Annotation of documentViewer/documentViewer.py, revision 1.167
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
1.1 dwinter 5: from AccessControl import ClassSecurityInfo
1.8 casties 6: from AccessControl import getSecurityManager
1.1 dwinter 7: from Globals import package_home
1.119 abukhman 8: from Products.zogiLib.zogiLib import browserCheck
1.1 dwinter 9:
1.70 casties 10: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.73 casties 11: import Ft.Xml.Domlette
1.1 dwinter 12: import os.path
1.7 casties 13: import sys
1.1 dwinter 14: import urllib
1.70 casties 15: import urllib2
1.20 dwinter 16: import logging
1.28 casties 17: import math
1.18 dwinter 18: import urlparse
1.70 casties 19: import cStringIO
1.99 dwinter 20: import re
1.149 abukhman 21: import string
1.117 abukhman 22:
1.22 dwinter 23: def logger(txt,method,txt2):
24: """logging"""
25: logging.info(txt+ txt2)
26:
27:
1.4 casties 28: def getInt(number, default=0):
29: """returns always an int (0 in case of problems)"""
30: try:
31: return int(number)
32: except:
1.29 casties 33: return int(default)
1.4 casties 34:
1.1 dwinter 35: def getTextFromNode(nodename):
1.18 dwinter 36: """get the cdata content of a node"""
1.8 casties 37: if nodename is None:
38: return ""
1.1 dwinter 39: nodelist=nodename.childNodes
40: rc = ""
41: for node in nodelist:
42: if node.nodeType == node.TEXT_NODE:
43: rc = rc + node.data
44: return rc
45:
1.43 casties 46: def serializeNode(node, encoding='utf-8'):
47: """returns a string containing node as XML"""
48: buf = cStringIO.StringIO()
1.75 casties 49: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
1.43 casties 50: s = buf.getvalue()
51: buf.close()
52: return s
53:
1.148 abukhman 54: def browserCheck(self):
55: """check the browsers request to find out the browser type"""
56: bt = {}
57: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
58: bt['ua'] = ua
59: bt['isIE'] = False
60: bt['isN4'] = False
1.165 abukhman 61: bt['versFirefox']=""
62: bt['versIE']=""
63: bt['versSafariChrome']=""
64: bt['versOpera']=""
65:
1.148 abukhman 66: if string.find(ua, 'MSIE') > -1:
67: bt['isIE'] = True
68: else:
69: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
1.165 abukhman 70: # Safari oder Chrome identification
71: try:
72: nav = ua[string.find(ua, '('):]
73: nav1=ua[string.find(ua,')'):]
74: nav2=nav1[string.find(nav1,'('):]
75: nav3=nav2[string.find(nav2,')'):]
76: ie = string.split(nav, "; ")[1]
77: ie1 =string.split(nav1, " ")[2]
78: ie2 =string.split(nav3, " ")[1]
79: ie3 =string.split(nav3, " ")[2]
80: if string.find(ie3, "Safari") >-1:
81: bt['versSafariChrome']=string.split(ie2, "/")[1]
82: except: pass
83: # IE identification
1.148 abukhman 84: try:
85: nav = ua[string.find(ua, '('):]
86: ie = string.split(nav, "; ")[1]
87: if string.find(ie, "MSIE") > -1:
88: bt['versIE'] = string.split(ie, " ")[1]
1.165 abukhman 89: except:pass
90: # Firefox identification
91: try:
92: nav = ua[string.find(ua, '('):]
93: nav1=ua[string.find(ua,')'):]
94: if string.find(ie1, "Firefox") >-1:
95: nav5= string.split(ie1, "/")[1]
96: logging.debug("FIREFOX: %s"%(nav5))
1.166 abukhman 97: bt['versFirefox']=nav5[0:3]
1.165 abukhman 98: except:pass
99: #Opera identification
100: try:
101: if string.find(ua,"Opera") >-1:
102: nav = ua[string.find(ua, '('):]
103: nav1=nav[string.find(nav,')'):]
104: bt['versOpera']=string.split(nav1,"/")[2]
105: except:pass
1.148 abukhman 106:
107: bt['isMac'] = string.find(ua, 'Macintosh') > -1
108: bt['isWin'] = string.find(ua, 'Windows') > -1
109: bt['isIEWin'] = bt['isIE'] and bt['isWin']
110: bt['isIEMac'] = bt['isIE'] and bt['isMac']
111: bt['staticHTML'] = False
112:
113: return bt
1.118 abukhman 114:
115:
1.9 casties 116: def getParentDir(path):
117: """returns pathname shortened by one"""
118: return '/'.join(path.split('/')[0:-1])
119:
120:
1.70 casties 121: def getHttpData(url, data=None, num_tries=3, timeout=10):
122: """returns result from url+data HTTP request"""
123: # we do GET (by appending data to url)
124: if isinstance(data, str) or isinstance(data, unicode):
125: # if data is string then append
126: url = "%s?%s"%(url,data)
127: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
128: # urlencode
129: url = "%s?%s"%(url,urllib.urlencode(data))
130:
131: response = None
132: errmsg = None
133: for cnt in range(num_tries):
134: try:
1.95 abukhman 135: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
1.70 casties 136: if sys.version_info < (2, 6):
137: # set timeout on socket -- ugly :-(
138: import socket
139: socket.setdefaulttimeout(float(timeout))
140: response = urllib2.urlopen(url)
141: else:
142: response = urllib2.urlopen(url,timeout=float(timeout))
143: # check result?
