Annotation of documentViewer/documentViewer.py, revision 1.175.2.7

1.1       dwinter     1: from OFS.Folder import Folder
                      2: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
1.22      dwinter     3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile 
1.1       dwinter     4: from AccessControl import ClassSecurityInfo
1.8       casties     5: from AccessControl import getSecurityManager
1.1       dwinter     6: from Globals import package_home
                      7: 
1.175.2.1  casties     8: #from Ft.Xml import EMPTY_NAMESPACE, Parse 
                      9: #import Ft.Xml.Domlette
                     10: 
                     11: import xml.etree.ElementTree as ET
                     12: 
1.1       dwinter    13: import os.path
1.7       casties    14: import sys
1.1       dwinter    15: import urllib
1.20      dwinter    16: import logging
1.28      casties    17: import math
1.18      dwinter    18: import urlparse 
1.99      dwinter    19: import re
1.149     abukhman   20: import string
1.117     abukhman   21: 
1.175.2.5  casties    22: from SrvTxtUtils import getInt, getText, getHttpData
                     23: 
1.22      dwinter    24: def logger(txt,method,txt2):
                     25:     """logging"""
                     26:     logging.info(txt+ txt2)
                     27:     
                     28:     
1.170     abukhman   29: def serializeNode(node, encoding="utf-8"):
1.43      casties    30:     """returns a string containing node as XML"""
1.175.2.1  casties    31:     s = ET.tostring(node)
                     32:     
                     33:     # 4Suite:
                     34:     #    stream = cStringIO.StringIO()
                     35:     #    Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
                     36:     #    s = stream.getvalue()
                     37:     #    stream.close()
1.43      casties    38:     return s
                     39: 
1.148     abukhman   40: def browserCheck(self):
                     41:     """check the browsers request to find out the browser type"""
                     42:     bt = {}
                     43:     ua = self.REQUEST.get_header("HTTP_USER_AGENT")
                     44:     bt['ua'] = ua
                     45:     bt['isIE'] = False
                     46:     bt['isN4'] = False
1.165     abukhman   47:     bt['versFirefox']=""
                     48:     bt['versIE']=""
                     49:     bt['versSafariChrome']=""
                     50:     bt['versOpera']=""
                     51:     
1.148     abukhman   52:     if string.find(ua, 'MSIE') > -1:
                     53:         bt['isIE'] = True
                     54:     else:
                     55:         bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
1.165     abukhman   56:     # Safari oder Chrome identification    
                     57:     try:
                     58:         nav = ua[string.find(ua, '('):]
                     59:         nav1=ua[string.find(ua,')'):]
                     60:         nav2=nav1[string.find(nav1,'('):]
                     61:         nav3=nav2[string.find(nav2,')'):]
                     62:         ie = string.split(nav, "; ")[1]
                     63:         ie1 =string.split(nav1, " ")[2]
                     64:         ie2 =string.split(nav3, " ")[1]
                     65:         ie3 =string.split(nav3, " ")[2]
                     66:         if string.find(ie3, "Safari") >-1:
                     67:             bt['versSafariChrome']=string.split(ie2, "/")[1]
                     68:     except: pass
                     69:     # IE identification
1.148     abukhman   70:     try:
                     71:         nav = ua[string.find(ua, '('):]
                     72:         ie = string.split(nav, "; ")[1]
                     73:         if string.find(ie, "MSIE") > -1:
                     74:             bt['versIE'] = string.split(ie, " ")[1]
1.165     abukhman   75:     except:pass
                     76:     # Firefox identification
                     77:     try:
                     78:         nav = ua[string.find(ua, '('):]
                     79:         nav1=ua[string.find(ua,')'):]
                     80:         if string.find(ie1, "Firefox") >-1:
                     81:             nav5= string.split(ie1, "/")[1]
                     82:             logging.debug("FIREFOX: %s"%(nav5))
1.166     abukhman   83:             bt['versFirefox']=nav5[0:3]                   
1.165     abukhman   84:     except:pass
                     85:     #Opera identification
                     86:     try:
                     87:         if string.find(ua,"Opera") >-1:
                     88:             nav = ua[string.find(ua, '('):]
                     89:             nav1=nav[string.find(nav,')'):]
                     90:             bt['versOpera']=string.split(nav1,"/")[2]
                     91:     except:pass
1.148     abukhman   92:     
                     93:     bt['isMac'] = string.find(ua, 'Macintosh') > -1
                     94:     bt['isWin'] = string.find(ua, 'Windows') > -1
                     95:     bt['isIEWin'] = bt['isIE'] and bt['isWin']
                     96:     bt['isIEMac'] = bt['isIE'] and bt['isMac']
                     97:     bt['staticHTML'] = False
                     98: 
                     99:     return bt
1.118     abukhman  100: 
1.9       casties   101: def getParentDir(path):
                    102:     """returns pathname shortened by one"""
                    103:     return '/'.join(path.split('/')[0:-1])
                    104:         
1.175.2.7! casties   105: def normalizeBibtype(bt):
        !           106:     """returns normalised bib type for looking up mappings"""
        !           107:     bt = bt.strip().replace(' ', '-').lower()
        !           108:     return bt
        !           109: 
1.175.2.5  casties   110: def getBibdataFromDom(dom):
                    111:     """returns dict with all elements from bib-tag"""
                    112:     bibinfo = {}
                    113:     bib = dom.find(".//meta/bib")
                    114:     if bib is not None:
                    115:         # put type in @type
                    116:         type = bib.get('type')
1.175.2.7! casties   117:         bibinfo['@type'] = normalizeBibtype(type)
1.175.2.5  casties   118:         # put all subelements in dict
                    119:         for e in bib:
                    120:             bibinfo[e.tag] = getText(e)
                    121:             
                    122:     return bibinfo
1.1       dwinter   123: 
1.3       casties   124: ##
                    125: ## documentViewer class
                    126: ##
                    127: class documentViewer(Folder):
1.1       dwinter   128:     """document viewer"""
                    129:     meta_type="Document viewer"
