Annotation of documentViewer/documentViewer.py, revision 1.69

1.18      dwinter     1: 
1.1       dwinter     2: from OFS.Folder import Folder
                      3: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
1.22      dwinter     4: from Products.PageTemplates.PageTemplateFile import PageTemplateFile 
1.50      abukhman    5: from Products.PythonScripts.standard import url_quote
1.1       dwinter     6: from AccessControl import ClassSecurityInfo
1.8       casties     7: from AccessControl import getSecurityManager
1.1       dwinter     8: from Globals import package_home
                      9: 
                     10: from Ft.Xml.Domlette import NonvalidatingReader
                     11: from Ft.Xml.Domlette import PrettyPrint, Print
1.11      casties    12: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.1       dwinter    13: 
1.47      abukhman   14: from xml.dom.minidom import parse, parseString
                     15: 
                     16: 
1.42      abukhman   17: 
1.1       dwinter    18: import Ft.Xml.XPath
1.43      casties    19: import cStringIO
1.42      abukhman   20: import xmlrpclib
1.1       dwinter    21: import os.path
1.7       casties    22: import sys
1.1       dwinter    23: import cgi
                     24: import urllib
1.20      dwinter    25: import logging
1.28      casties    26: import math
1.22      dwinter    27: 
1.18      dwinter    28: import urlparse 
1.37      dwinter    29: from types import *
1.43      casties    30: 
1.22      dwinter    31: def logger(txt,method,txt2):
                     32:     """logging"""
                     33:     logging.info(txt+ txt2)
                     34:     
                     35:     
1.4       casties    36: def getInt(number, default=0):
                     37:     """returns always an int (0 in case of problems)"""
                     38:     try:
                     39:         return int(number)
                     40:     except:
1.29      casties    41:         return int(default)
1.4       casties    42: 
1.1       dwinter    43: def getTextFromNode(nodename):
1.18      dwinter    44:     """get the cdata content of a node"""
1.8       casties    45:     if nodename is None:
                     46:         return ""
1.1       dwinter    47:     nodelist=nodename.childNodes
                     48:     rc = ""
                     49:     for node in nodelist:
                     50:         if node.nodeType == node.TEXT_NODE:
                     51:            rc = rc + node.data
                     52:     return rc
                     53: 
1.43      casties    54: def serializeNode(node, encoding='utf-8'):
                     55:     """returns a string containing node as XML"""
                     56:     buf = cStringIO.StringIO()
                     57:     Print(node, stream=buf, encoding=encoding)
                     58:     s = buf.getvalue()
                     59:     buf.close()
                     60:     return s
                     61: 
1.9       casties    62:         
                     63: def getParentDir(path):
                     64:     """returns pathname shortened by one"""
                     65:     return '/'.join(path.split('/')[0:-1])
                     66:         
                     67: 
1.1       dwinter    68: import socket
                     69: 
1.8       casties    70: def urlopen(url,timeout=2):
1.1       dwinter    71:         """urlopen mit timeout"""
1.8       casties    72:         socket.setdefaulttimeout(timeout)
1.1       dwinter    73:         ret=urllib.urlopen(url)
                     74:         socket.setdefaulttimeout(5)
                     75:         return ret
                     76: 
                     77: 
1.3       casties    78: ##
                     79: ## documentViewer class
                     80: ##
                     81: class documentViewer(Folder):
1.1       dwinter    82:     """document viewer"""
1.20      dwinter    83:     #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
1.18      dwinter    84:     
1.1       dwinter    85:     meta_type="Document viewer"
                     86:     
                     87:     security=ClassSecurityInfo()
1.3       casties    88:     manage_options=Folder.manage_options+(
1.1       dwinter    89:         {'label':'main config','action':'changeDocumentViewerForm'},
                     90:         )
                     91: 
1.3       casties    92:     # templates and forms
                     93:     viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44      casties    94:     toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
                     95:     toc_text = PageTemplateFile('zpt/toc_text', globals())
                     96:     toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43      casties    97:     page_main_images = PageTemplateFile('zpt/page_main_images', globals())
                     98:     page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44      casties    99:     page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.48      abukhman  100:     page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3       casties   101:     head_main = PageTemplateFile('zpt/head_main', globals())
                    102:     docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26      casties   103:     info_xml = PageTemplateFile('zpt/info_xml', globals())
1.3       casties   104: 
1.32      dwinter   105:     thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3       casties   106:     security.declareProtected('View management screens','changeDocumentViewerForm')    
                    107:     changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
                    108: 
1.1       dwinter   109:     
1.45      abukhman  110:     def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1       dwinter   111:         """init document viewer"""
                    112:         self.id=id
                    113:         self.title=title
1.4       casties   114:         self.thumbcols = thumbcols
                    115:         self.thumbrows = thumbrows
1.8       casties   116:         # authgroups is list of authorized groups (delimited by ,)
                    117:         self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43      casties   118:         # create template folder so we can always use template.something
                    119:         
                    120:         templateFolder = Folder('template')
                    121:         #self['template'] = templateFolder # Zope-2.12 style
                    122:         self._setObject('template',templateFolder) # old style
                    123:         try:
