version 1.69, 2010/06/11 10:34:24
|
version 1.69.2.2, 2010/06/16 16:38:17
|
Line 13 from Ft.Xml import EMPTY_NAMESPACE, Pars
|
Line 13 from Ft.Xml import EMPTY_NAMESPACE, Pars
|
|
|
from xml.dom.minidom import parse, parseString |
from xml.dom.minidom import parse, parseString |
|
|
|
from extraFunction import * |
|
|
|
|
import Ft.Xml.XPath |
import Ft.Xml.XPath |
Line 78 def urlopen(url,timeout=2):
|
Line 79 def urlopen(url,timeout=2):
|
## |
## |
## documentViewer class |
## documentViewer class |
## |
## |
class documentViewer(Folder): |
class documentViewer(Folder, extraFunction): |
"""document viewer""" |
"""document viewer""" |
#textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" |
#textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" |
|
|
Line 102 class documentViewer(Folder):
|
Line 103 class documentViewer(Folder):
|
docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) |
docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) |
info_xml = PageTemplateFile('zpt/info_xml', globals()) |
info_xml = PageTemplateFile('zpt/info_xml', globals()) |
|
|
|
|
thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
security.declareProtected('View management screens','changeDocumentViewerForm') |
security.declareProtected('View management screens','changeDocumentViewerForm') |
changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
Line 264 class documentViewer(Folder):
|
Line 266 class documentViewer(Folder):
|
params[param] = str(val) |
params[param] = str(val) |
|
|
# quote values and assemble into query string |
# quote values and assemble into query string |
logging.info("XYXXXXX: %s"%repr(params.items())) |
logging.debug("XYXXXXX: %s"%repr(params.items())) |
ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
url=self.REQUEST['URL1']+"?"+ps |
url=self.REQUEST['URL1']+"?"+ps |
return url |
return url |
Line 283 class documentViewer(Folder):
|
Line 285 class documentViewer(Folder):
|
def isAccessible(self, docinfo): |
def isAccessible(self, docinfo): |
"""returns if access to the resource is granted""" |
"""returns if access to the resource is granted""" |
access = docinfo.get('accessType', None) |
access = docinfo.get('accessType', None) |
logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
logging.debug("documentViewer (accessOK) access type %s"%access) |
if access is not None and access == 'free': |
if access is not None and access == 'free': |
logger("documentViewer (accessOK)", logging.INFO, "access is free") |
logging.debug("documentViewer (accessOK) access is free") |
return True |
return True |
elif access is None or access in self.authgroups: |
elif access is None or access in self.authgroups: |
# only local access -- only logged in users |
# only local access -- only logged in users |
Line 296 class documentViewer(Folder):
|
Line 298 class documentViewer(Folder):
|
else: |
else: |
return False |
return False |
|
|
logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
logging.debug("documentViewer (accessOK) unknown access type %s"%access) |
return False |
return False |
|
|
|
|
Line 312 class documentViewer(Folder):
|
Line 314 class documentViewer(Folder):
|
|
|
infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
|
|
logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) |
|
|
for cnt in range(num_retries): |
for cnt in range(num_retries): |
try: |
try: |
Line 321 class documentViewer(Folder):
|
Line 323 class documentViewer(Folder):
|
dom = Parse(txt) |
dom = Parse(txt) |
break |
break |
except: |
except: |
logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
logging.error("documentViewer (getdirinfofromdigilib) error reading %s (try %d)"%(infoUrl,cnt)) |
else: |
else: |
raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
|
|
sizes=dom.xpath("//dir/size") |
sizes=dom.xpath("//dir/size") |
logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) |
|
|
if sizes: |
if sizes: |
docinfo['numPages'] = int(getTextFromNode(sizes[0])) |
docinfo['numPages'] = int(getTextFromNode(sizes[0])) |
Line 361 class documentViewer(Folder):
|
Line 363 class documentViewer(Folder):
|
dom = Parse(txt) |
dom = Parse(txt) |
break |
break |
except: |
except: |
logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
logging.error("ERROR documentViewer (getIndexMeta) %s (%s)"%sys.exc_info()[0:2]) |
|
|
if dom is None: |
if dom is None: |
raise IOError("Unable to read index meta from %s"%(url)) |