                    130:     
                    131:     security=ClassSecurityInfo()
1.3       casties   132:     manage_options=Folder.manage_options+(
1.1       dwinter   133:         {'label':'main config','action':'changeDocumentViewerForm'},
                    134:         )
                    135: 
1.3       casties   136:     # templates and forms
                    137:     viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44      casties   138:     toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
                    139:     toc_text = PageTemplateFile('zpt/toc_text', globals())
                    140:     toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43      casties   141:     page_main_images = PageTemplateFile('zpt/page_main_images', globals())
1.161     abukhman  142:     page_main_double = PageTemplateFile('zpt/page_main_double', globals())
1.43      casties   143:     page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44      casties   144:     page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77      abukhman  145:     page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48      abukhman  146:     page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.157     abukhman  147:     page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
1.3       casties   148:     head_main = PageTemplateFile('zpt/head_main', globals())
                    149:     docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26      casties   150:     info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70      casties   151:     
                    152:     
1.32      dwinter   153:     thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3       casties   154:     security.declareProtected('View management screens','changeDocumentViewerForm')    
                    155:     changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
                    156: 
1.1       dwinter   157:     
1.45      abukhman  158:     def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1       dwinter   159:         """init document viewer"""
                    160:         self.id=id
                    161:         self.title=title
1.4       casties   162:         self.thumbcols = thumbcols
                    163:         self.thumbrows = thumbrows
1.8       casties   164:         # authgroups is list of authorized groups (delimited by ,)
                    165:         self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43      casties   166:         # create template folder so we can always use template.something
                    167:         
                    168:         templateFolder = Folder('template')
                    169:         #self['template'] = templateFolder # Zope-2.12 style
                    170:         self._setObject('template',templateFolder) # old style
                    171:         try:
1.70      casties   172:             import MpdlXmlTextServer
1.71      casties   173:             textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43      casties   174:             #templateFolder['fulltextclient'] = xmlRpcClient
1.70      casties   175:             templateFolder._setObject('fulltextclient',textServer)
1.43      casties   176:         except Exception, e:
1.70      casties   177:             logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43      casties   178:         try:
                    179:             from Products.zogiLib.zogiLib import zogiLib
                    180:             zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
                    181:             #templateFolder['zogilib'] = zogilib
                    182:             templateFolder._setObject('zogilib',zogilib)
                    183:         except Exception, e:
                    184:             logging.error("Unable to create zogiLib for zogilib: "+str(e))
                    185:         
1.70      casties   186:         
                    187:     # proxy text server methods to fulltextclient
                    188:     def getTextPage(self, **args):
                    189:         """get page"""
                    190:         return self.template.fulltextclient.getTextPage(**args)
1.171     abukhman  191: 
                    192:     def getOrigPages(self, **args):
                    193:         """get page"""
                    194:         return self.template.fulltextclient.getOrigPages(**args)
1.167     abukhman  195:     
1.171     abukhman  196:     def getOrigPagesNorm(self, **args):
                    197:         """get page"""
                    198:         return self.template.fulltextclient.getOrigPagesNorm(**args)
                    199: 
1.70      casties   200:     def getQuery(self, **args):
1.163     abukhman  201:         """get query in search"""
1.70      casties   202:         return self.template.fulltextclient.getQuery(**args)
1.163     abukhman  203:      
1.70      casties   204:     def getSearch(self, **args):
                    205:         """get search"""
                    206:         return self.template.fulltextclient.getSearch(**args)
1.120     abukhman  207:     
                    208:     def getGisPlaces(self, **args):
1.121     abukhman  209:         """get gis places"""
1.120     abukhman  210:         return self.template.fulltextclient.getGisPlaces(**args)
1.121     abukhman  211:  
                    212:     def getAllGisPlaces(self, **args):
1.122     abukhman  213:         """get all gis places """
                    214:         return self.template.fulltextclient.getAllGisPlaces(**args)
1.163     abukhman  215:        
1.70      casties   216:     def getTranslate(self, **args):
                    217:         """get translate"""
                    218:         return self.template.fulltextclient.getTranslate(**args)
                    219: 
                    220:     def getLemma(self, **args):
                    221:         """get lemma"""
                    222:         return self.template.fulltextclient.getLemma(**args)
                    223: 
1.173     abukhman  224:     def getLemmaQuery(self, **args):
                    225:         """get query"""
                    226:         return self.template.fulltextclient.getLemmaQuery(**args)
                    227: 
                    228:     def getLex(self, **args):
                    229:         """get lex"""
                    230:         return self.template.fulltextclient.getLex(**args)
                    231: 
1.70      casties   232:     def getToc(self, **args):
                    233:         """get toc"""
                    234:         return self.template.fulltextclient.getToc(**args)
                    235: 
                    236:     def getTocPage(self, **args):
                    237:         """get tocpage"""
                    238:         return self.template.fulltextclient.getTocPage(**args)