                    124:             from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy
                    125:             xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)
                    126:             #templateFolder['fulltextclient'] = xmlRpcClient
                    127:             templateFolder._setObject('fulltextclient',xmlRpcClient)
                    128:         except Exception, e:
                    129:             logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))
                    130:         try:
                    131:             from Products.zogiLib.zogiLib import zogiLib
                    132:             zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
                    133:             #templateFolder['zogilib'] = zogilib
                    134:             templateFolder._setObject('zogilib',zogilib)
                    135:         except Exception, e:
                    136:             logging.error("Unable to create zogiLib for zogilib: "+str(e))
                    137:         
1.3       casties   138: 
1.32      dwinter   139:     security.declareProtected('View','thumbs_rss')
                    140:     def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
                    141:         '''
                    142:         view it
                    143:         @param mode: defines how to access the document behind url 
                    144:         @param url: url which contains display information
                    145:         @param viewMode: if images display images, if text display text, default is images (text,images or auto)
                    146:         
                    147:         '''
1.43      casties   148:         logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32      dwinter   149:         logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
                    150:         
                    151:         if not hasattr(self, 'template'):
                    152:             # create template folder if it doesn't exist
                    153:             self.manage_addFolder('template')
                    154:             
                    155:         if not self.digilibBaseUrl:
                    156:             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
                    157:             
                    158:         docinfo = self.getDocinfo(mode=mode,url=url)
                    159:         pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
                    160:         pt = getattr(self.template, 'thumbs_main_rss')
                    161:         
                    162:         if viewMode=="auto": # automodus gewaehlt
                    163:             if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
                    164:                 viewMode="text"
                    165:             else:
                    166:                 viewMode="images"
                    167:                
                    168:         return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
                    169:   
1.3       casties   170:     security.declareProtected('View','index_html')
1.45      abukhman  171:     def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3       casties   172:         '''
                    173:         view it
1.26      casties   174:         @param mode: defines how to access the document behind url 
1.3       casties   175:         @param url: url which contains display information
1.44      casties   176:         @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48      abukhman  177:         @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.49      abukhman  178:         @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3       casties   179:         '''
                    180:         
1.43      casties   181:         logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1       dwinter   182:         
1.3       casties   183:         if not hasattr(self, 'template'):
1.43      casties   184:             # this won't work
                    185:             logging.error("template folder missing!")
                    186:             return "ERROR: template folder missing!"
1.3       casties   187:             
1.43      casties   188:         if not getattr(self, 'digilibBaseUrl', None):
1.3       casties   189:             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
                    190:             
1.4       casties   191:         docinfo = self.getDocinfo(mode=mode,url=url)
1.47      abukhman  192:         
                    193:         
1.44      casties   194:         if tocMode != "thumbs":
                    195:             # get table of contents
                    196:             docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47      abukhman  197:             
1.21      dwinter   198:         if viewMode=="auto": # automodus gewaehlt
1.43      casties   199:             if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.68      casties   200:                 viewMode="text_dict"
1.21      dwinter   201:             else:
                    202:                 viewMode="images"
1.44      casties   203:                 
1.68      casties   204:         pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
                    205:         
1.44      casties   206:         pt = getattr(self.template, 'viewer_main')               
1.37      dwinter   207:         return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1       dwinter   208:   
1.36      dwinter   209:     def generateMarks(self,mk):
                    210:         ret=""
1.44      casties   211:         if mk is None:
                    212:             return ""
                    213:        if type(mk) is not ListType:
                    214:            mk=[mk]
1.36      dwinter   215:         for m in mk:
1.37      dwinter   216:             ret+="mk=%s"%m
1.36      dwinter   217:         return ret
1.43      casties   218: 
1.44      casties   219: 
1.43      casties   220:     def findDigilibUrl(self):
                    221:         """try to get the digilib URL from zogilib"""
                    222:         url = self.template.zogilib.getDLBaseUrl()
                    223:         return url
1.67      casties   224: 
                    225:     def getDocumentViewerURL(self):
                    226:         """returns the URL of this instance"""
                    227:         return self.absolute_url()
1.43      casties   228:     
                    229:     def getStyle(self, idx, selected, style=""):
                    230:         """returns a string with the given style and append 'sel' if path == selected."""