144: break
145: except urllib2.HTTPError, e:
1.95 abukhman 146: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
1.70 casties 147: errmsg = str(e)
148: # stop trying
149: break
150: except urllib2.URLError, e:
1.95 abukhman 151: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
1.70 casties 152: errmsg = str(e)
153: # stop trying
154: #break
155:
156: if response is not None:
157: data = response.read()
158: response.close()
159: return data
160:
161: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
162: #return None
1.1 dwinter 163:
164:
165:
1.3 casties 166: ##
167: ## documentViewer class
168: ##
169: class documentViewer(Folder):
1.1 dwinter 170: """document viewer"""
171: meta_type="Document viewer"
172:
173: security=ClassSecurityInfo()
1.3 casties 174: manage_options=Folder.manage_options+(
1.1 dwinter 175: {'label':'main config','action':'changeDocumentViewerForm'},
176: )
177:
1.3 casties 178: # templates and forms
179: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 180: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
181: toc_text = PageTemplateFile('zpt/toc_text', globals())
182: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 183: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
1.161 abukhman 184: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
1.43 casties 185: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 186: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 187: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 188: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.157 abukhman 189: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
1.3 casties 190: head_main = PageTemplateFile('zpt/head_main', globals())
191: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 192: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 193:
194:
1.32 dwinter 195: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 196: security.declareProtected('View management screens','changeDocumentViewerForm')
197: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
198:
1.1 dwinter 199:
1.45 abukhman 200: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 201: """init document viewer"""
202: self.id=id
203: self.title=title
1.4 casties 204: self.thumbcols = thumbcols
205: self.thumbrows = thumbrows
1.8 casties 206: # authgroups is list of authorized groups (delimited by ,)
207: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 208: # create template folder so we can always use template.something
209:
210: templateFolder = Folder('template')
211: #self['template'] = templateFolder # Zope-2.12 style
212: self._setObject('template',templateFolder) # old style
213: try:
1.70 casties 214: import MpdlXmlTextServer
1.71 casties 215: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 216: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 217: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 218: except Exception, e:
1.70 casties 219: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 220: try:
221: from Products.zogiLib.zogiLib import zogiLib
222: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
223: #templateFolder['zogilib'] = zogilib
224: templateFolder._setObject('zogilib',zogilib)
225: except Exception, e:
226: logging.error("Unable to create zogiLib for zogilib: "+str(e))
227:
1.70 casties 228:
229: # proxy text server methods to fulltextclient
230: def getTextPage(self, **args):
231: """get page"""
232: return self.template.fulltextclient.getTextPage(**args)
1.167 ! abukhman 233:
! 234: def getText(self, **args):
! 235: """get page text"""
! 236: return self.template.fulltextclient.getText(**args)
! 237:
! 238: def getXML(self, **args):
! 239: """get page xml"""
! 240: return self.template.fulltextclient.getXML(**args)
! 241:
! 242: def getDictionary(self, **args):
! 243: """get page dictionary"""
! 244: return self.template.fulltextclient.getDictionary(**args)
! 245:
1.70 casties 246: def getQuery(self, **args):
1.163 abukhman 247: """get query in search"""
1.70 casties 248: return self.template.fulltextclient.getQuery(**args)
1.163 abukhman 249:
1.70 casties 250: def getSearch(self, **args):
251: """get search"""
252: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 253:
254: def getGisPlaces(self, **args):
1.121 abukhman 255: """get gis places"""
1.120 abukhman 256: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 257:
258: def getAllGisPlaces(self, **args):
1.122 abukhman 259: """get all gis places """
260: return self.template.fulltextclient.getAllGisPlaces(**args)
1.163 abukhman 261:
1.70 casties 262: def getTranslate(self, **args):
263: """get translate"""
264: return self.template.fulltextclient.getTranslate(**args)
265:
266: def getLemma(self, **args):
267: """get lemma"""
268: return self.template.fulltextclient.getLemma(**args)
269:
270: def getToc(self, **args):
271: """get toc"""
272: return self.template.fulltextclient.getToc(**args)
273:
274: def getTocPage(self, **args):
275: """get tocpage"""
276: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 277:
1.70 casties 278:
1.32 dwinter 279: security.declareProtected('View','thumbs_rss')
280: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
281: '''
282: view it
283: @param mode: defines how to access the document behind url
284: @param url: url which contains display information
285: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
286:
287: '''
1.95 abukhman 288: logging.debug("HHHHHHHHHHHHHH:load the rss")
289: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 290:
291: if not hasattr(self, 'template'):
292: # create template folder if it doesn't exist
293: self.manage_addFolder('template')
294:
295: if not self.digilibBaseUrl:
296: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
297:
298: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 299: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 abukhman 300: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 301: ''' ZDES '''
1.32 dwinter 302: pt = getattr(self.template, 'thumbs_main_rss')
303:
304: if viewMode=="auto": # automodus gewaehlt
1.159 casties 305: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 306: viewMode="text"
307: else:
308: viewMode="images"
309:
310: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
311:
1.3 casties 312: security.declareProtected('View','index_html')
1.158 casties 313: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
1.3 casties 314: '''
315: view it
1.26 casties 316: @param mode: defines how to access the document behind url
1.3 casties 317: @param url: url which contains display information
1.44 casties 318: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 319: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 320: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 321: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 322: '''
323:
1.138 abukhman 324: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 325:
1.3 casties 326: if not hasattr(self, 'template'):
1.43 casties 327: # this won't work
328: logging.error("template folder missing!")
329: return "ERROR: template folder missing!"
1.3 casties 330:
1.43 casties 331: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 332: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 333:
1.4 casties 334: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 335:
1.44 casties 336: if tocMode != "thumbs":
337: # get table of contents
338: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 339:
1.21 dwinter 340: if viewMode=="auto": # automodus gewaehlt
1.159 casties 341: if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.68 casties 342: viewMode="text_dict"
1.21 dwinter 343: else:
344: viewMode="images"
1.44 casties 345:
1.138 abukhman 346: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 347:
1.163 abukhman 348: if (docinfo.get('textURLPath',None)):
349: page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo)
350: pageinfo['textPage'] = page
1.167 ! abukhman 351: tt = getattr(self, 'template')
! 352: pt = getattr(tt, 'viewer_main')
1.37 dwinter 353: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 354:
1.36 dwinter 355: def generateMarks(self,mk):
356: ret=""
1.44 casties 357: if mk is None:
358: return ""
1.73 casties 359: if not isinstance(mk, list):
1.71 casties 360: mk=[mk]
1.36 dwinter 361: for m in mk:
1.37 dwinter 362: ret+="mk=%s"%m
1.36 dwinter 363: return ret
1.149 abukhman 364:
365:
1.148 abukhman 366: def getBrowser(self):
367: """getBrowser the version of browser """
1.162 casties 368: bt = browserCheck(self)
1.164 abukhman 369: logging.debug("BROWSER VERSION: %s"%(bt))
1.162 casties 370: return bt
1.148 abukhman 371:
1.43 casties 372: def findDigilibUrl(self):
373: """try to get the digilib URL from zogilib"""
374: url = self.template.zogilib.getDLBaseUrl()
375: return url
1.67 casties 376:
377: def getDocumentViewerURL(self):
378: """returns the URL of this instance"""
379: return self.absolute_url()
1.43 casties 380:
381: def getStyle(self, idx, selected, style=""):
382: """returns a string with the given style and append 'sel' if path == selected."""