1.3       casties   239: 
1.70      casties   240:     
1.32      dwinter   241:     security.declareProtected('View','thumbs_rss')
                    242:     def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
                    243:         '''
                    244:         view it
                    245:         @param mode: defines how to access the document behind url 
                    246:         @param url: url which contains display information
                    247:         @param viewMode: if images display images, if text display text, default is images (text,images or auto)
                    248:         
                    249:         '''
1.95      abukhman  250:         logging.debug("HHHHHHHHHHHHHH:load the rss")
1.175.2.5  casties   251:         logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32      dwinter   252:         
                    253:         if not hasattr(self, 'template'):
                    254:             # create template folder if it doesn't exist
                    255:             self.manage_addFolder('template')
                    256:             
                    257:         if not self.digilibBaseUrl:
                    258:             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
                    259:             
                    260:         docinfo = self.getDocinfo(mode=mode,url=url)
1.132     abukhman  261:         #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138     abukhman  262:         pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126     abukhman  263:         ''' ZDES '''
1.32      dwinter   264:         pt = getattr(self.template, 'thumbs_main_rss')
                    265:         
                    266:         if viewMode=="auto": # automodus gewaehlt
1.159     casties   267:             if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.32      dwinter   268:                 viewMode="text"
                    269:             else:
                    270:                 viewMode="images"
                    271:                
                    272:         return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
                    273:   
1.3       casties   274:     security.declareProtected('View','index_html')
1.158     casties   275:     def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
1.3       casties   276:         '''
                    277:         view it
1.26      casties   278:         @param mode: defines how to access the document behind url 
1.3       casties   279:         @param url: url which contains display information
1.44      casties   280:         @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48      abukhman  281:         @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78      abukhman  282:         @param characterNormalization type of text display (reg, norm, none)
1.49      abukhman  283:         @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3       casties   284:         '''
                    285:         
1.138     abukhman  286:         logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1       dwinter   287:         
1.3       casties   288:         if not hasattr(self, 'template'):
1.43      casties   289:             # this won't work
                    290:             logging.error("template folder missing!")
                    291:             return "ERROR: template folder missing!"
1.3       casties   292:             
1.43      casties   293:         if not getattr(self, 'digilibBaseUrl', None):
1.71      casties   294:             self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3       casties   295:             
1.4       casties   296:         docinfo = self.getDocinfo(mode=mode,url=url)
1.47      abukhman  297:         
1.44      casties   298:         if tocMode != "thumbs":
                    299:             # get table of contents
                    300:             docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.175.2.3  casties   301: 
                    302:         # auto viewMode: text_dict if text else images
                    303:         if viewMode=="auto": 
                    304:             if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): 
                    305:                 #texturl gesetzt und textViewer konfiguriert
1.68      casties   306:                 viewMode="text_dict"
1.21      dwinter   307:             else:
                    308:                 viewMode="images"
1.44      casties   309:                 
1.175.2.3  casties   310:         pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode)
1.68      casties   311:         
1.175.2.3  casties   312:         if viewMode != 'images' and docinfo.get('textURLPath', None):
                    313:             # get full text page
                    314:             page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
1.163     abukhman  315:             pageinfo['textPage'] = page
1.175.2.3  casties   316:             
                    317:         # get template /template/viewer_main
                    318:         pt = getattr(self.template, 'viewer_main')
                    319:         # and execute with parameters
                    320:         return pt(docinfo=docinfo, pageinfo=pageinfo, viewMode=viewMode, mk=self.generateMarks(mk))
1.1       dwinter   321:   
1.36      dwinter   322:     def generateMarks(self,mk):
                    323:         ret=""
1.44      casties   324:         if mk is None:
                    325:             return ""
1.73      casties   326:         if not isinstance(mk, list):
1.71      casties   327:             mk=[mk]
1.36      dwinter   328:         for m in mk:
1.37      dwinter   329:             ret+="mk=%s"%m
1.36      dwinter   330:         return ret
1.149     abukhman  331:     
                    332:     
1.148     abukhman  333:     def getBrowser(self):
                    334:         """getBrowser the version of browser """
1.162     casties   335:         bt = browserCheck(self)
1.164     abukhman  336:         logging.debug("BROWSER VERSION: %s"%(bt))
1.162     casties   337:         return bt
1.148     abukhman  338:         
1.43      casties   339:     def findDigilibUrl(self):
                    340:         """try to get the digilib URL from zogilib"""
                    341:         url = self.template.zogilib.getDLBaseUrl()
                    342:         return url
1.67      casties   343: 
                    344:     def getDocumentViewerURL(self):
                    345:         """returns the URL of this instance"""
                    346:         return self.absolute_url()
1.43      casties   347:     
                    348:     def getStyle(self, idx, selected, style=""):
                    349:         """returns a string with the given style and append 'sel' if path == selected."""