                    231:         #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
                    232:         if idx == selected:
                    233:             return style + 'sel'
                    234:         else:
                    235:             return style
1.36      dwinter   236:     
1.4       casties   237:     def getLink(self,param=None,val=None):
                    238:         """link to documentviewer with parameter param set to val"""
1.9       casties   239:         params=self.REQUEST.form.copy()
1.4       casties   240:         if param is not None:
1.7       casties   241:             if val is None:
                    242:                 if params.has_key(param):
                    243:                     del params[param]
1.4       casties   244:             else:
1.9       casties   245:                 params[param] = str(val)
1.43      casties   246:                 
                    247:         if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38      dwinter   248:                 params["mode"] = "imagepath"
                    249:                 params["url"] = getParentDir(params["url"])
1.7       casties   250:                 
1.9       casties   251:         # quote values and assemble into query string
                    252:         ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
                    253:         url=self.REQUEST['URL1']+"?"+ps
1.4       casties   254:         return url
                    255: 
1.32      dwinter   256:     def getLinkAmp(self,param=None,val=None):
                    257:         """link to documentviewer with parameter param set to val"""
                    258:         params=self.REQUEST.form.copy()
                    259:         if param is not None:
                    260:             if val is None:
                    261:                 if params.has_key(param):
                    262:                     del params[param]
                    263:             else:
                    264:                 params[param] = str(val)
                    265:                 
                    266:         # quote values and assemble into query string
                    267:         logging.info("XYXXXXX: %s"%repr(params.items()))
                    268:         ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
                    269:         url=self.REQUEST['URL1']+"?"+ps
                    270:         return url
1.40      casties   271:     
1.26      casties   272:     def getInfo_xml(self,url,mode):
                    273:         """returns info about the document as XML"""
                    274: 
                    275:         if not self.digilibBaseUrl:
                    276:             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
                    277:         
                    278:         docinfo = self.getDocinfo(mode=mode,url=url)
                    279:         pt = getattr(self.template, 'info_xml')
                    280:         return pt(docinfo=docinfo)
                    281: 
1.4       casties   282:     
1.9       casties   283:     def isAccessible(self, docinfo):
1.8       casties   284:         """returns if access to the resource is granted"""
                    285:         access = docinfo.get('accessType', None)
1.22      dwinter   286:         logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
1.17      casties   287:         if access is not None and access == 'free':
1.22      dwinter   288:             logger("documentViewer (accessOK)", logging.INFO, "access is free")
1.8       casties   289:             return True
1.17      casties   290:         elif access is None or access in self.authgroups:
1.9       casties   291:             # only local access -- only logged in users
                    292:             user = getSecurityManager().getUser()
                    293:             if user is not None:
                    294:                 #print "user: ", user
                    295:                 return (user.getUserName() != "Anonymous User")
                    296:             else:
                    297:                 return False
1.8       casties   298:         
1.22      dwinter   299:         logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
1.8       casties   300:         return False
1.9       casties   301:     
1.8       casties   302:                 
1.35      dwinter   303:     def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6       casties   304:         """gibt param von dlInfo aus"""
1.13      casties   305:         num_retries = 3
1.7       casties   306:         if docinfo is None:
                    307:             docinfo = {}
1.35      dwinter   308:         
                    309:         for x in range(cut):
1.38      dwinter   310:                
1.35      dwinter   311:                 path=getParentDir(path)
1.38      dwinter   312:        
1.13      casties   313:         infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6       casties   314:     
1.22      dwinter   315:         logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
1.6       casties   316:         
1.13      casties   317:         for cnt in range(num_retries):
1.9       casties   318:             try:
1.13      casties   319:                 # dom = NonvalidatingReader.parseUri(imageUrl)
                    320:                 txt=urllib.urlopen(infoUrl).read()
                    321:                 dom = Parse(txt)
1.9       casties   322:                 break
                    323:             except:
1.22      dwinter   324:                 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9       casties   325:         else:
1.13      casties   326:             raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6       casties   327:         
1.10      casties   328:         sizes=dom.xpath("//dir/size")
1.22      dwinter   329:         logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
1.6       casties   330:         
1.10      casties   331:         if sizes:
                    332:             docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7       casties   333:         else:
                    334:             docinfo['numPages'] = 0
1.43      casties   335:             
                    336:         # TODO: produce and keep list of image names and numbers
1.7       casties   337:                         
                    338:         return docinfo
1.8       casties   339:     
1.6       casties   340:             
1.9       casties   341:     def getIndexMeta(self, url):
                    342:         """returns dom of index.meta document at url"""
1.12      casties   343:         num_retries = 3
1.9       casties   344:         dom = None
1.12      casties   345:         metaUrl = None
1.9       casties   346:         if url.startswith("http://"):
                    347:             # real URL
1.12      casties   348:             metaUrl = url
1.9       casties   349:         else:
                    350:             # online path
                    351:             server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13      casties   352:             metaUrl=server+url.replace("/mpiwg/online","")
1.9       casties   353:             if not metaUrl.endswith("index.meta"):
                    354:                 metaUrl += "/index.meta"
1.37      dwinter   355:         logging.debug("METAURL: %s"%metaUrl)
1.13      casties   356:         for cnt in range(num_retries):
1.9       casties   357:             try:
1.12      casties   358:                 # patch dirk encoding fehler treten dann nicht mehr auf
1.11      casties   359:                 # dom = NonvalidatingReader.parseUri(metaUrl)
1.12      casties   360:                 txt=urllib.urlopen(metaUrl).read()
                    361:                 dom = Parse(txt)
1.13      casties   362:                 break
1.9       casties   363:             except:
1.44      casties   364:                 logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.12      casties   365:                 
                    366:         if dom is None:
                    367:             raise IOError("Unable to read index meta from %s"%(url))
1.9       casties   368:                  
                    369:         return dom
1.20      dwinter   370:     
                    371:     def getPresentationInfoXML(self, url):
                    372:         """returns dom of info.xml document at url"""
                    373:         num_retries = 3
                    374:         dom = None
                    375:         metaUrl = None
                    376:         if url.startswith("http://"):
                    377:             # real URL
                    378:             metaUrl = url
                    379:         else:
                    380:             # online path
