Annotation of documentViewer/documentViewer.py, revision 1.52

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:             
                    198:         pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
                    199:         
1.21      dwinter   200:         if viewMode=="auto": # automodus gewaehlt
1.43      casties   201:             if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.21      dwinter   202:                 viewMode="text"
                    203:             else:
                    204:                 viewMode="images"
1.44      casties   205:                 
                    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
                    224:     
                    225:     def getStyle(self, idx, selected, style=""):
                    226:         """returns a string with the given style and append 'sel' if path == selected."""
                    227:         #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
                    228:         if idx == selected:
                    229:             return style + 'sel'
                    230:         else:
                    231:             return style
1.36      dwinter   232:     
1.4       casties   233:     def getLink(self,param=None,val=None):
                    234:         """link to documentviewer with parameter param set to val"""
1.9       casties   235:         params=self.REQUEST.form.copy()
1.4       casties   236:         if param is not None:
1.7       casties   237:             if val is None:
                    238:                 if params.has_key(param):
                    239:                     del params[param]
1.4       casties   240:             else:
1.9       casties   241:                 params[param] = str(val)
1.43      casties   242:                 
                    243:         if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38      dwinter   244:                 params["mode"] = "imagepath"
                    245:                 params["url"] = getParentDir(params["url"])
1.7       casties   246:                 
1.9       casties   247:         # quote values and assemble into query string
                    248:         ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
                    249:         url=self.REQUEST['URL1']+"?"+ps
1.4       casties   250:         return url
                    251: 
1.32      dwinter   252:     def getLinkAmp(self,param=None,val=None):
                    253:         """link to documentviewer with parameter param set to val"""
                    254:         params=self.REQUEST.form.copy()
                    255:         if param is not None:
                    256:             if val is None:
                    257:                 if params.has_key(param):
                    258:                     del params[param]
                    259:             else:
                    260:                 params[param] = str(val)
                    261:                 
                    262:         # quote values and assemble into query string
                    263:         logging.info("XYXXXXX: %s"%repr(params.items()))
                    264:         ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
                    265:         url=self.REQUEST['URL1']+"?"+ps
                    266:         return url
1.40      casties   267:     
1.26      casties   268:     def getInfo_xml(self,url,mode):
                    269:         """returns info about the document as XML"""
                    270: 
                    271:         if not self.digilibBaseUrl:
                    272:             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
                    273:         
                    274:         docinfo = self.getDocinfo(mode=mode,url=url)
                    275:         pt = getattr(self.template, 'info_xml')
                    276:         return pt(docinfo=docinfo)
                    277: 
1.4       casties   278:     
1.9       casties   279:     def isAccessible(self, docinfo):
1.8       casties   280:         """returns if access to the resource is granted"""
                    281:         access = docinfo.get('accessType', None)
1.22      dwinter   282:         logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
1.17      casties   283:         if access is not None and access == 'free':
1.22      dwinter   284:             logger("documentViewer (accessOK)", logging.INFO, "access is free")
1.8       casties   285:             return True
1.17      casties   286:         elif access is None or access in self.authgroups:
1.9       casties   287:             # only local access -- only logged in users
                    288:             user = getSecurityManager().getUser()
                    289:             if user is not None:
                    290:                 #print "user: ", user
                    291:                 return (user.getUserName() != "Anonymous User")
                    292:             else:
                    293:                 return False
1.8       casties   294:         
1.22      dwinter   295:         logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
1.8       casties   296:         return False
1.9       casties   297:     
1.8       casties   298:                 
1.35      dwinter   299:     def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6       casties   300:         """gibt param von dlInfo aus"""
1.13      casties   301:         num_retries = 3
1.7       casties   302:         if docinfo is None:
                    303:             docinfo = {}
1.35      dwinter   304:         
                    305:         for x in range(cut):
1.38      dwinter   306:                
1.35      dwinter   307:                 path=getParentDir(path)
1.38      dwinter   308:        
1.13      casties   309:         infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6       casties   310:     
1.22      dwinter   311:         logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
1.6       casties   312:         
1.13      casties   313:         for cnt in range(num_retries):