383: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
384: if idx == selected:
385: return style + 'sel'
386: else:
387: return style
1.36 dwinter 388:
1.162 casties 389: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
390: """returns URL to documentviewer with parameter param set to val or from dict params"""
391: # copy existing request params
392: urlParams=self.REQUEST.form.copy()
393: # change single param
1.4 casties 394: if param is not None:
1.7 casties 395: if val is None:
1.162 casties 396: if urlParams.has_key(param):
397: del urlParams[param]
1.4 casties 398: else:
1.162 casties 399: urlParams[param] = str(val)
1.43 casties 400:
1.162 casties 401: # change more params
402: if params is not None:
403: for k in params.keys():
404: v = params[k]
405: if v is None:
406: # val=None removes param
407: if urlParams.has_key(k):
408: del urlParams[k]
409:
410: else:
411: urlParams[k] = v
412:
413: # FIXME: does this belong here?
414: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
415: urlParams["mode"] = "imagepath"
416: urlParams["url"] = getParentDir(urlParams["url"])
1.7 casties 417:
1.162 casties 418: # quote values and assemble into query string (not escaping '/')
419: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
420: #ps = urllib.urlencode(urlParams)
421: if baseUrl is None:
422: baseUrl = self.REQUEST['URL1']
423:
424: url = "%s?%s"%(baseUrl, ps)
1.4 casties 425: return url
426:
1.162 casties 427:
428: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
1.32 dwinter 429: """link to documentviewer with parameter param set to val"""
1.162 casties 430: return self.getLink(param, val, params, baseUrl, '&')
1.40 casties 431:
1.26 casties 432: def getInfo_xml(self,url,mode):
433: """returns info about the document as XML"""
434:
435: if not self.digilibBaseUrl:
436: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
437:
438: docinfo = self.getDocinfo(mode=mode,url=url)
439: pt = getattr(self.template, 'info_xml')
440: return pt(docinfo=docinfo)
441:
1.153 casties 442: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
443: """returns new option state"""
1.155 casties 444: if not self.REQUEST.SESSION.has_key(optionName):
1.153 casties 445: # not in session -- initial
446: opt = {'lastState': newState, 'state': initialState}
447: else:
1.155 casties 448: opt = self.REQUEST.SESSION.get(optionName)
1.153 casties 449: if opt['lastState'] != newState:
450: # state in session has changed -- toggle
451: opt['state'] = not opt['state']
452: opt['lastState'] = newState
453:
454: self.REQUEST.SESSION[optionName] = opt
455: return opt['state']
1.4 casties 456:
1.9 casties 457: def isAccessible(self, docinfo):
1.8 casties 458: """returns if access to the resource is granted"""
459: access = docinfo.get('accessType', None)
1.95 abukhman 460: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 461: if access is not None and access == 'free':
1.95 abukhman 462: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 463: return True
1.17 casties 464: elif access is None or access in self.authgroups:
1.9 casties 465: # only local access -- only logged in users
466: user = getSecurityManager().getUser()
1.95 abukhman 467: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 468: if user is not None:
469: #print "user: ", user
470: return (user.getUserName() != "Anonymous User")
471: else:
472: return False
1.8 casties 473:
1.95 abukhman 474: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 475: return False
1.9 casties 476:
1.8 casties 477:
1.35 dwinter 478: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 479: """gibt param von dlInfo aus"""
1.7 casties 480: if docinfo is None:
481: docinfo = {}
1.35 dwinter 482:
483: for x in range(cut):
1.38 dwinter 484:
1.35 dwinter 485: path=getParentDir(path)
1.38 dwinter 486:
1.13 casties 487: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 488:
1.95 abukhman 489: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 490:
1.70 casties 491: txt = getHttpData(infoUrl)
492: if txt is None:
1.13 casties 493: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 494:
495: dom = Parse(txt)
1.10 casties 496: sizes=dom.xpath("//dir/size")
1.95 abukhman 497: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 498:
1.10 casties 499: if sizes:
500: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 501: else:
502: docinfo['numPages'] = 0
1.43 casties 503:
504: # TODO: produce and keep list of image names and numbers
1.7 casties 505:
506: return docinfo
1.8 casties 507:
1.99 dwinter 508: def getIndexMetaPath(self,url):
509: """gib nur den Pfad zurueck"""