                    381:             server=self.digilibBaseUrl+"/servlet/Texter?fn="
                    382:             metaUrl=server+url.replace("/mpiwg/online","")
                    383:         
                    384:         for cnt in range(num_retries):
                    385:             try:
                    386:                 # patch dirk encoding fehler treten dann nicht mehr auf
                    387:                 # dom = NonvalidatingReader.parseUri(metaUrl)
                    388:                 txt=urllib.urlopen(metaUrl).read()
                    389:                 dom = Parse(txt)
                    390:                 break
                    391:             except:
1.22      dwinter   392:                 logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.20      dwinter   393:                 
                    394:         if dom is None:
                    395:             raise IOError("Unable to read infoXMLfrom %s"%(url))
                    396:                  
                    397:         return dom
1.9       casties   398:                         
                    399:         
1.33      dwinter   400:     def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9       casties   401:         """gets authorization info from the index.meta file at path or given by dom"""
1.22      dwinter   402:         logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
1.8       casties   403:         
                    404:         access = None
                    405:         
                    406:         if docinfo is None:
                    407:             docinfo = {}
                    408:             
                    409:         if dom is None:
1.38      dwinter   410:             for x in range(cut):
1.33      dwinter   411:                 path=getParentDir(path)
                    412:             dom = self.getIndexMeta(path)
1.18      dwinter   413:        
1.8       casties   414:         acctype = dom.xpath("//access-conditions/access/@type")
                    415:         if acctype and (len(acctype)>0):
                    416:             access=acctype[0].value
1.9       casties   417:             if access in ['group', 'institution']:
1.8       casties   418:                 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
                    419:             
                    420:         docinfo['accessType'] = access
                    421:         return docinfo
1.6       casties   422:     
1.8       casties   423:         
1.33      dwinter   424:     def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9       casties   425:         """gets bibliographical info from the index.meta file at path or given by dom"""
1.27      casties   426:         logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2       dwinter   427:         
1.3       casties   428:         if docinfo is None:
                    429:             docinfo = {}
1.38      dwinter   430:         
1.3       casties   431:         if dom is None:
1.38      dwinter   432:             for x in range(cut):
1.33      dwinter   433:                 path=getParentDir(path)
                    434:             dom = self.getIndexMeta(path)
1.39      dwinter   435:         
                    436:         logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27      casties   437:         # put in all raw bib fields as dict "bib"
                    438:         bib = dom.xpath("//bib/*")
                    439:         if bib and len(bib)>0:
                    440:             bibinfo = {}
                    441:             for e in bib:
                    442:                 bibinfo[e.localName] = getTextFromNode(e)
                    443:             docinfo['bib'] = bibinfo
                    444:         
                    445:         # extract some fields (author, title, year) according to their mapping
1.4       casties   446:         metaData=self.metadata.main.meta.bib
                    447:         bibtype=dom.xpath("//bib/@type")
                    448:         if bibtype and (len(bibtype)>0):
                    449:             bibtype=bibtype[0].value
1.2       dwinter   450:         else:
1.4       casties   451:             bibtype="generic"
1.27      casties   452:             
1.4       casties   453:         bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27      casties   454:         docinfo['bib_type'] = bibtype
1.4       casties   455:         bibmap=metaData.generateMappingForType(bibtype)
1.8       casties   456:         # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7       casties   457:         if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30      casties   458:             try:
                    459:                 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
                    460:             except: pass
                    461:             try:
                    462:                 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
                    463:             except: pass
                    464:             try:
                    465:                 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
                    466:             except: pass
1.27      casties   467:             logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22      dwinter   468:             try:
                    469:                 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
                    470:             except:
                    471:                 docinfo['lang']=''
1.27      casties   472: 
1.3       casties   473:         return docinfo
1.42      abukhman  474:     
                    475:     
1.43      casties   476:     def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
                    477:         """parse texttool tag in index meta"""
                    478:         logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))
                    479:         if docinfo is None:
                    480:            docinfo = {}
                    481:         if docinfo.get('lang', None) is None:
                    482:             docinfo['lang'] = '' # default keine Sprache gesetzt
                    483:         if dom is None:
                    484:             dom = self.getIndexMeta(url)
                    485:         
                    486:         archivePath = None
                    487:         archiveName = None
                    488:     
                    489:         archiveNames = dom.xpath("//resource/name")
                    490:         if archiveNames and (len(archiveNames) > 0):
                    491:             archiveName = getTextFromNode(archiveNames[0])
                    492:         else:
                    493:             logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url))
                    494:         
                    495:         archivePaths = dom.xpath("//resource/archive-path")
                    496:         if archivePaths and (len(archivePaths) > 0):
                    497:             archivePath = getTextFromNode(archivePaths[0])
                    498:             # clean up archive path
                    499:             if archivePath[0] != '/':
                    500:                 archivePath = '/' + archivePath
                    501:             if archiveName and (not archivePath.endswith(archiveName)):
                    502:                 archivePath += "/" + archiveName
                    503:         else:
                    504:             # try to get archive-path from url
                    505:             logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url))
                    506:             if (not url.startswith('http')):
                    507:                 archivePath = url.replace('index.meta', '')
                    508:                 
                    509:         if archivePath is None:
                    510:             # we balk without archive-path
                    511:             raise IOError("Missing archive-path (for text-tool) in %s" % (url))
                    512:         
                    513:         imageDirs = dom.xpath("//texttool/image")
                    514:         if imageDirs and (len(imageDirs) > 0):
                    515:             imageDir = getTextFromNode(imageDirs[0])
                    516:             
                    517:         else:
                    518:             # we balk with no image tag / not necessary anymore because textmode is now standard
                    519:             #raise IOError("No text-tool info in %s"%(url))
                    520:             imageDir = ""
                    521:             #xquery="//pb"  
                    522:             docinfo['imagePath'] = "" # keine Bilder
                    523:             docinfo['imageURL'] = ""