1.9       casties   314:             try:
1.13      casties   315:                 # dom = NonvalidatingReader.parseUri(imageUrl)
                    316:                 txt=urllib.urlopen(infoUrl).read()
                    317:                 dom = Parse(txt)
1.9       casties   318:                 break
                    319:             except:
1.22      dwinter   320:                 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9       casties   321:         else:
1.13      casties   322:             raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6       casties   323:         
1.10      casties   324:         sizes=dom.xpath("//dir/size")
1.22      dwinter   325:         logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
1.6       casties   326:         
1.10      casties   327:         if sizes:
                    328:             docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7       casties   329:         else:
                    330:             docinfo['numPages'] = 0
1.43      casties   331:             
                    332:         # TODO: produce and keep list of image names and numbers
1.7       casties   333:                         
                    334:         return docinfo
1.8       casties   335:     
1.6       casties   336:             
1.9       casties   337:     def getIndexMeta(self, url):
                    338:         """returns dom of index.meta document at url"""
1.12      casties   339:         num_retries = 3
1.9       casties   340:         dom = None
1.12      casties   341:         metaUrl = None
1.9       casties   342:         if url.startswith("http://"):
                    343:             # real URL
1.12      casties   344:             metaUrl = url
1.9       casties   345:         else:
                    346:             # online path
                    347:             server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13      casties   348:             metaUrl=server+url.replace("/mpiwg/online","")
1.9       casties   349:             if not metaUrl.endswith("index.meta"):
                    350:                 metaUrl += "/index.meta"
1.37      dwinter   351:         logging.debug("METAURL: %s"%metaUrl)
1.13      casties   352:         for cnt in range(num_retries):
1.9       casties   353:             try:
1.12      casties   354:                 # patch dirk encoding fehler treten dann nicht mehr auf
1.11      casties   355:                 # dom = NonvalidatingReader.parseUri(metaUrl)
1.12      casties   356:                 txt=urllib.urlopen(metaUrl).read()
                    357:                 dom = Parse(txt)
1.13      casties   358:                 break
1.9       casties   359:             except:
1.44      casties   360:                 logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.12      casties   361:                 
                    362:         if dom is None:
                    363:             raise IOError("Unable to read index meta from %s"%(url))
1.9       casties   364:                  
                    365:         return dom
1.20      dwinter   366:     
                    367:     def getPresentationInfoXML(self, url):
                    368:         """returns dom of info.xml document at url"""
                    369:         num_retries = 3
                    370:         dom = None
                    371:         metaUrl = None
                    372:         if url.startswith("http://"):
                    373:             # real URL
                    374:             metaUrl = url
                    375:         else:
                    376:             # online path
                    377:             server=self.digilibBaseUrl+"/servlet/Texter?fn="
                    378:             metaUrl=server+url.replace("/mpiwg/online","")
                    379:         
                    380:         for cnt in range(num_retries):
                    381:             try:
                    382:                 # patch dirk encoding fehler treten dann nicht mehr auf
                    383:                 # dom = NonvalidatingReader.parseUri(metaUrl)
                    384:                 txt=urllib.urlopen(metaUrl).read()
                    385:                 dom = Parse(txt)
                    386:                 break
                    387:             except:
1.22      dwinter   388:                 logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.20      dwinter   389:                 
                    390:         if dom is None:
                    391:             raise IOError("Unable to read infoXMLfrom %s"%(url))
                    392:                  
                    393:         return dom
1.9       casties   394:                         
                    395:         
1.33      dwinter   396:     def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9       casties   397:         """gets authorization info from the index.meta file at path or given by dom"""
1.22      dwinter   398:         logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
1.8       casties   399:         
                    400:         access = None
                    401:         
                    402:         if docinfo is None:
                    403:             docinfo = {}
                    404:             
                    405:         if dom is None:
1.38      dwinter   406:             for x in range(cut):
1.33      dwinter   407:                 path=getParentDir(path)
                    408:             dom = self.getIndexMeta(path)
1.18      dwinter   409:        
1.8       casties   410:         acctype = dom.xpath("//access-conditions/access/@type")
                    411:         if acctype and (len(acctype)>0):
                    412:             access=acctype[0].value
1.9       casties   413:             if access in ['group', 'institution']:
1.8       casties   414:                 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
                    415:             
                    416:         docinfo['accessType'] = access
                    417:         return docinfo