510: regexp = re.compile(r".*(experimental|permanent)/(.*)")
511: regpath = regexp.match(url)
512: if (regpath==None):
513: return ""
1.110 abukhman 514: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 515: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
516:
1.111 abukhman 517:
518:
1.99 dwinter 519: def getIndexMetaUrl(self,url):
520: """returns utr of index.meta document at url"""
521:
1.12 casties 522: metaUrl = None
1.9 casties 523: if url.startswith("http://"):
524: # real URL
1.12 casties 525: metaUrl = url
1.9 casties 526: else:
527: # online path
528: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 529: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 530: if not metaUrl.endswith("index.meta"):
531: metaUrl += "/index.meta"
1.99 dwinter 532:
533: return metaUrl
534:
535: def getDomFromIndexMeta(self, url):
536: """get dom from index meta"""
537: dom = None
538: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 539:
1.99 dwinter 540: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 541: txt=getHttpData(metaUrl)
542: if txt is None:
1.12 casties 543: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 544:
545: dom = Parse(txt)
1.9 casties 546: return dom
1.20 dwinter 547:
548: def getPresentationInfoXML(self, url):
549: """returns dom of info.xml document at url"""
550: dom = None
551: metaUrl = None
552: if url.startswith("http://"):
553: # real URL
554: metaUrl = url
555: else:
556: # online path
557: server=self.digilibBaseUrl+"/servlet/Texter?fn="
558: metaUrl=server+url.replace("/mpiwg/online","")
559:
1.70 casties 560: txt=getHttpData(metaUrl)
561: if txt is None:
1.20 dwinter 562: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 563:
564: dom = Parse(txt)
1.20 dwinter 565: return dom
1.9 casties 566:
567:
1.33 dwinter 568: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 569: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 570: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 571:
572: access = None
573:
574: if docinfo is None:
575: docinfo = {}
576:
577: if dom is None:
1.38 dwinter 578: for x in range(cut):
1.33 dwinter 579: path=getParentDir(path)
1.99 dwinter 580: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 581:
1.8 casties 582: acctype = dom.xpath("//access-conditions/access/@type")
583: if acctype and (len(acctype)>0):
584: access=acctype[0].value
1.9 casties 585: if access in ['group', 'institution']:
1.8 casties 586: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
587:
588: docinfo['accessType'] = access
589: return docinfo
1.6 casties 590:
1.8 casties 591:
1.33 dwinter 592: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 593: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 594: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 595:
1.3 casties 596: if docinfo is None:
597: docinfo = {}
1.38 dwinter 598:
1.3 casties 599: if dom is None:
1.38 dwinter 600: for x in range(cut):
1.33 dwinter 601: path=getParentDir(path)
1.99 dwinter 602: dom = self.getDomFromIndexMeta(path)
603:
604: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 605:
1.95 abukhman 606: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 607: # put in all raw bib fields as dict "bib"
608: bib = dom.xpath("//bib/*")
609: if bib and len(bib)>0:
610: bibinfo = {}
611: for e in bib:
612: bibinfo[e.localName] = getTextFromNode(e)
613: docinfo['bib'] = bibinfo
614:
615: # extract some fields (author, title, year) according to their mapping
1.4 casties 616: metaData=self.metadata.main.meta.bib
617: bibtype=dom.xpath("//bib/@type")
618: if bibtype and (len(bibtype)>0):
619: bibtype=bibtype[0].value
1.2 dwinter 620: else:
1.4 casties 621: bibtype="generic"
1.27 casties 622:
1.4 casties 623: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 624: docinfo['bib_type'] = bibtype
1.4 casties 625: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 626: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
627: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 628: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 629: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 630: try:
631: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
632: except: pass
633: try:
634: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
635: except: pass
636: try:
637: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
638: except: pass
1.95 abukhman 639: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 640: try:
641: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
642: except:
643: docinfo['lang']=''
1.167 ! abukhman 644: try:
! 645: docinfo['city']=getTextFromNode(dom.xpath("//bib/city")[0])