                    524:             
                    525:         if imageDir and archivePath:
                    526:             #print "image: ", imageDir, " archivepath: ", archivePath
                    527:             imageDir = os.path.join(archivePath, imageDir)
                    528:             imageDir = imageDir.replace("/mpiwg/online", '')
                    529:             docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
                    530:             docinfo['imagePath'] = imageDir
                    531:             
                    532:             docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
                    533:             
                    534:         viewerUrls = dom.xpath("//texttool/digiliburlprefix")
                    535:         if viewerUrls and (len(viewerUrls) > 0):
                    536:             viewerUrl = getTextFromNode(viewerUrls[0])
                    537:             docinfo['viewerURL'] = viewerUrl
                    538:                    
                    539:         textUrls = dom.xpath("//texttool/text")
                    540:         if textUrls and (len(textUrls) > 0):
                    541:             textUrl = getTextFromNode(textUrls[0])
                    542:             if urlparse.urlparse(textUrl)[0] == "": #keine url
                    543:                 textUrl = os.path.join(archivePath, textUrl) 
                    544:             # fix URLs starting with /mpiwg/online
                    545:             if textUrl.startswith("/mpiwg/online"):
                    546:                 textUrl = textUrl.replace("/mpiwg/online", '', 1)
                    547:             
                    548:             docinfo['textURL'] = textUrl
                    549:     
                    550:         textUrls = dom.xpath("//texttool/text-url-path")
                    551:         if textUrls and (len(textUrls) > 0):
                    552:             textUrl = getTextFromNode(textUrls[0])
1.51      casties   553:             docinfo['textURLPath'] = textUrl
                    554:             if not docinfo['imagePath']:
                    555:                 # text-only, no page images
                    556:                 docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht    
1.43      casties   557:          
                    558:         presentationUrls = dom.xpath("//texttool/presentation")
                    559:         docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get info von bib tag
                    560:         
                    561:         if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen 
                    562:              # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
                    563:              # durch den relativen Pfad auf die presentation infos
                    564:             presentationPath = getTextFromNode(presentationUrls[0])
                    565:             if url.endswith("index.meta"): 
                    566:                 presentationUrl = url.replace('index.meta', presentationPath)
                    567:             else:
                    568:                 presentationUrl = url + "/" + presentationPath
1.51      casties   569:                 
1.43      casties   570:             docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
                    571:     
                    572:         docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get access info
1.3       casties   573:         
1.43      casties   574:         return docinfo
1.3       casties   575:    
1.20      dwinter   576:    
                    577:     def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
                    578:         """gets the bibliographical information from the preseantion entry in texttools
                    579:         """
                    580:         dom=self.getPresentationInfoXML(url)
1.29      casties   581:         try:
                    582:             docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
                    583:         except:
                    584:             pass
                    585:         try:
                    586:             docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
                    587:         except:
                    588:             pass
                    589:         try:
                    590:             docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
                    591:         except:
                    592:             pass
1.20      dwinter   593:         return docinfo
                    594:     
1.33      dwinter   595:     def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3       casties   596:         """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.22      dwinter   597:         logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
1.3       casties   598:         if docinfo is None:
                    599:             docinfo = {}
1.6       casties   600:         path=path.replace("/mpiwg/online","")
1.3       casties   601:         docinfo['imagePath'] = path
1.35      dwinter   602:         docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38      dwinter   603:         
1.39      dwinter   604:         pathorig=path
1.38      dwinter   605:         for x in range(cut):       
                    606:                 path=getParentDir(path)
                    607:         logging.error("PATH:"+path)
1.7       casties   608:         imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3       casties   609:         docinfo['imageURL'] = imageUrl
                    610:         
1.39      dwinter   611:         #path ist the path to the images it assumes that the index.meta file is one level higher.
                    612:         docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
                    613:         docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3       casties   614:         return docinfo
                    615:     
1.2       dwinter   616:     
1.3       casties   617:     def getDocinfo(self, mode, url):
                    618:         """returns docinfo depending on mode"""
1.22      dwinter   619:         logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
1.3       casties   620:         # look for cached docinfo in session
1.21      dwinter   621:         if self.REQUEST.SESSION.has_key('docinfo'):
1.3       casties   622:             docinfo = self.REQUEST.SESSION['docinfo']
                    623:             # check if its still current
                    624:             if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.22      dwinter   625:                 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
1.3       casties   626:                 return docinfo
                    627:         # new docinfo
                    628:         docinfo = {'mode': mode, 'url': url}
                    629:         if mode=="texttool": #index.meta with texttool information
                    630:             docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
                    631:         elif mode=="imagepath":
                    632:             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33      dwinter   633:         elif mode=="filepath":
1.37      dwinter   634:             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3       casties   635:         else:
1.22      dwinter   636:             logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
1.44      casties   637:             raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10      casties   638:                         
1.22      dwinter   639:         logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
1.3       casties   640:         self.REQUEST.SESSION['docinfo'] = docinfo
                    641:         return docinfo
1.69    ! abukhman  642:                
1.44      casties   643:     def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3       casties   644:         """returns pageinfo with the given parameters"""
                    645:         pageinfo = {}
1.4       casties   646:         current = getInt(current)
                    647:         pageinfo['current'] = current
                    648:         rows = int(rows or self.thumbrows)
                    649:         pageinfo['rows'] = rows
                    650:         cols = int(cols or self.thumbcols)
                    651:         pageinfo['cols'] = cols
                    652:         grpsize = cols * rows
                    653:         pageinfo['groupsize'] = grpsize
1.28      casties   654:         start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
                    655:         # int(current / grpsize) * grpsize +1))
1.3       casties   656:         pageinfo['start'] = start