1.6       casties   418:     
1.8       casties   419:         
1.33      dwinter   420:     def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9       casties   421:         """gets bibliographical info from the index.meta file at path or given by dom"""
1.27      casties   422:         logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2       dwinter   423:         
1.3       casties   424:         if docinfo is None:
                    425:             docinfo = {}
1.38      dwinter   426:         
1.3       casties   427:         if dom is None:
1.38      dwinter   428:             for x in range(cut):
1.33      dwinter   429:                 path=getParentDir(path)
                    430:             dom = self.getIndexMeta(path)
1.39      dwinter   431:         
                    432:         logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27      casties   433:         # put in all raw bib fields as dict "bib"
                    434:         bib = dom.xpath("//bib/*")
                    435:         if bib and len(bib)>0:
                    436:             bibinfo = {}
                    437:             for e in bib:
                    438:                 bibinfo[e.localName] = getTextFromNode(e)
                    439:             docinfo['bib'] = bibinfo
                    440:         
                    441:         # extract some fields (author, title, year) according to their mapping
1.4       casties   442:         metaData=self.metadata.main.meta.bib
                    443:         bibtype=dom.xpath("//bib/@type")
                    444:         if bibtype and (len(bibtype)>0):
                    445:             bibtype=bibtype[0].value
1.2       dwinter   446:         else:
1.4       casties   447:             bibtype="generic"
1.27      casties   448:             
1.4       casties   449:         bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27      casties   450:         docinfo['bib_type'] = bibtype
1.4       casties   451:         bibmap=metaData.generateMappingForType(bibtype)
1.8       casties   452:         # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7       casties   453:         if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30      casties   454:             try:
                    455:                 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
                    456:             except: pass
                    457:             try:
                    458:                 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
                    459:             except: pass
                    460:             try:
                    461:                 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
                    462:             except: pass
1.27      casties   463:             logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22      dwinter   464:             try:
                    465:                 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
                    466:             except:
                    467:                 docinfo['lang']=''
1.27      casties   468: 
1.3       casties   469:         return docinfo
1.42      abukhman  470:     
                    471:     
1.43      casties   472:     def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
                    473:         """parse texttool tag in index meta"""
                    474:         logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))
                    475:         if docinfo is None:
                    476:            docinfo = {}
                    477:         if docinfo.get('lang', None) is None:
                    478:             docinfo['lang'] = '' # default keine Sprache gesetzt
                    479:         if dom is None:
                    480:             dom = self.getIndexMeta(url)
                    481:         
                    482:         archivePath = None
                    483:         archiveName = None
                    484:     
                    485:         archiveNames = dom.xpath("//resource/name")
                    486:         if archiveNames and (len(archiveNames) > 0):
                    487:             archiveName = getTextFromNode(archiveNames[0])
                    488:         else:
                    489:             logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url))
                    490:         
                    491:         archivePaths = dom.xpath("//resource/archive-path")
                    492:         if archivePaths and (len(archivePaths) > 0):
                    493:             archivePath = getTextFromNode(archivePaths[0])
                    494:             # clean up archive path
                    495:             if archivePath[0] != '/':
                    496:                 archivePath = '/' + archivePath
                    497:             if archiveName and (not archivePath.endswith(archiveName)):
                    498:                 archivePath += "/" + archiveName
                    499:         else:
                    500:             # try to get archive-path from url
                    501:             logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url))
                    502:             if (not url.startswith('http')):
                    503:                 archivePath = url.replace('index.meta', '')
                    504:                 
                    505:         if archivePath is None:
                    506:             # we balk without archive-path
                    507:             raise IOError("Missing archive-path (for text-tool) in %s" % (url))
                    508:         
                    509:         imageDirs = dom.xpath("//texttool/image")
                    510:         if imageDirs and (len(imageDirs) > 0):
                    511:             imageDir = getTextFromNode(imageDirs[0])
                    512:             
                    513:         else:
                    514:             # we balk with no image tag / not necessary anymore because textmode is now standard