                    350:         #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
                    351:         if idx == selected:
                    352:             return style + 'sel'
                    353:         else:
                    354:             return style
1.36      dwinter   355:     
1.162     casties   356:     def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
                    357:         """returns URL to documentviewer with parameter param set to val or from dict params"""
                    358:         # copy existing request params
                    359:         urlParams=self.REQUEST.form.copy()
                    360:         # change single param
1.4       casties   361:         if param is not None:
1.7       casties   362:             if val is None:
1.162     casties   363:                 if urlParams.has_key(param):
                    364:                     del urlParams[param]
1.4       casties   365:             else:
1.162     casties   366:                 urlParams[param] = str(val)
1.43      casties   367:                 
1.162     casties   368:         # change more params
                    369:         if params is not None:
                    370:             for k in params.keys():
                    371:                 v = params[k]
                    372:                 if v is None:
                    373:                     # val=None removes param
                    374:                     if urlParams.has_key(k):
                    375:                         del urlParams[k]
                    376:                         
                    377:                 else:
                    378:                     urlParams[k] = v
                    379: 
                    380:         # FIXME: does this belong here?
                    381:         if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
                    382:                 urlParams["mode"] = "imagepath"
                    383:                 urlParams["url"] = getParentDir(urlParams["url"])
1.7       casties   384:                 
1.162     casties   385:         # quote values and assemble into query string (not escaping '/')
                    386:         ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
                    387:         #ps = urllib.urlencode(urlParams)
                    388:         if baseUrl is None:
                    389:             baseUrl = self.REQUEST['URL1']
                    390:             
                    391:         url = "%s?%s"%(baseUrl, ps)
1.4       casties   392:         return url
                    393: 
1.162     casties   394: 
                    395:     def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
1.32      dwinter   396:         """link to documentviewer with parameter param set to val"""
1.162     casties   397:         return self.getLink(param, val, params, baseUrl, '&')
1.40      casties   398:     
1.26      casties   399:     def getInfo_xml(self,url,mode):
                    400:         """returns info about the document as XML"""
                    401: 
                    402:         if not self.digilibBaseUrl:
                    403:             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
                    404:         
                    405:         docinfo = self.getDocinfo(mode=mode,url=url)
                    406:         pt = getattr(self.template, 'info_xml')
                    407:         return pt(docinfo=docinfo)
                    408: 
1.153     casties   409:     def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
                    410:         """returns new option state"""
1.155     casties   411:         if not self.REQUEST.SESSION.has_key(optionName):
1.153     casties   412:             # not in session -- initial
                    413:             opt = {'lastState': newState, 'state': initialState}
                    414:         else:
1.155     casties   415:             opt = self.REQUEST.SESSION.get(optionName)
1.153     casties   416:             if opt['lastState'] != newState:
                    417:                 # state in session has changed -- toggle
                    418:                 opt['state'] = not opt['state']
                    419:                 opt['lastState'] = newState
                    420:         
                    421:         self.REQUEST.SESSION[optionName] = opt
                    422:         return opt['state']
1.4       casties   423:     
1.9       casties   424:     def isAccessible(self, docinfo):
1.8       casties   425:         """returns if access to the resource is granted"""
                    426:         access = docinfo.get('accessType', None)
1.95      abukhman  427:         logging.debug("documentViewer (accessOK) access type %s"%access)
1.17      casties   428:         if access is not None and access == 'free':
1.95      abukhman  429:             logging.debug("documentViewer (accessOK) access is free")
1.8       casties   430:             return True
1.17      casties   431:         elif access is None or access in self.authgroups:
1.9       casties   432:             # only local access -- only logged in users
                    433:             user = getSecurityManager().getUser()
1.95      abukhman  434:             logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9       casties   435:             if user is not None:
                    436:                 #print "user: ", user
                    437:                 return (user.getUserName() != "Anonymous User")
                    438:             else:
                    439:                 return False
1.8       casties   440:         
1.95      abukhman  441:         logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8       casties   442:         return False
1.9       casties   443:     
1.8       casties   444:                 
1.35      dwinter   445:     def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6       casties   446:         """gibt param von dlInfo aus"""
1.7       casties   447:         if docinfo is None:
                    448:             docinfo = {}
1.35      dwinter   449:         
                    450:         for x in range(cut):
1.175.2.2  casties   451:             path=getParentDir(path)
1.38      dwinter   452:        
1.13      casties   453:         infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6       casties   454:     
1.95      abukhman  455:         logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6       casties   456:         
1.70      casties   457:         txt = getHttpData(infoUrl)
                    458:         if txt is None:
1.13      casties   459:             raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70      casties   460: 
1.175.2.1  casties   461:         dom = ET.fromstring(txt)
                    462:         #dom = Parse(txt)
                    463:         size=getText(dom.find("size"))
                    464:         #sizes=dom.xpath("//dir/size")
                    465:         logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size)
1.6       casties   466:         
1.175.2.1  casties   467:         if size:
                    468:             docinfo['numPages'] = int(size)
1.7       casties   469:         else:
                    470:             docinfo['numPages'] = 0