raise IOError("Unable to read index meta from %s"%(url)) |
Line 389 class documentViewer(Folder):
|
Line 391 class documentViewer(Folder):
|
dom = Parse(txt) |
dom = Parse(txt) |
break |
break |
except: |
except: |
logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
logging.error("ERROR documentViewer (getPresentationInfoXML) %s (%s)"%sys.exc_info()[0:2]) |
|
|
if dom is None: |
if dom is None: |
raise IOError("Unable to read infoXMLfrom %s"%(url)) |
raise IOError("Unable to read infoXMLfrom %s"%(url)) |
Line 399 class documentViewer(Folder):
|
Line 401 class documentViewer(Folder):
|
|
|
def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
"""gets authorization info from the index.meta file at path or given by dom""" |
"""gets authorization info from the index.meta file at path or given by dom""" |
logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) |
|
|
access = None |
access = None |
|
|
Line 475 class documentViewer(Folder):
|
Line 477 class documentViewer(Folder):
|
|
|
def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): |
def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): |
"""parse texttool tag in index meta""" |
"""parse texttool tag in index meta""" |
logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url)) |
logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) |
if docinfo is None: |
if docinfo is None: |
docinfo = {} |
docinfo = {} |
if docinfo.get('lang', None) is None: |
if docinfo.get('lang', None) is None: |
Line 490 class documentViewer(Folder):
|
Line 492 class documentViewer(Folder):
|
if archiveNames and (len(archiveNames) > 0): |
if archiveNames and (len(archiveNames) > 0): |
archiveName = getTextFromNode(archiveNames[0]) |
archiveName = getTextFromNode(archiveNames[0]) |
else: |
else: |
logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url)) |
logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) |
|
|
archivePaths = dom.xpath("//resource/archive-path") |
archivePaths = dom.xpath("//resource/archive-path") |
if archivePaths and (len(archivePaths) > 0): |
if archivePaths and (len(archivePaths) > 0): |
Line 502 class documentViewer(Folder):
|
Line 504 class documentViewer(Folder):
|
archivePath += "/" + archiveName |
archivePath += "/" + archiveName |
else: |
else: |
# try to get archive-path from url |
# try to get archive-path from url |
logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url)) |
logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url)) |
if (not url.startswith('http')): |
if (not url.startswith('http')): |
archivePath = url.replace('index.meta', '') |
archivePath = url.replace('index.meta', '') |
|
|
Line 594 class documentViewer(Folder):
|
Line 596 class documentViewer(Folder):
|
|
|
def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
"""path ist the path to the images it assumes that the index.meta file is one level higher.""" |
"""path ist the path to the images it assumes that the index.meta file is one level higher.""" |
logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) |
if docinfo is None: |
if docinfo is None: |
docinfo = {} |
docinfo = {} |
path=path.replace("/mpiwg/online","") |
path=path.replace("/mpiwg/online","") |
Line 604 class documentViewer(Folder):
|
Line 606 class documentViewer(Folder):
|
pathorig=path |
pathorig=path |
for x in range(cut): |
for x in range(cut): |
path=getParentDir(path) |
path=getParentDir(path) |
logging.error("PATH:"+path) |
logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) |
imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
docinfo['imageURL'] = imageUrl |
docinfo['imageURL'] = imageUrl |
|
|
Line 616 class documentViewer(Folder):
|
Line 618 class documentViewer(Folder):
|
|
|
def getDocinfo(self, mode, url): |
def getDocinfo(self, mode, url): |
"""returns docinfo depending on mode""" |
"""returns docinfo depending on mode""" |
logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) |
# look for cached docinfo in session |
# look for cached docinfo in session |
if self.REQUEST.SESSION.has_key('docinfo'): |
if self.REQUEST.SESSION.has_key('docinfo'): |
docinfo = self.REQUEST.SESSION['docinfo'] |
docinfo = self.REQUEST.SESSION['docinfo'] |
# check if its still current |
# check if its still current |
if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: |
if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: |
logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) |
return docinfo |
return docinfo |
# new docinfo |
# new docinfo |
docinfo = {'mode': mode, 'url': url} |
docinfo = {'mode': mode, 'url': url} |
Line 633 class documentViewer(Folder):
|
Line 635 class documentViewer(Folder):
|
elif mode=="filepath": |
elif mode=="filepath": |
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
else: |
else: |
logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
|
|
logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
self.REQUEST.SESSION['docinfo'] = docinfo |
self.REQUEST.SESSION['docinfo'] = docinfo |
return docinfo |
return docinfo |
|
|
Line 687 class documentViewer(Folder):
|
Line 689 class documentViewer(Folder):
|
pageinfo['sn'] =self.REQUEST.get('sn','') |
pageinfo['sn'] =self.REQUEST.get('sn','') |
return pageinfo |
return pageinfo |
|
|
def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None): |
|
"""get search list""" |
|
docpath = docinfo['textURLPath'] |
|
url = docinfo['url'] |
|
logging.debug("documentViewer (gettoc) docpath: %s"%(docpath)) |
|
logging.debug("documentViewer (gettoc) url: %s"%(url)) |
|
pagesize = pageinfo['queryPageSize'] |
|
pn = pageinfo['searchPN'] |
|
sn = pageinfo['sn'] |
|
highlightQuery = pageinfo['highlightQuery'] |
|
query =pageinfo['query'] |
|
queryType =pageinfo['queryType'] |
|
viewMode= pageinfo['viewMode'] |
|
tocMode = pageinfo['tocMode'] |
|
tocPN = pageinfo['tocPN'] |
|
selfurl = self.absolute_url() |
|
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 = page.replace('?document=%s'%str(docpath),'?url=%s'%url) |
|
pagedom = Parse(pagexml) |
|
if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"): |
|
pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
|
if len(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('page-fragment.xql'): |
|
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)) |
|
hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
|
return serializeNode(pagenode) |
|
if (queryType=="fulltextMorph"): |
|
pagedivs = pagedom.xpath("//div[@class='queryResult']") |
|
if len(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('page-fragment.xql'): |
|
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)) |
|
hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
|
if href.startswith('../lt/lemma.xql'): |
|
hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl)) |
|
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, 'onDblclick', 'popupWin.focus();') |
|
pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']") |
|
return serializeNode(pagenode) |
|
if (queryType=="ftIndex")or(queryType=="ftIndexMorph"): |
|
pagedivs= pagedom.xpath("//div[@class='queryResultPage']") |
|
if len(pagedivs)>0: |
|
pagenode=pagedivs[0] |
|
links=pagenode.xpath("//a") |
|
for l in links: |
|
hrefNode = l.getAttributeNodeNS(None, u"href") |
|
if hrefNode: |
|
href = hrefNode.nodeValue |
|
hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn)) |
|
if href.startswith('../lt/lex.xql'): |
|
hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl) |
|
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, 'onDblclick', 'popupWin.focus();') |
|
if href.startswith('../lt/lemma.xql'): |
|
hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl) |
|
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, 'onDblclick', 'popupWin.focus();') |
|
return serializeNode(pagenode) |
|
return "no text here" |
|
|
|
def getNumPages(self,docinfo=None): |
|
"""get list of pages from fulltext and put in docinfo""" |
|
xquery = '//pb' |
|
text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) |
|
# TODO: better processing of the page list. do we need the info somewhere else also? |
|
docinfo['numPages'] = text.count("<pb ") |
|
return docinfo |
|
|
|
def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None): |
|
"""returns single page from fulltext""" |
|
docpath = docinfo['textURLPath'] |
|
path = docinfo['textURLPath'] |
|
url = docinfo['url'] |
|
viewMode= pageinfo['viewMode'] |
|
tocMode = pageinfo['tocMode'] |
|
tocPN = pageinfo['tocPN'] |
|
selfurl = self.absolute_url() |
|
if mode == "text_dict": |
|
textmode = "textPollux" |
|
else: |
|
textmode = mode |
|
|
|
textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn) |
|
if highlightQuery is not None: |
|
textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn) |