                    515:             #raise IOError("No text-tool info in %s"%(url))
                    516:             imageDir = ""
                    517:             #xquery="//pb"  
                    518:             docinfo['imagePath'] = "" # keine Bilder
                    519:             docinfo['imageURL'] = ""
                    520:             
                    521:         if imageDir and archivePath:
                    522:             #print "image: ", imageDir, " archivepath: ", archivePath
                    523:             imageDir = os.path.join(archivePath, imageDir)
                    524:             imageDir = imageDir.replace("/mpiwg/online", '')
                    525:             docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
                    526:             docinfo['imagePath'] = imageDir
                    527:             
                    528:             docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
                    529:             
                    530:         viewerUrls = dom.xpath("//texttool/digiliburlprefix")
                    531:         if viewerUrls and (len(viewerUrls) > 0):
                    532:             viewerUrl = getTextFromNode(viewerUrls[0])
                    533:             docinfo['viewerURL'] = viewerUrl
                    534:                    
                    535:         textUrls = dom.xpath("//texttool/text")
                    536:         if textUrls and (len(textUrls) > 0):
                    537:             textUrl = getTextFromNode(textUrls[0])
                    538:             if urlparse.urlparse(textUrl)[0] == "": #keine url
                    539:                 textUrl = os.path.join(archivePath, textUrl) 
                    540:             # fix URLs starting with /mpiwg/online
                    541:             if textUrl.startswith("/mpiwg/online"):
                    542:                 textUrl = textUrl.replace("/mpiwg/online", '', 1)
                    543:             
                    544:             docinfo['textURL'] = textUrl
                    545:     
                    546:         textUrls = dom.xpath("//texttool/text-url-path")
                    547:         if textUrls and (len(textUrls) > 0):
                    548:             textUrl = getTextFromNode(textUrls[0])
1.51      casties   549:             docinfo['textURLPath'] = textUrl
                    550:             if not docinfo['imagePath']:
                    551:                 # text-only, no page images
                    552:                 docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht    
1.43      casties   553:          
                    554:         presentationUrls = dom.xpath("//texttool/presentation")
                    555:         docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get info von bib tag
                    556:         
                    557:         if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen 
                    558:              # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
                    559:              # durch den relativen Pfad auf die presentation infos
                    560:             presentationPath = getTextFromNode(presentationUrls[0])
                    561:             if url.endswith("index.meta"): 
                    562:                 presentationUrl = url.replace('index.meta', presentationPath)
                    563:             else:
                    564:                 presentationUrl = url + "/" + presentationPath
1.51      casties   565:                 
1.43      casties   566:             docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
                    567:     
                    568:         docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get access info
1.3       casties   569:         
1.43      casties   570:         return docinfo
1.3       casties   571:    
1.20      dwinter   572:    
                    573:     def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
                    574:         """gets the bibliographical information from the preseantion entry in texttools
                    575:         """
                    576:         dom=self.getPresentationInfoXML(url)
1.29      casties   577:         try:
                    578:             docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
                    579:         except:
                    580:             pass
                    581:         try:
                    582:             docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
                    583:         except:
                    584:             pass
                    585:         try:
                    586:             docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
                    587:         except:
                    588:             pass
1.20      dwinter   589:         return docinfo
                    590:     
1.33      dwinter   591:     def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3       casties   592:         """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.22      dwinter   593:         logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
1.3       casties   594:         if docinfo is None:
                    595:             docinfo = {}
1.6       casties   596:         path=path.replace("/mpiwg/online","")
1.3       casties   597:         docinfo['imagePath'] = path
1.35      dwinter   598:         docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38      dwinter   599:         
1.39      dwinter   600:         pathorig=path
1.38      dwinter   601:         for x in range(cut):       
                    602:                 path=getParentDir(path)
                    603:         logging.error("PATH:"+path)
1.7       casties   604:         imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3       casties   605:         docinfo['imageURL'] = imageUrl
                    606:         
1.39      dwinter   607:         #path ist the path to the images it assumes that the index.meta file is one level higher.