1.4       casties   657:         pageinfo['end'] = start + grpsize
1.44      casties   658:         if (docinfo is not None) and ('numPages' in docinfo):
1.4       casties   659:             np = int(docinfo['numPages'])
                    660:             pageinfo['end'] = min(pageinfo['end'], np)
                    661:             pageinfo['numgroups'] = int(np / grpsize)
                    662:             if np % grpsize > 0:
1.69    ! abukhman  663:                 pageinfo['numgroups'] += 1        
1.44      casties   664:         pageinfo['viewMode'] = viewMode
                    665:         pageinfo['tocMode'] = tocMode
1.45      abukhman  666:         pageinfo['query'] = self.REQUEST.get('query',' ')
                    667:         pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
                    668:         pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48      abukhman  669:         pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55      abukhman  670:         pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45      abukhman  671:         pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54      abukhman  672:         pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44      casties   673:         pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48      abukhman  674:         toc = int (pageinfo['tocPN'])
                    675:         pageinfo['textPages'] =int (toc)
                    676:         
                    677:         if 'tocSize_%s'%tocMode in docinfo:
                    678:             tocSize = int(docinfo['tocSize_%s'%tocMode])
                    679:             tocPageSize = int(pageinfo['tocPageSize'])
1.69    ! abukhman  680:             # cached toc           
1.48      abukhman  681:             if tocSize%tocPageSize>0:
                    682:                 tocPages=tocSize/tocPageSize+1
                    683:             else:
                    684:                 tocPages=tocSize/tocPageSize
1.69    ! abukhman  685:             pageinfo['tocPN'] = min (tocPages,toc)                    
1.45      abukhman  686:         pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59      abukhman  687:         pageinfo['sn'] =self.REQUEST.get('sn','')
1.3       casties   688:         return pageinfo
                    689:                 
1.69    ! abukhman  690:     def getSearch(self, pn=1, pageinfo=None,  docinfo=None, query=None, queryType=None, lemma=None):
1.45      abukhman  691:         """get search list"""
                    692:         docpath = docinfo['textURLPath'] 
1.50      abukhman  693:         url = docinfo['url']
                    694:         logging.debug("documentViewer (gettoc) docpath: %s"%(docpath))
                    695:         logging.debug("documentViewer (gettoc) url: %s"%(url))
1.45      abukhman  696:         pagesize = pageinfo['queryPageSize']
                    697:         pn = pageinfo['searchPN']
                    698:         sn = pageinfo['sn']
1.55      abukhman  699:         highlightQuery = pageinfo['highlightQuery']
1.45      abukhman  700:         query =pageinfo['query']
                    701:         queryType =pageinfo['queryType']
1.46      abukhman  702:         viewMode=  pageinfo['viewMode']
                    703:         tocMode = pageinfo['tocMode']
                    704:         tocPN = pageinfo['tocPN']
1.49      abukhman  705:         selfurl = self.absolute_url()
1.56      abukhman  706:         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)                
1.50      abukhman  707:         pagexml = page.replace('?document=%s'%str(docpath),'?url=%s'%url)
1.45      abukhman  708:         pagedom = Parse(pagexml)
1.49      abukhman  709:         if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):   
                    710:             pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
                    711:             if len(pagedivs)>0:
                    712:                 pagenode=pagedivs[0]
                    713:                 links=pagenode.xpath("//a")
                    714:                 for l in links:
                    715:                     hrefNode = l.getAttributeNodeNS(None, u"href")
                    716:                     if hrefNode:
                    717:                         href = hrefNode.nodeValue
                    718:                         if href.startswith('page-fragment.xql'):
1.59      abukhman  719:                             selfurl = self.absolute_url()            
1.49      abukhman  720:                             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))
1.59      abukhman  721:                             hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)                                           
1.69    ! abukhman  722:                 return serializeNode(pagenode)        
1.49      abukhman  723:         if (queryType=="fulltextMorph"):
                    724:             pagedivs = pagedom.xpath("//div[@class='queryResult']")
                    725:             if len(pagedivs)>0:
                    726:                 pagenode=pagedivs[0]
                    727:                 links=pagenode.xpath("//a")
                    728:                 for l in links:
                    729:                     hrefNode = l.getAttributeNodeNS(None, u"href")
                    730:                     if hrefNode:
                    731:                         href = hrefNode.nodeValue
                    732:                         if href.startswith('page-fragment.xql'):
                    733:                             selfurl = self.absolute_url()       
                    734:                             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))
                    735:                             hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)  
                    736:                         if href.startswith('../lt/lemma.xql'):
1.69    ! abukhman  737:                             hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl))        
1.49      abukhman  738:                             l.setAttributeNS(None, 'target', '_blank')
                    739:                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.64      abukhman  740:                             l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')  
                    741:                 pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")                
1.69    ! abukhman  742:                 return serializeNode(pagenode)        
1.48      abukhman  743:         if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
                    744:             pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
                    745:             if len(pagedivs)>0:
                    746:                 pagenode=pagedivs[0]
                    747:                 links=pagenode.xpath("//a")
                    748:                 for l in links:
                    749:                     hrefNode = l.getAttributeNodeNS(None, u"href")
                    750:                     if hrefNode:
                    751:                         href = hrefNode.nodeValue
1.69    ! abukhman  752:                         hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))             
1.48      abukhman  753:                         if href.startswith('../lt/lex.xql'):
1.55      abukhman  754:                             hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)         
1.48      abukhman  755:                             l.setAttributeNS(None, 'target', '_blank')
1.49      abukhman  756:                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.48      abukhman  757:                             l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
                    758:                         if href.startswith('../lt/lemma.xql'):
1.55      abukhman  759:                             hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl)        
1.48      abukhman  760:                             l.setAttributeNS(None, 'target', '_blank')
1.49      abukhman  761:                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.48      abukhman  762:                             l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.49      abukhman  763:                 return serializeNode(pagenode)      
1.50      abukhman  764:         return "no text here"   
1.47      abukhman  765:                        
1.43      casties   766:     def getNumPages(self,docinfo=None):
                    767:         """get list of pages from fulltext and put in docinfo"""
                    768:         xquery = '//pb'
                    769:         text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
                    770:         # TODO: better processing of the page list. do we need the info somewhere else also?