1.43      casties   471:             
                    472:         # TODO: produce and keep list of image names and numbers
1.7       casties   473:                         
                    474:         return docinfo
1.8       casties   475:     
1.99      dwinter   476:     def getIndexMetaPath(self,url):
                    477:         """gib nur den Pfad zurueck"""
                    478:         regexp = re.compile(r".*(experimental|permanent)/(.*)")
                    479:         regpath = regexp.match(url)
                    480:         if (regpath==None):
                    481:             return ""
1.110     abukhman  482:         logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))            
1.99      dwinter   483:         return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
                    484:      
1.111     abukhman  485:     
                    486:     
1.99      dwinter   487:     def getIndexMetaUrl(self,url):
                    488:         """returns utr  of index.meta document at url"""
                    489:       
1.12      casties   490:         metaUrl = None
1.9       casties   491:         if url.startswith("http://"):
                    492:             # real URL
1.12      casties   493:             metaUrl = url
1.9       casties   494:         else:
                    495:             # online path
                    496:             server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13      casties   497:             metaUrl=server+url.replace("/mpiwg/online","")
1.9       casties   498:             if not metaUrl.endswith("index.meta"):
                    499:                 metaUrl += "/index.meta"
1.99      dwinter   500:         
                    501:         return metaUrl
                    502:     
                    503:     def getDomFromIndexMeta(self, url):
                    504:         """get dom from index meta"""
                    505:         dom = None
                    506:         metaUrl = self.getIndexMetaUrl(url)
1.12      casties   507:                 
1.99      dwinter   508:         logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70      casties   509:         txt=getHttpData(metaUrl)
                    510:         if txt is None:
1.12      casties   511:             raise IOError("Unable to read index meta from %s"%(url))
1.70      casties   512:         
1.175.2.1  casties   513:         dom = ET.fromstring(txt)
                    514:         #dom = Parse(txt)
1.9       casties   515:         return dom
1.20      dwinter   516:     
                    517:     def getPresentationInfoXML(self, url):
                    518:         """returns dom of info.xml document at url"""
                    519:         dom = None
                    520:         metaUrl = None
                    521:         if url.startswith("http://"):
                    522:             # real URL
                    523:             metaUrl = url
                    524:         else:
                    525:             # online path
                    526:             server=self.digilibBaseUrl+"/servlet/Texter?fn="
                    527:             metaUrl=server+url.replace("/mpiwg/online","")
                    528:         
1.70      casties   529:         txt=getHttpData(metaUrl)
                    530:         if txt is None:
1.20      dwinter   531:             raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70      casties   532:             
1.175.2.1  casties   533:         dom = ET.fromstring(txt)
                    534:         #dom = Parse(txt)
1.20      dwinter   535:         return dom
1.9       casties   536:                         
                    537:         
1.33      dwinter   538:     def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9       casties   539:         """gets authorization info from the index.meta file at path or given by dom"""
1.95      abukhman  540:         logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8       casties   541:         
                    542:         access = None
                    543:         
                    544:         if docinfo is None:
                    545:             docinfo = {}
                    546:             
                    547:         if dom is None:
1.38      dwinter   548:             for x in range(cut):
1.33      dwinter   549:                 path=getParentDir(path)
1.99      dwinter   550:             dom = self.getDomFromIndexMeta(path)
1.18      dwinter   551:        
1.175.2.1  casties   552:         acc = dom.find(".//access-conditions/access")
                    553:         if acc is not None:
                    554:             acctype = acc.get('type')
                    555:             #acctype = dom.xpath("//access-conditions/access/@type")
                    556:             if acctype:
                    557:                 access=acctype
                    558:                 if access in ['group', 'institution']:
                    559:                     access = dom.find(".//access-conditions/access/name").text.lower()
1.8       casties   560:             
                    561:         docinfo['accessType'] = access
                    562:         return docinfo
1.6       casties   563:     
1.8       casties   564:         
1.33      dwinter   565:     def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9       casties   566:         """gets bibliographical info from the index.meta file at path or given by dom"""
1.95      abukhman  567:         logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2       dwinter   568:         
1.3       casties   569:         if docinfo is None:
                    570:             docinfo = {}
1.38      dwinter   571:         
1.3       casties   572:         if dom is None:
1.38      dwinter   573:             for x in range(cut):
1.33      dwinter   574:                 path=getParentDir(path)
1.99      dwinter   575:             dom = self.getDomFromIndexMeta(path)
                    576:         
                    577:         docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39      dwinter   578:         
1.95      abukhman  579:         logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.175.2.6  casties   580:         # put all raw bib fields in dict "bib"
1.175.2.5  casties   581:         bib = getBibdataFromDom(dom)
                    582:         docinfo['bib'] = bib
1.175.2.7! casties   583:         bibtype = bib.get('@type', None)
1.27      casties   584:         docinfo['bib_type'] = bibtype
1.175.2.7! casties   585:         if bibtype:
        !           586:             # also store standard mapped metadata for convenience
1.30      casties   587:             try:
1.175.2.7! casties   588:                 stdbib = self.metadata.getStdMappedHash(bib)
        !           589:                 docinfo['std_bib'] = stdbib
        !           590:                 docinfo['author'] = stdbib['author']
        !           591:                 docinfo['title'] = stdbib['title']
        !           592:                 docinfo['year'] = stdbib['year']
        !           593:             except:
        !           594:                 pass
        !           595: 
1.3       casties   596:         return docinfo
1.42      abukhman  597:     
1.175.2.2  casties   598:     
                    599:     # TODO: is this needed?