                    608:         docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
                    609:         docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3       casties   610:         return docinfo
                    611:     
1.2       dwinter   612:     
1.3       casties   613:     def getDocinfo(self, mode, url):
                    614:         """returns docinfo depending on mode"""
1.22      dwinter   615:         logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
1.3       casties   616:         # look for cached docinfo in session
1.21      dwinter   617:         if self.REQUEST.SESSION.has_key('docinfo'):
1.3       casties   618:             docinfo = self.REQUEST.SESSION['docinfo']
                    619:             # check if its still current
                    620:             if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.22      dwinter   621:                 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
1.3       casties   622:                 return docinfo
                    623:         # new docinfo
                    624:         docinfo = {'mode': mode, 'url': url}
                    625:         if mode=="texttool": #index.meta with texttool information
                    626:             docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
                    627:         elif mode=="imagepath":
                    628:             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33      dwinter   629:         elif mode=="filepath":
1.37      dwinter   630:             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3       casties   631:         else:
1.22      dwinter   632:             logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
1.44      casties   633:             raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10      casties   634:                         
1.22      dwinter   635:         logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
1.3       casties   636:         self.REQUEST.SESSION['docinfo'] = docinfo
                    637:         return docinfo
1.2       dwinter   638:         
                    639:         
1.44      casties   640:     def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3       casties   641:         """returns pageinfo with the given parameters"""
                    642:         pageinfo = {}
1.4       casties   643:         current = getInt(current)
                    644:         pageinfo['current'] = current
                    645:         rows = int(rows or self.thumbrows)
                    646:         pageinfo['rows'] = rows
                    647:         cols = int(cols or self.thumbcols)
                    648:         pageinfo['cols'] = cols
                    649:         grpsize = cols * rows
                    650:         pageinfo['groupsize'] = grpsize
1.28      casties   651:         start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
                    652:         # int(current / grpsize) * grpsize +1))
1.3       casties   653:         pageinfo['start'] = start
1.4       casties   654:         pageinfo['end'] = start + grpsize
1.44      casties   655:         if (docinfo is not None) and ('numPages' in docinfo):
1.4       casties   656:             np = int(docinfo['numPages'])
                    657:             pageinfo['end'] = min(pageinfo['end'], np)
                    658:             pageinfo['numgroups'] = int(np / grpsize)
                    659:             if np % grpsize > 0:
                    660:                 pageinfo['numgroups'] += 1
1.48      abukhman  661:         
                    662:           
1.44      casties   663:         pageinfo['viewMode'] = viewMode
                    664:         pageinfo['tocMode'] = tocMode
1.45      abukhman  665:         pageinfo['query'] = self.REQUEST.get('query',' ')
                    666:         pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
                    667:         pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48      abukhman  668:         
                    669:         pageinfo['textPN'] = self.REQUEST.get('textPN','1')
                    670:         
1.45      abukhman  671:         pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
                    672:         pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '20')
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'])
1.47      abukhman  680:             # cached toc
1.48      abukhman  681:            
                    682:             if tocSize%tocPageSize>0:
                    683:                 tocPages=tocSize/tocPageSize+1
                    684:             else:
                    685:                 tocPages=tocSize/tocPageSize
                    686:             pageinfo['tocPN'] = min (tocPages,toc)
                    687:                      
1.45      abukhman  688:         pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
                    689:         pageinfo['sn'] =self.REQUEST.get('sn','1')
1.38      dwinter   690: 
1.3       casties   691:         return pageinfo
                    692:                 
1.45      abukhman  693:     def getSearch(self, pn=1, pageinfo=None,  docinfo=None, query=None, queryType=None):
                    694:         """get search list"""
                    695:         docpath = docinfo['textURLPath'] 
1.50      abukhman  696:         url = docinfo['url']
                    697:         logging.debug("documentViewer (gettoc) docpath: %s"%(docpath))
                    698:         logging.debug("documentViewer (gettoc) url: %s"%(url))
1.45      abukhman  699:         pagesize = pageinfo['queryPageSize']
                    700:         pn = pageinfo['searchPN']
                    701:         sn = pageinfo['sn']
                    702:         query =pageinfo['query']
                    703:         queryType =pageinfo['queryType']
1.46      abukhman  704:         viewMode=  pageinfo['viewMode']
                    705:         tocMode = pageinfo['tocMode']
                    706:         tocPN = pageinfo['tocPN']
1.49      abukhman  707:         selfurl = self.absolute_url()