                    771:         docinfo['numPages'] = text.count("<pb ")
                    772:         return docinfo
                    773:        
1.65      abukhman  774:     def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None):
1.43      casties   775:         """returns single page from fulltext"""
1.44      casties   776:         docpath = docinfo['textURLPath']
1.59      abukhman  777:         path = docinfo['textURLPath']
                    778:         url = docinfo['url']
                    779:         viewMode= pageinfo['viewMode']
                    780:         tocMode = pageinfo['tocMode']
                    781:         tocPN = pageinfo['tocPN']
                    782:         selfurl = self.absolute_url()   
1.44      casties   783:         if mode == "text_dict":
                    784:             textmode = "textPollux"
                    785:         else:
                    786:             textmode = mode
1.59      abukhman  787:         
                    788:         textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn)
                    789:         if highlightQuery is not None:
1.69    ! abukhman  790:             textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn)           
1.59      abukhman  791:         pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
1.43      casties   792:         pagedom = Parse(pagexml)
                    793:         # plain text mode
                    794:         if mode == "text":
                    795:             # first div contains text
                    796:             pagedivs = pagedom.xpath("/div")
1.59      abukhman  797:             if len(pagedivs) > 0:      
1.43      casties   798:                 pagenode = pagedivs[0]
1.52      abukhman  799:                 links = pagenode.xpath("//a")
                    800:                 for l in links:
                    801:                     hrefNode = l.getAttributeNodeNS(None, u"href")
                    802:                     if hrefNode:
                    803:                         href= hrefNode.nodeValue
1.59      abukhman  804:                         if href.startswith('#note-'):
                    805:                             hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.43      casties   806:                 return serializeNode(pagenode)
1.48      abukhman  807:         if mode == "xml":
                    808:               # first div contains text
                    809:               pagedivs = pagedom.xpath("/div")
                    810:               if len(pagedivs) > 0:
                    811:                   pagenode = pagedivs[0]
                    812:                   return serializeNode(pagenode)
1.66      abukhman  813:         if mode == "pureXml":
                    814:               # first div contains text
                    815:               pagedivs = pagedom.xpath("/div")
                    816:               if len(pagedivs) > 0:
                    817:                   pagenode = pagedivs[0]
                    818:                   return serializeNode(pagenode)      
1.43      casties   819:         # text-with-links mode
1.44      casties   820:         if mode == "text_dict":
1.43      casties   821:             # first div contains text
                    822:             pagedivs = pagedom.xpath("/div")
                    823:             if len(pagedivs) > 0:
                    824:                 pagenode = pagedivs[0]
                    825:                 # check all a-tags
                    826:                 links = pagenode.xpath("//a")
                    827:                 for l in links:
                    828:                     hrefNode = l.getAttributeNodeNS(None, u"href")
                    829:                     if hrefNode:
                    830:                         # is link with href
                    831:                         href = hrefNode.nodeValue
                    832:                         if href.startswith('lt/lex.xql'):
                    833:                             # is pollux link
                    834:                             selfurl = self.absolute_url()
                    835:                             # change href
1.46      abukhman  836:                             hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
1.43      casties   837:                             # add target
                    838:                             l.setAttributeNS(None, 'target', '_blank')
1.48      abukhman  839:                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
1.69    ! abukhman  840:                             l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')      
1.46      abukhman  841:                         if href.startswith('lt/lemma.xql'):    
                    842:                             selfurl = self.absolute_url()
                    843:                             hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
                    844:                             l.setAttributeNS(None, 'target', '_blank')
1.48      abukhman  845:                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
1.69    ! abukhman  846:                             l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')   
1.59      abukhman  847:                         if href.startswith('#note-'):
                    848:                             hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))    
1.43      casties   849:                 return serializeNode(pagenode)
                    850:         return "no text here"
1.3       casties   851: 
1.46      abukhman  852:     def getTranslate(self, query=None, language=None):
                    853:         """translate into another languages"""
1.50      abukhman  854:         pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
1.46      abukhman  855:         return pagexml
                    856:     
1.47      abukhman  857:     def getLemma(self, lemma=None, language=None):
1.48      abukhman  858:         """simular words lemma """
1.50      abukhman  859:         pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
1.69    ! abukhman  860:         return pagexml
        !           861:     
        !           862:     def getLemmaNew(self, query=None, language=None):
        !           863:         """simular words lemma """
        !           864:         pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
1.46      abukhman  865:         return pagexml
                    866: 
1.47      abukhman  867:     def getQuery (self,  docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
                    868:          """number of"""
                    869:          docpath = docinfo['textURLPath'] 
                    870:          pagesize = pageinfo['queryPageSize']
                    871:          pn = pageinfo['searchPN']