1.104     abukhman  600:     def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
                    601:         """gets name info from the index.meta file at path or given by dom"""
                    602:         if docinfo is None:
                    603:             docinfo = {}
                    604:         
                    605:         if dom is None:
                    606:             for x in range(cut):
                    607:                 path=getParentDir(path)
                    608:             dom = self.getDomFromIndexMeta(path)
1.125     abukhman  609: 
1.175.2.1  casties   610:         docinfo['name']=getText(dom.find("name"))
1.116     abukhman  611:         logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104     abukhman  612:         return docinfo
1.42      abukhman  613:     
1.43      casties   614:     def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
                    615:         """parse texttool tag in index meta"""
1.95      abukhman  616:         logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43      casties   617:         if docinfo is None:
                    618:            docinfo = {}
                    619:         if docinfo.get('lang', None) is None:
                    620:             docinfo['lang'] = '' # default keine Sprache gesetzt
                    621:         if dom is None:
1.99      dwinter   622:             dom = self.getDomFromIndexMeta(url)
1.43      casties   623:         
                    624:         archivePath = None
                    625:         archiveName = None
                    626:     
1.175.2.2  casties   627:         archiveName = getText(dom.find("name"))
1.175.2.1  casties   628:         if not archiveName:
1.70      casties   629:             logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43      casties   630:         
1.175.2.2  casties   631:         archivePath = getText(dom.find("archive-path"))
1.175.2.1  casties   632:         if archivePath:
1.43      casties   633:             # clean up archive path
                    634:             if archivePath[0] != '/':
                    635:                 archivePath = '/' + archivePath
                    636:             if archiveName and (not archivePath.endswith(archiveName)):
                    637:                 archivePath += "/" + archiveName
                    638:         else:
                    639:             # try to get archive-path from url
1.95      abukhman  640:             logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43      casties   641:             if (not url.startswith('http')):
                    642:                 archivePath = url.replace('index.meta', '')
                    643:                 
                    644:         if archivePath is None:
                    645:             # we balk without archive-path
                    646:             raise IOError("Missing archive-path (for text-tool) in %s" % (url))
                    647:         
1.175.2.1  casties   648:         imageDir = getText(dom.find(".//texttool/image"))
1.43      casties   649:             
1.175.2.1  casties   650:         if not imageDir:
1.43      casties   651:             # we balk with no image tag / not necessary anymore because textmode is now standard
                    652:             #raise IOError("No text-tool info in %s"%(url))
                    653:             imageDir = ""
                    654:             #xquery="//pb"  
                    655:             docinfo['imagePath'] = "" # keine Bilder
                    656:             docinfo['imageURL'] = ""
                    657:             
                    658:         if imageDir and archivePath:
                    659:             #print "image: ", imageDir, " archivepath: ", archivePath
                    660:             imageDir = os.path.join(archivePath, imageDir)
                    661:             imageDir = imageDir.replace("/mpiwg/online", '')
                    662:             docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
                    663:             docinfo['imagePath'] = imageDir
                    664:             
                    665:             docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
                    666:             
1.175.2.1  casties   667:         viewerUrl = getText(dom.find(".//texttool/digiliburlprefix"))
                    668:         if viewerUrl:
1.43      casties   669:             docinfo['viewerURL'] = viewerUrl
1.70      casties   670:         
                    671:         # old style text URL
1.175.2.1  casties   672:         textUrl = getText(dom.find(".//texttool/text"))
                    673:         if textUrl:
1.43      casties   674:             if urlparse.urlparse(textUrl)[0] == "": #keine url
                    675:                 textUrl = os.path.join(archivePath, textUrl) 
                    676:             # fix URLs starting with /mpiwg/online
                    677:             if textUrl.startswith("/mpiwg/online"):
                    678:                 textUrl = textUrl.replace("/mpiwg/online", '', 1)
                    679:             
                    680:             docinfo['textURL'] = textUrl
                    681:     
1.70      casties   682:         # new style text-url-path
1.175.2.1  casties   683:         textUrl = getText(dom.find(".//texttool/text-url-path"))
                    684:         if textUrl:
1.51      casties   685:             docinfo['textURLPath'] = textUrl
1.169     abukhman  686:             textUrlkurz = string.split(textUrl, ".")[0]
                    687:             docinfo['textURLPathkurz'] = textUrlkurz
1.163     abukhman  688:             #if not docinfo['imagePath']:
1.51      casties   689:                 # text-only, no page images
1.163     abukhman  690:                 #docinfo = self.getNumTextPages(docinfo)
                    691:                   
1.43      casties   692:          
1.175.2.1  casties   693:         presentationUrl = getText(dom.find(".//texttool/presentation"))
1.43      casties   694:         docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get info von bib tag
1.175.2.2  casties   695:         # TODO: is this needed here?