1.52    ! abukhman  708:         logging.debug("documentViewer (gettoc) /mpdl/interface/doc-query.xql?document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode))
1.49      abukhman  709:         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"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode) ,outputUnicode=False)                
1.50      abukhman  710:         pagexml = page.replace('?document=%s'%str(docpath),'?url=%s'%url)
1.45      abukhman  711:         pagedom = Parse(pagexml)
1.49      abukhman  712:         if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):   
                    713:             pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
                    714:             if len(pagedivs)>0:
                    715:                 pagenode=pagedivs[0]
                    716:                 links=pagenode.xpath("//a")
                    717:                 for l in links:
                    718:                     hrefNode = l.getAttributeNodeNS(None, u"href")
                    719:                     if hrefNode:
                    720:                         href = hrefNode.nodeValue
                    721:                         if href.startswith('page-fragment.xql'):
                    722:                             selfurl = self.absolute_url()
                    723:                             #l.setAttributeNS(None, "span class = 'hit highlight'", "background-color: #77DD77;")            
                    724:                             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))
1.50      abukhman  725:                             hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)                                          
1.52    ! abukhman  726:                             l.setAttributeNS(None, "onClick", "id='highlighting'")              
1.49      abukhman  727:                 return serializeNode(pagenode)
1.47      abukhman  728:         
1.49      abukhman  729:         if (queryType=="fulltextMorph"):
                    730:             pagedivs = pagedom.xpath("//div[@class='queryResult']")
                    731:             
                    732:             if len(pagedivs)>0:
                    733:                 pagenode=pagedivs[0]
                    734:                 links=pagenode.xpath("//a")
                    735:                 for l in links:
                    736:                     hrefNode = l.getAttributeNodeNS(None, u"href")
                    737:                     if hrefNode:
                    738:                         href = hrefNode.nodeValue
                    739:                         if href.startswith('page-fragment.xql'):
                    740:                             selfurl = self.absolute_url()       
                    741:                             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))
                    742:                             hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)  
                    743:                         if href.startswith('../lt/lemma.xql'):
                    744:                             selfurl = self.absolute_url()
                    745:                             hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)        
                    746:                             l.setAttributeNS(None, 'target', '_blank')
                    747:                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
                    748:                             l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')                  
                    749:                 return serializeNode(pagenode)
1.48      abukhman  750:         
                    751:         if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
                    752:             pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
                    753:             if len(pagedivs)>0:
                    754:                 pagenode=pagedivs[0]
                    755:                 links=pagenode.xpath("//a")
                    756:                 for l in links:
                    757:                     hrefNode = l.getAttributeNodeNS(None, u"href")
                    758:                     if hrefNode:
                    759:                         href = hrefNode.nodeValue
1.49      abukhman  760:                         hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
                    761:                        
1.48      abukhman  762:                         if href.startswith('../lt/lex.xql'):
1.52    ! abukhman  763:                            # selfurl = self.absolute_url()
        !           764:                             hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)         
1.48      abukhman  765:                             l.setAttributeNS(None, 'target', '_blank')
1.49      abukhman  766:                             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  767:                             l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
                    768:                         if href.startswith('../lt/lemma.xql'):
1.52    ! abukhman  769:                             #selfurl = self.absolute_url()
        !           770:                             hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl)        
1.48      abukhman  771:                             l.setAttributeNS(None, 'target', '_blank')
1.49      abukhman  772:                             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  773:                             l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.49      abukhman  774:                 return serializeNode(pagenode)      
1.50      abukhman  775:         return "no text here"   
1.47      abukhman  776:                        
1.43      casties   777:     def getNumPages(self,docinfo=None):
                    778:         """get list of pages from fulltext and put in docinfo"""
                    779:         xquery = '//pb'
                    780:         text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
                    781:         # TODO: better processing of the page list. do we need the info somewhere else also?