                    872:          query =pageinfo['query']
                    873:          queryType =pageinfo['queryType']
                    874:          tocSearch = 0
                    875:          tocDiv = None
                    876:          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)
                    877:          pagedom = Parse(pagexml)
                    878:          numdivs = pagedom.xpath("//div[@class='queryResultHits']")
                    879:          tocSearch = int(getTextFromNode(numdivs[0]))
1.54      abukhman  880:          tc=int((tocSearch/10)+1)
1.47      abukhman  881:          logging.debug("documentViewer (gettoc) tc: %s"%(tc))
                    882:          return tc
                    883: 
1.44      casties   884:     def getToc(self, mode="text", docinfo=None):
                    885:         """loads table of contents and stores in docinfo"""
                    886:         logging.debug("documentViewer (gettoc) mode: %s"%(mode))
1.67      casties   887:         if mode == "none":
1.69    ! abukhman  888:             return docinfo        
1.44      casties   889:         if 'tocSize_%s'%mode in docinfo:
                    890:             # cached toc
1.67      casties   891:             return docinfo
                    892:         
1.44      casties   893:         docpath = docinfo['textURLPath']
                    894:         # we need to set a result set size
                    895:         pagesize = 1000
                    896:         pn = 1
                    897:         if mode == "text":
                    898:             queryType = "toc"
                    899:         else:
                    900:             queryType = mode
                    901:         # number of entries in toc
                    902:         tocSize = 0
                    903:         tocDiv = None
                    904:         pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
                    905:         # post-processing downloaded xml
                    906:         pagedom = Parse(pagexml)
                    907:         # get number of entries
                    908:         numdivs = pagedom.xpath("//div[@class='queryResultHits']")
                    909:         if len(numdivs) > 0:
                    910:             tocSize = int(getTextFromNode(numdivs[0]))
                    911:         docinfo['tocSize_%s'%mode] = tocSize
                    912:         return docinfo
                    913:     
1.69    ! abukhman  914: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
1.44      casties   915:         """returns single page from the table of contents"""
                    916:         # TODO: this should use the cached TOC
                    917:         if mode == "text":
                    918:             queryType = "toc"
                    919:         else:
                    920:             queryType = mode
                    921:         docpath = docinfo['textURLPath']
1.69    ! abukhman  922:         path = docinfo['textURLPath']       
1.44      casties   923:         pagesize = pageinfo['tocPageSize']
                    924:         pn = pageinfo['tocPN']
1.50      abukhman  925:         url = docinfo['url']
1.46      abukhman  926:         selfurl = self.absolute_url()  
                    927:         viewMode=  pageinfo['viewMode']
                    928:         tocMode = pageinfo['tocMode']
1.69    ! abukhman  929:         tocPN = pageinfo['tocPN']    
1.45      abukhman  930:         pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False)
1.50      abukhman  931:         page = pagexml.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
1.46      abukhman  932:         text = page.replace('mode=image','mode=texttool')
                    933:         return text
1.3       casties   934:     
1.69    ! abukhman  935: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3       casties   936:         """init document viewer"""
                    937:         self.title=title
                    938:         self.digilibBaseUrl = digilibBaseUrl
1.4       casties   939:         self.thumbrows = thumbrows
                    940:         self.thumbcols = thumbcols
1.8       casties   941:         self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3       casties   942:         if RESPONSE is not None:
                    943:             RESPONSE.redirect('manage_main')
1.1       dwinter   944:         
                    945: def manage_AddDocumentViewerForm(self):
                    946:     """add the viewer form"""
1.3       casties   947:     pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1       dwinter   948:     return pt()
                    949:   
1.43      casties   950: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1       dwinter   951:     """add the viewer"""
1.43      casties   952:     newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1       dwinter   953:     self._setObject(id,newObj)
                    954:     
                    955:     if RESPONSE is not None:
                    956:         RESPONSE.redirect('manage_main')
1.3       casties   957: 
                    958: ## DocumentViewerTemplate class
                    959: class DocumentViewerTemplate(ZopePageTemplate):
                    960:     """Template for document viewer"""
                    961:     meta_type="DocumentViewer Template"
                    962: 
                    963: 
                    964: def manage_addDocumentViewerTemplateForm(self):
                    965:     """Form for adding"""
                    966:     pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
                    967:     return pt()
                    968: 
                    969: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
                    970:                            REQUEST=None, submit=None):
                    971:     "Add a Page Template with optional file content."
                    972: 
                    973:     self._setObject(id, DocumentViewerTemplate(id))
                    974:     ob = getattr(self, id)
1.23      dwinter   975:     txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
                    976:     logging.info("txt %s:"%txt)
                    977:     ob.pt_edit(txt,"text/html")
1.3       casties   978:     if title:
                    979:         ob.pt_setTitle(title)
                    980:     try:
                    981:         u = self.DestinationURL()
                    982:     except AttributeError:
                    983:         u = REQUEST['URL1']
                    984:         
                    985:     u = "%s/%s" % (u, urllib.quote(id))
                    986:     REQUEST.RESPONSE.redirect(u+'/manage_main')
                    987:     return ''
                    988: 
                    989: 
1.14      casties   990:     

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