1.114     abukhman  696:         docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.147     abukhman  697:         
1.43      casties   698:         
1.175.2.1  casties   699:         if presentationUrl: # ueberschreibe diese durch presentation informationen 
1.43      casties   700:              # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
                    701:              # durch den relativen Pfad auf die presentation infos
1.175.2.1  casties   702:             presentationPath = presentationUrl
1.43      casties   703:             if url.endswith("index.meta"): 
                    704:                 presentationUrl = url.replace('index.meta', presentationPath)
                    705:             else:
                    706:                 presentationUrl = url + "/" + presentationPath
1.51      casties   707:                 
1.43      casties   708:             docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
                    709:     
                    710:         docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get access info
1.3       casties   711:         
1.43      casties   712:         return docinfo
1.3       casties   713:    
1.20      dwinter   714:    
                    715:     def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
                    716:         """gets the bibliographical information from the preseantion entry in texttools
                    717:         """
                    718:         dom=self.getPresentationInfoXML(url)
1.175.2.2  casties   719:         docinfo['author']=getText(dom.find(".//author"))
                    720:         docinfo['title']=getText(dom.find(".//title"))
                    721:         docinfo['year']=getText(dom.find(".//date"))
1.20      dwinter   722:         return docinfo
                    723:     
1.33      dwinter   724:     def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3       casties   725:         """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95      abukhman  726:         logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3       casties   727:         if docinfo is None:
                    728:             docinfo = {}
1.6       casties   729:         path=path.replace("/mpiwg/online","")
1.3       casties   730:         docinfo['imagePath'] = path
1.35      dwinter   731:         docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38      dwinter   732:         
1.39      dwinter   733:         pathorig=path
1.38      dwinter   734:         for x in range(cut):       
                    735:                 path=getParentDir(path)
1.95      abukhman  736:         logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7       casties   737:         imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3       casties   738:         docinfo['imageURL'] = imageUrl
                    739:         
1.175.2.7! casties   740:         #TODO: use getDocinfoFromIndexMeta
1.39      dwinter   741:         #path ist the path to the images it assumes that the index.meta file is one level higher.
                    742:         docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
                    743:         docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3       casties   744:         return docinfo
                    745:     
1.2       dwinter   746:     
1.3       casties   747:     def getDocinfo(self, mode, url):
                    748:         """returns docinfo depending on mode"""
1.95      abukhman  749:         logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3       casties   750:         # look for cached docinfo in session
1.21      dwinter   751:         if self.REQUEST.SESSION.has_key('docinfo'):
1.3       casties   752:             docinfo = self.REQUEST.SESSION['docinfo']
                    753:             # check if its still current
                    754:             if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.175.2.3  casties   755:                 logging.debug("documentViewer (getdocinfo) docinfo in session. keys=%s"%docinfo.keys())
1.3       casties   756:                 return docinfo
1.175.2.3  casties   757:             
1.3       casties   758:         # new docinfo
                    759:         docinfo = {'mode': mode, 'url': url}
1.175.2.3  casties   760:         # add self url
                    761:         docinfo['viewerUrl'] = self.getDocumentViewerURL()
                    762:         if mode=="texttool": 
                    763:             # index.meta with texttool information
1.3       casties   764:             docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
                    765:         elif mode=="imagepath":
1.175.2.3  casties   766:             # folder with images, index.meta optional
1.3       casties   767:             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33      dwinter   768:         elif mode=="filepath":
1.175.2.3  casties   769:             # filename
1.37      dwinter   770:             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3       casties   771:         else:
1.95      abukhman  772:             logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44      casties   773:             raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.159     casties   774:                 
1.175.2.5  casties   775:         logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
                    776:         #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.175.2.7! casties   777:         # store in session
1.3       casties   778:         self.REQUEST.SESSION['docinfo'] = docinfo
                    779:         return docinfo
1.69      abukhman  780:                
1.158     casties   781:     def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3       casties   782:         """returns pageinfo with the given parameters"""
                    783:         pageinfo = {}
1.4       casties   784:         current = getInt(current)
1.132     abukhman  785:     
1.4       casties   786:         pageinfo['current'] = current
                    787:         rows = int(rows or self.thumbrows)
                    788:         pageinfo['rows'] = rows
                    789:         cols = int(cols or self.thumbcols)
                    790:         pageinfo['cols'] = cols
                    791:         grpsize = cols * rows
                    792:         pageinfo['groupsize'] = grpsize
1.175.2.7! casties   793:         # what does this do?
