version 1.173, 2010/10/18 10:46:03
|
version 1.238, 2011/06/14 09:57:11
|
Line 2
|
Line 2
|
from OFS.SimpleItem import SimpleItem |
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 |
|
from Ft.Xml.Domlette import NonvalidatingReader |
|
|
|
import md5 |
import sys |
import sys |
import logging |
import logging |
import urllib |
import urllib |
Line 19 class MpdlXmlTextServer(SimpleItem):
|
Line 21 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-system.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 42 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, 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 51 class MpdlXmlTextServer(SimpleItem):
|
Line 55 class MpdlXmlTextServer(SimpleItem):
|
viewMode= pageinfo['viewMode'] |
viewMode= pageinfo['viewMode'] |
tocMode = pageinfo['tocMode'] |
tocMode = pageinfo['tocMode'] |
characterNormalization = pageinfo['characterNormalization'] |
characterNormalization = pageinfo['characterNormalization'] |
|
#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&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization, 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&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,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 70 class MpdlXmlTextServer(SimpleItem):
|
Line 86 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,urllib.quote(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&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN, 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 84 class MpdlXmlTextServer(SimpleItem):
|
Line 101 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,urllib.quote(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&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,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 102 class MpdlXmlTextServer(SimpleItem):
|
Line 119 class MpdlXmlTextServer(SimpleItem):
|
hrefNode = l.getAttributeNodeNS(None, u"href") |
hrefNode = l.getAttributeNodeNS(None, u"href") |
if hrefNode: |
if hrefNode: |
href = hrefNode.nodeValue |
href = hrefNode.nodeValue |
hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn)) |
hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,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 getNumPages(self, docinfo): |
|
""get list of pages from fulltext and put in docinfo"" |
|
if 'numPages' in docinfo: |
|
# already there |
|
return docinfo |
|
xquery = '//pb' |
|
text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) |
|
docinfo['numPages'] = text.count("<pb ") |
|
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): |
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' |
docpath = docinfo['textURLPath'] |
docpath = docinfo.get('textURLPath',None) |
|
if not docpath: |
|
return None |
|
|
url = docinfo['url'] |
url = docinfo['url'] |
selfurl = self.absolute_url() |
selfurl = self.absolute_url() |
pn = pageinfo['current'] |
pn = pageinfo['current'] |
Line 155 class MpdlXmlTextServer(SimpleItem):
|
Line 153 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 170 class MpdlXmlTextServer(SimpleItem):
|
Line 168 class MpdlXmlTextServer(SimpleItem):
|
text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath)) |
text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath)) |
dom =Parse(text) |
dom =Parse(text) |
result = dom.xpath("//result/resultPage/place") |
result = dom.xpath("//result/resultPage/place") |
|
|
for l in result: |
for l in result: |
hrefNode = l.getAttributeNodeNS(None, u"id") |
hrefNode = l.getAttributeNodeNS(None, u"id") |
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): |
|
"""Show original page """ |
|
#docpath = docinfo['textURLPath'] |
|
#url = docinfo['url'] |
|
selfurl = self.absolute_url() |
|
#pn =pageinfo['current'] |
|
|
|
#viewMode= pageinfo['viewMode'] |
|
#text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text', pn)) |
|
text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath'])) |
|
logging.debug("TEXTIXAXA:%s"%(text)) |
|
dom =Parse(text) |
|
pagedivs = dom.xpath("//div[@class='pageNumberOrig']") |
|
if len(pagedivs)>0: |
|
docinfo['originalPage'] = getTextFromNode(pagedivs[0]) |
|
#return docinfo['originalPage'] |
|
#return originalPage |
|
return docinfo |
|
|
|
def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=""): |
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['url'] |
url = docinfo.get('url',None) |
name = docinfo['name'] |
name = docinfo.get('name',None) |
viewMode= pageinfo['viewMode'] |
pn =pageinfo['current'] |
|
sn = pageinfo['sn'] |
|
#optionToggle =pageinfo ['optionToggle'] |
|
highlightQuery = pageinfo['highlightQuery'] |
|
#mode = pageinfo ['viewMode'] |
tocMode = pageinfo['tocMode'] |