                    782:         docinfo['numPages'] = text.count("<pb ")
                    783:         return docinfo
                    784:        
1.46      abukhman  785:     def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None,):
1.43      casties   786:         """returns single page from fulltext"""
1.44      casties   787:         docpath = docinfo['textURLPath']
                    788:         if mode == "text_dict":
                    789:             textmode = "textPollux"
                    790:         else:
                    791:             textmode = mode
                    792:             
1.46      abukhman  793:         #selfurl = self.absolute_url()  
                    794:         #viewMode=  pageinfo['viewMode']
                    795:         #tocMode = pageinfo['tocMode']
                    796:         #tocPN = pageinfo['tocPN']
                    797:   
1.44      casties   798:         pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False)
1.43      casties   799:         # post-processing downloaded xml
                    800:         pagedom = Parse(pagexml)
                    801:         # plain text mode
                    802:         if mode == "text":
                    803:             # first div contains text
                    804:             pagedivs = pagedom.xpath("/div")
1.45      abukhman  805:             #queryResultPage
1.43      casties   806:             if len(pagedivs) > 0:
1.52    ! abukhman  807:                
1.43      casties   808:                 pagenode = pagedivs[0]
1.52    ! abukhman  809:                 links = pagenode.xpath("//a")
        !           810:                 for l in links:
        !           811:                     hrefNode = l.getAttributeNodeNS(None, u"href")
        !           812:                     if hrefNode:
        !           813:                         href= hrefNode.nodeValue
        !           814:                         if href.startswith('#note-0006-01'):
        !           815:                             selfurl = self.absolute_url()
        !           816:                             hrefNode.nodeValue = href.replace("href='#note-'",'xaxa/%s/'%selfurl)
1.43      casties   817:                 return serializeNode(pagenode)
1.48      abukhman  818:         if mode == "xml":
                    819:               # first div contains text
                    820:               pagedivs = pagedom.xpath("/div")
                    821:               if len(pagedivs) > 0:
                    822:                   pagenode = pagedivs[0]
                    823:                   return serializeNode(pagenode)
1.43      casties   824:         # text-with-links mode
1.44      casties   825:         if mode == "text_dict":
1.43      casties   826:             # first div contains text
                    827:             pagedivs = pagedom.xpath("/div")
                    828:             if len(pagedivs) > 0:
                    829:                 pagenode = pagedivs[0]
                    830:                 # check all a-tags
                    831:                 links = pagenode.xpath("//a")
                    832:                 for l in links:
                    833:                     hrefNode = l.getAttributeNodeNS(None, u"href")
                    834:                     if hrefNode:
                    835:                         # is link with href
                    836:                         href = hrefNode.nodeValue
                    837:                         if href.startswith('lt/lex.xql'):
                    838:                             # is pollux link
                    839:                             selfurl = self.absolute_url()
                    840:                             # change href
1.46      abukhman  841:                             hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
1.43      casties   842:                             # add target
                    843:                             l.setAttributeNS(None, 'target', '_blank')
1.48      abukhman  844:                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
                    845:                             l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.46      abukhman  846:                             
                    847:                         if href.startswith('lt/lemma.xql'):    
                    848:                             selfurl = self.absolute_url()
                    849:                             hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
                    850:                             l.setAttributeNS(None, 'target', '_blank')
1.48      abukhman  851:                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
                    852:                             l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.43      casties   853:                 return serializeNode(pagenode)
1.1       dwinter   854:         
1.43      casties   855:         return "no text here"
1.3       casties   856: 
1.46      abukhman  857:     def getTranslate(self, query=None, language=None):
                    858:         """translate into another languages"""
1.50      abukhman  859:         pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
1.46      abukhman  860:         return pagexml
                    861:     
1.47      abukhman  862:     def getLemma(self, lemma=None, language=None):
1.48      abukhman  863:         """simular words lemma """
1.50      abukhman  864:         pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
                    865:         #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False)
1.46      abukhman  866:         return pagexml
                    867: 
1.47      abukhman  868:     def getQuery (self,  docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
                    869:          """number of"""
                    870:          docpath = docinfo['textURLPath'] 
                    871:          pagesize = pageinfo['queryPageSize']
                    872:          pn = pageinfo['searchPN']
                    873:          query =pageinfo['query']
                    874:          queryType =pageinfo['queryType']
                    875: 
                    876:          tocSearch = 0
                    877:          tocDiv = None
                    878:          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)
                    879:          
                    880:          pagedom = Parse(pagexml)