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False) |
|
pagedom = Parse(pagexml) |
|
# plain text mode |
|
if mode == "text": |
|
# first div contains text |
|
pagedivs = pagedom.xpath("/div") |
|
if len(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('#note-'): |
|
hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) |
|
return serializeNode(pagenode) |
|
if mode == "xml": |
|
# first div contains text |
|
pagedivs = pagedom.xpath("/div") |
|
if len(pagedivs) > 0: |
|
pagenode = pagedivs[0] |
|
return serializeNode(pagenode) |
|
if mode == "pureXml": |
|
# first div contains text |
|
pagedivs = pagedom.xpath("/div") |
|
if len(pagedivs) > 0: |
|
pagenode = pagedivs[0] |
|
return serializeNode(pagenode) |
|
# text-with-links mode |
|
if mode == "text_dict": |
|
# first div contains text |
|
pagedivs = pagedom.xpath("/div") |
|
if len(pagedivs) > 0: |
|
pagenode = pagedivs[0] |
|
# check all a-tags |
|
links = pagenode.xpath("//a") |
|
for l in links: |
|
hrefNode = l.getAttributeNodeNS(None, u"href") |
|
if hrefNode: |
|
# is link with href |
|
href = hrefNode.nodeValue |
|
if href.startswith('lt/lex.xql'): |
|
# is pollux link |
|
selfurl = self.absolute_url() |
|
# change href |
|
hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl) |
|
# add target |
|
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, 'onDblclick', 'popupWin.focus();') |
|
if href.startswith('lt/lemma.xql'): |
|
selfurl = self.absolute_url() |
|
hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) |
|
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, 'onDblclick', 'popupWin.focus();') |
|
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)) |
|
return serializeNode(pagenode) |
|
return "no text here" |
|
|
|
def getTranslate(self, query=None, language=None): |
|
"""translate into another languages""" |
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) |
|
return pagexml |
|
|
|
def getLemma(self, lemma=None, language=None): |
|
"""simular words lemma """ |
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) |
|
return pagexml |
|
|
|
def getLemmaNew(self, query=None, language=None): |
|
"""simular words lemma """ |
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query))) |
|
return pagexml |
|
|
|
def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1): |
|
"""number of""" |
|
docpath = docinfo['textURLPath'] |
|
pagesize = pageinfo['queryPageSize'] |
|
pn = pageinfo['searchPN'] |
|
query =pageinfo['query'] |
|
queryType =pageinfo['queryType'] |
|
tocSearch = 0 |
|
tocDiv = None |
|
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])) |
|
tc=int((tocSearch/10)+1) |
|
logging.debug("documentViewer (gettoc) tc: %s"%(tc)) |
|
return tc |
|
|
|
def getToc(self, mode="text", docinfo=None): |
|
"""loads table of contents and stores in docinfo""" |
|
logging.debug("documentViewer (gettoc) mode: %s"%(mode)) |
|
if mode == "none": |
|
return docinfo |
|
if 'tocSize_%s'%mode in docinfo: |
|
# cached toc |
|
return docinfo |
|
|
|
docpath = docinfo['textURLPath'] |
|
# we need to set a result set size |
|
pagesize = 1000 |
|
pn = 1 |
|
if mode == "text": |
|
queryType = "toc" |
|
else: |
|
queryType = mode |
|
# number of entries in toc |
|
tocSize = 0 |
|
tocDiv = None |
|
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 |
|
pagedom = Parse(pagexml) |
|
# get number of entries |
|
numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
|
if len(numdivs) > 0: |
|
tocSize = int(getTextFromNode(numdivs[0])) |
|
docinfo['tocSize_%s'%mode] = tocSize |
|
return docinfo |
|
|
|
def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None): |
|
"""returns single page from the table of contents""" |
|
# TODO: this should use the cached TOC |
|
if mode == "text": |
|
queryType = "toc" |
|
else: |
|
queryType = mode |
|
docpath = docinfo['textURLPath'] |
|
path = docinfo['textURLPath'] |
|
pagesize = pageinfo['tocPageSize'] |
|
pn = pageinfo['tocPN'] |
|
url = docinfo['url'] |
|
selfurl = self.absolute_url() |
|
viewMode= pageinfo['viewMode'] |
|
tocMode = pageinfo['tocMode'] |
|
tocPN = pageinfo['tocPN'] |
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False) |
|
page = pagexml.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') |
|
return text |
|
|
|
def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
"""init document viewer""" |
"""init document viewer""" |
self.title=title |
self.title=title |