tocMode = pageinfo['tocMode'] |
characterNormalization=pageinfo['characterNormalization'] |
characterNormalization=pageinfo['characterNormalization'] |
tocPN = pageinfo['tocPN'] |
tocPN = pageinfo['tocPN'] |
Line 212 class MpdlXmlTextServer(SimpleItem):
|
Line 197 class MpdlXmlTextServer(SimpleItem):
|
textmode = "textPollux" |
textmode = "textPollux" |
else: |
else: |
textmode = mode |
textmode = mode |
#logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization)) |
|
textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization) |
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"%(urllib.quote(highlightQuery),sn) |
textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn) |
|
|
pagexml = self.getServerData("page-fragment.xql",textParam) |
pagexml = self.getServerData("page-fragment.xql",textParam) |
#pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False) |
dom = Parse(pagexml) |
|
#dom = NonvalidatingReader.parseStream(pagexml) |
|
|
|
#original Pages |
|
pagedivs = dom.xpath("//div[@class='pageNumberOrig']") |
|
|
|
"""if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"): |
|
if len(pagedivs)>0: |
|
docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0]) |
|
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 |
|
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]) |
|
if s=='0': |
|
try: |
|
docinfo['countFigureEntries'] = int(s) |
|
except: |
|
docinfo['countFigureEntries'] = 0 |
|
else: |
|
s1 = int(s)/30+1 |
|
try: |
|
docinfo['countFigureEntries'] = int(s1) |
|
except: |
|
docinfo['countFigureEntries'] = 0 |
|
|
|
#allPlaces |
|
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]) |
|
try: |
|
docinfo['countPlaces'] = int(s) |
|
except: |
|
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: |
|
s1 = int(s)/30+1 |
|
try: |
|
docinfo['countTocEntries'] = int(s1) |
|
except: |
|
docinfo['countTocEntries'] = 0 |
|
|
|
#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)) |
|
|
|
np = docinfo['numPages'] |
|
pageinfo['end'] = min(pageinfo['end'], np) |
|
pageinfo['numgroups'] = int(np / pageinfo['groupsize']) |
|
if np % pageinfo['groupsize'] > 0: |
|
pageinfo['numgroups'] += 1 |
|
except: |
|
docinfo['numPages'] = 0 |
|
|
|
else: |
|
#no full text -- init to 0 |
|
docinfo['pageNumberOrig'] = 0 |
|
docinfo['countFigureEntries'] = 0 |
|
docinfo['countPlaces'] = 0 |
|
docinfo['countTocEntries'] = 0 |
|
docinfo['numPages'] = 0 |
|
docinfo['pageNumberOrigNorm'] = 0 |
|
#return docinfo |
|
|
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 233 class MpdlXmlTextServer(SimpleItem):
|
Line 309 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 258 class MpdlXmlTextServer(SimpleItem):
|
Line 334 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 |
links = pagenode.xpath("//a") |
links = pagenode.xpath("//a") |
|
|
for l in links: |
for l in links: |
hrefNode = l.getAttributeNodeNS(None, u"href") |
hrefNode = l.getAttributeNodeNS(None, u"href") |
|
|
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 |
|
|
|
def getLex(self, query=None, language=None): |
|
#simular words lemma |
|
data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query)) |
return data |
return data |
|
|
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'] |
pagesize = pageinfo['queryPageSize'] |
pagesize = pageinfo['queryPageSize'] |
pn = pageinfo['searchPN'] |
pn = pageinfo['searchPN'] |
Line 324 class MpdlXmlTextServer(SimpleItem):
|
Line 435 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) |
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 354 class MpdlXmlTextServer(SimpleItem):
|
Line 462 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 379 class MpdlXmlTextServer(SimpleItem):
|
Line 487 class MpdlXmlTextServer(SimpleItem):
|
selfurl = self.absolute_url() |
selfurl = self.absolute_url() |
viewMode= pageinfo['viewMode'] |
viewMode= pageinfo['viewMode'] |
characterNormalization = pageinfo ['characterNormalization'] |
characterNormalization = pageinfo ['characterNormalization'] |
|
#optionToggle =pageinfo ['optionToggle'] |
tocMode = pageinfo['tocMode'] |
tocMode = pageinfo['tocMode'] |
tocPN = pageinfo['tocPN'] |
tocPN = pageinfo['tocPN'] |
|
|
data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=%s"%(docpath,queryType, pagesize, pn,characterNormalization)) |
data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm"%(docpath,queryType, pagesize, pn)) |
page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN)) |
page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(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 403 def manage_addMpdlXmlTextServerForm(self
|
Line 511 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') |
|
|
|
|
|
|