                    881:          numdivs = pagedom.xpath("//div[@class='queryResultHits']")
                    882:          tocSearch = int(getTextFromNode(numdivs[0]))
                    883:          tc=int((tocSearch/20)+1)
                    884:          logging.debug("documentViewer (gettoc) tc: %s"%(tc))
                    885:          return tc
                    886: 
1.44      casties   887:     def getToc(self, mode="text", docinfo=None):
                    888:         """loads table of contents and stores in docinfo"""
                    889:         logging.debug("documentViewer (gettoc) mode: %s"%(mode))
                    890:         if 'tocSize_%s'%mode in docinfo:
                    891:             # cached toc
1.47      abukhman  892:             return docinfo 
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:             # div contains text
                    912:             #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
                    913:             #if len(pagedivs) > 0:
                    914:             #    tocDiv = pagedivs[0]
                    915: 
                    916:         docinfo['tocSize_%s'%mode] = tocSize
                    917:         #docinfo['tocDiv_%s'%mode] = tocDiv
                    918:         return docinfo
                    919:     
1.45      abukhman  920:     def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
1.44      casties   921:         """returns single page from the table of contents"""
                    922:         # TODO: this should use the cached TOC
                    923:         if mode == "text":
                    924:             queryType = "toc"
                    925:         else:
                    926:             queryType = mode
                    927:         docpath = docinfo['textURLPath']
1.50      abukhman  928:         path = docinfo['textURLPath']
                    929:         #logging.debug("documentViewer (gettoc) pathNomer: %s"%(pathNomer))
1.44      casties   930:         pagesize = pageinfo['tocPageSize']
                    931:         pn = pageinfo['tocPN']
1.50      abukhman  932:         url = docinfo['url']
1.46      abukhman  933:         selfurl = self.absolute_url()  
                    934:         viewMode=  pageinfo['viewMode']
                    935:         tocMode = pageinfo['tocMode']
                    936:         tocPN = pageinfo['tocPN']
                    937:     
1.45      abukhman  938:         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  939:         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  940:         text = page.replace('mode=image','mode=texttool')
                    941:         return text
1.44      casties   942:         # post-processing downloaded xml
1.46      abukhman  943:         #pagedom = Parse(text)
1.44      casties   944:         # div contains text
1.46      abukhman  945:         #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
                    946:         #if len(pagedivs) > 0:
                    947:         #    pagenode = pagedivs[0]
                    948:         #    return serializeNode(pagenode)
                    949:         #else:
                    950:         #    return "No TOC!"
1.44      casties   951: 
1.3       casties   952:     
1.45      abukhman  953:     def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3       casties   954:         """init document viewer"""
                    955:         self.title=title
                    956:         self.digilibBaseUrl = digilibBaseUrl
1.4       casties   957:         self.thumbrows = thumbrows
                    958:         self.thumbcols = thumbcols
1.8       casties   959:         self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3       casties   960:         if RESPONSE is not None:
                    961:             RESPONSE.redirect('manage_main')
1.1       dwinter   962:     
                    963:     
                    964:         
                    965: def manage_AddDocumentViewerForm(self):
                    966:     """add the viewer form"""
1.3       casties   967:     pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1       dwinter   968:     return pt()
                    969:   
1.43      casties   970: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1       dwinter   971:     """add the viewer"""
1.43      casties   972:     newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1       dwinter   973:     self._setObject(id,newObj)
                    974:     
                    975:     if RESPONSE is not None:
                    976:         RESPONSE.redirect('manage_main')
1.3       casties   977: 
                    978: 
                    979: ##
                    980: ## DocumentViewerTemplate class
                    981: ##
                    982: class DocumentViewerTemplate(ZopePageTemplate):
                    983:     """Template for document viewer"""
                    984:     meta_type="DocumentViewer Template"
                    985: 
                    986: 
                    987: def manage_addDocumentViewerTemplateForm(self):
                    988:     """Form for adding"""
                    989:     pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
                    990:     return pt()
                    991: 
                    992: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
                    993:                            REQUEST=None, submit=None):
                    994:     "Add a Page Template with optional file content."
                    995: 
                    996:     self._setObject(id, DocumentViewerTemplate(id))
                    997:     ob = getattr(self, id)
1.23      dwinter   998:     txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
                    999:     logging.info("txt %s:"%txt)
                   1000:     ob.pt_edit(txt,"text/html")
1.3       casties  1001:     if title:
                   1002:         ob.pt_setTitle(title)
                   1003:     try:
                   1004:         u = self.DestinationURL()
                   1005:     except AttributeError:
                   1006:         u = REQUEST['URL1']
                   1007:         
                   1008:     u = "%s/%s" % (u, urllib.quote(id))
                   1009:     REQUEST.RESPONSE.redirect(u+'/manage_main')
                   1010:     return ''
                   1011: 
                   1012: 
1.14      casties  1013:     

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