1.28      casties   794:         start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
                    795:         # int(current / grpsize) * grpsize +1))
1.3       casties   796:         pageinfo['start'] = start
1.4       casties   797:         pageinfo['end'] = start + grpsize
1.44      casties   798:         if (docinfo is not None) and ('numPages' in docinfo):
1.4       casties   799:             np = int(docinfo['numPages'])
                    800:             pageinfo['end'] = min(pageinfo['end'], np)
                    801:             pageinfo['numgroups'] = int(np / grpsize)
                    802:             if np % grpsize > 0:
1.175.2.7! casties   803:                 pageinfo['numgroups'] += 1
        !           804:                 
1.44      casties   805:         pageinfo['viewMode'] = viewMode
                    806:         pageinfo['tocMode'] = tocMode
1.161     abukhman  807:         pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
1.174     abukhman  808:         #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
1.156     abukhman  809:         pageinfo['query'] = self.REQUEST.get('query','') 
1.146     abukhman  810:         pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45      abukhman  811:         pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48      abukhman  812:         pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.146     abukhman  813:         pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45      abukhman  814:         pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54      abukhman  815:         pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.175.2.7! casties   816:         pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
        !           817:         # WTF?:
        !           818:         toc = int(pageinfo['tocPN'])
        !           819:         pageinfo['textPages'] =int(toc)
1.90      abukhman  820:         
1.175.2.7! casties   821:         # What does this do?
1.48      abukhman  822:         if 'tocSize_%s'%tocMode in docinfo:
                    823:             tocSize = int(docinfo['tocSize_%s'%tocMode])
                    824:             tocPageSize = int(pageinfo['tocPageSize'])
1.69      abukhman  825:             # cached toc           
1.48      abukhman  826:             if tocSize%tocPageSize>0:
                    827:                 tocPages=tocSize/tocPageSize+1
                    828:             else:
                    829:                 tocPages=tocSize/tocPageSize
1.175.2.7! casties   830:                 
        !           831:             pageinfo['tocPN'] = min(tocPages,toc)
        !           832:             
1.45      abukhman  833:         pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59      abukhman  834:         pageinfo['sn'] =self.REQUEST.get('sn','')
1.3       casties   835:         return pageinfo
1.175.2.7! casties   836: 
1.3       casties   837:     
1.175.2.7! casties   838:     def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3       casties   839:         """init document viewer"""
                    840:         self.title=title
                    841:         self.digilibBaseUrl = digilibBaseUrl
1.4       casties   842:         self.thumbrows = thumbrows
                    843:         self.thumbcols = thumbcols
1.8       casties   844:         self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3       casties   845:         if RESPONSE is not None:
                    846:             RESPONSE.redirect('manage_main')
1.1       dwinter   847:         
                    848: def manage_AddDocumentViewerForm(self):
                    849:     """add the viewer form"""
1.3       casties   850:     pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1       dwinter   851:     return pt()
                    852:   
1.43      casties   853: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1       dwinter   854:     """add the viewer"""
1.43      casties   855:     newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1       dwinter   856:     self._setObject(id,newObj)
                    857:     
                    858:     if RESPONSE is not None:
                    859:         RESPONSE.redirect('manage_main')
1.3       casties   860: 
                    861: ## DocumentViewerTemplate class
                    862: class DocumentViewerTemplate(ZopePageTemplate):
                    863:     """Template for document viewer"""
                    864:     meta_type="DocumentViewer Template"
                    865: 
                    866: 
                    867: def manage_addDocumentViewerTemplateForm(self):
                    868:     """Form for adding"""
                    869:     pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
                    870:     return pt()
                    871: 
                    872: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
                    873:                            REQUEST=None, submit=None):
                    874:     "Add a Page Template with optional file content."
                    875: 
                    876:     self._setObject(id, DocumentViewerTemplate(id))
                    877:     ob = getattr(self, id)
1.23      dwinter   878:     txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95      abukhman  879:     logging.info("txt %s:"%txt)
1.23      dwinter   880:     ob.pt_edit(txt,"text/html")
1.3       casties   881:     if title:
                    882:         ob.pt_setTitle(title)
                    883:     try:
                    884:         u = self.DestinationURL()
                    885:     except AttributeError:
                    886:         u = REQUEST['URL1']
                    887:         
                    888:     u = "%s/%s" % (u, urllib.quote(id))
                    889:     REQUEST.RESPONSE.redirect(u+'/manage_main')
                    890:     return ''
                    891: 
                    892: 
1.14      casties   893:     

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