(text)
pagedivs = dom.xpath("//div[@class='countFigureEntries']")
logging.debug ("pagedivs=%s"%(pagedivs))
if len(pagedivs)>0:
originalPage= (getTextFromNode(pagedivs[0]))
tc = int (originalPage)
tc1 =tc/30+1
return tc1


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 467 class MpdlXmlTextServer(SimpleItem):	Line 455 class MpdlXmlTextServer(SimpleItem):
tocDiv = None	tocDiv = None

pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))	pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
#pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
# post-processing downloaded xml	# post-processing downloaded xml
pagedom = Parse(pagexml)	pagedom = Parse(pagexml)
# get number of entries	# get number of entries
Line 499 class MpdlXmlTextServer(SimpleItem):	Line 487 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("documentViewer (characterNormalization) 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-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
	#def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/",timeout=40,RESPONSE=None):
"""change settings"""	"""change settings"""
self.title=title	self.title=title
self.timeout = timeout	self.timeout = timeout
Line 517 def manage_addMpdlXmlTextServerForm(self	Line 504 def manage_addMpdlXmlTextServerForm(self
pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)	pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
return pt()	return pt()

def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):	def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
	#def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/",timeout=40,RESPONSE=None):
"""add zogiimage"""	"""add zogiimage"""
newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)	newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
self.Destination()._setObject(id, newObj)	self.Destination()._setObject(id, newObj)
if RESPONSE is not None:	if RESPONSE is not None:
RESPONSE.redirect('manage_main')	RESPONSE.redirect('manage_main')

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>

Removed from v.1.221
changed lines
	Added in v.1.235