! 646: except:
! 647: docinfo['city']=''
! 648: try:
! 649: docinfo['number_of_pages']=getTextFromNode(dom.xpath("//bib/number_of_pages")[0])
! 650: except:
! 651: docinfo['number_of_pages']=''
! 652: try:
! 653: docinfo['series_volume']=getTextFromNode(dom.xpath("//bib/series_volume")[0])
! 654: except:
! 655: docinfo['series_volume']=''
! 656: try:
! 657: docinfo['number_of_volumes']=getTextFromNode(dom.xpath("//bib/number_of_volumes")[0])
! 658: except:
! 659: docinfo['number_of_volumes']=''
! 660: try:
! 661: docinfo['translator']=getTextFromNode(dom.xpath("//bib/translator")[0])
! 662: except:
! 663: docinfo['translator']=''
! 664: try:
! 665: docinfo['edition']=getTextFromNode(dom.xpath("//bib/edition")[0])
! 666: except:
! 667: docinfo['edition']=''
! 668: try:
! 669: docinfo['series_author']=getTextFromNode(dom.xpath("//bib/series_author")[0])
! 670: except:
! 671: docinfo['series_author']=''
! 672: try:
! 673: docinfo['publisher']=getTextFromNode(dom.xpath("//bib/publisher")[0])
! 674: except:
! 675: docinfo['publisher']=''
! 676: try:
! 677: docinfo['series_title']=getTextFromNode(dom.xpath("//bib/series_title")[0])
! 678: except:
! 679: docinfo['series_title']=''
! 680: try:
! 681: docinfo['isbn_issn']=getTextFromNode(dom.xpath("//bib/isbn_issn")[0])
! 682: except:
! 683: docinfo['isbn_issn']=''
1.3 casties 684: return docinfo
1.42 abukhman 685:
1.104 abukhman 686:
687: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
688: """gets name info from the index.meta file at path or given by dom"""
689: if docinfo is None:
690: docinfo = {}
691:
692: if dom is None:
693: for x in range(cut):
694: path=getParentDir(path)
695: dom = self.getDomFromIndexMeta(path)
1.125 abukhman 696:
1.115 abukhman 697: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
1.116 abukhman 698: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104 abukhman 699: return docinfo
1.42 abukhman 700:
1.43 casties 701: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
702: """parse texttool tag in index meta"""
1.95 abukhman 703: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 704: if docinfo is None:
705: docinfo = {}
706: if docinfo.get('lang', None) is None:
707: docinfo['lang'] = '' # default keine Sprache gesetzt
708: if dom is None:
1.99 dwinter 709: dom = self.getDomFromIndexMeta(url)
1.43 casties 710:
711: archivePath = None
712: archiveName = None
713:
714: archiveNames = dom.xpath("//resource/name")
715: if archiveNames and (len(archiveNames) > 0):
716: archiveName = getTextFromNode(archiveNames[0])
717: else:
1.70 casties 718: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 719:
720: archivePaths = dom.xpath("//resource/archive-path")
721: if archivePaths and (len(archivePaths) > 0):
722: archivePath = getTextFromNode(archivePaths[0])
723: # clean up archive path
724: if archivePath[0] != '/':
725: archivePath = '/' + archivePath
726: if archiveName and (not archivePath.endswith(archiveName)):
727: archivePath += "/" + archiveName
728: else:
729: # try to get archive-path from url
1.95 abukhman 730: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 731: if (not url.startswith('http')):
732: archivePath = url.replace('index.meta', '')
733:
734: if archivePath is None:
735: # we balk without archive-path
736: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
737:
738: imageDirs = dom.xpath("//texttool/image")
739: if imageDirs and (len(imageDirs) > 0):
740: imageDir = getTextFromNode(imageDirs[0])
741:
742: else:
743: # we balk with no image tag / not necessary anymore because textmode is now standard
744: #raise IOError("No text-tool info in %s"%(url))
745: imageDir = ""
746: #xquery="//pb"
747: docinfo['imagePath'] = "" # keine Bilder
748: docinfo['imageURL'] = ""
749:
750: if imageDir and archivePath:
751: #print "image: ", imageDir, " archivepath: ", archivePath
752: imageDir = os.path.join(archivePath, imageDir)
753: imageDir = imageDir.replace("/mpiwg/online", '')
754: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
755: docinfo['imagePath'] = imageDir
756:
757: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
758:
759: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
760: if viewerUrls and (len(viewerUrls) > 0):
761: viewerUrl = getTextFromNode(viewerUrls[0])
762: docinfo['viewerURL'] = viewerUrl
1.70 casties 763:
764: # old style text URL
1.43 casties 765: textUrls = dom.xpath("//texttool/text")
766: if textUrls and (len(textUrls) > 0):
767: textUrl = getTextFromNode(textUrls[0])
768: if urlparse.urlparse(textUrl)[0] == "": #keine url
769: textUrl = os.path.join(archivePath, textUrl)
770: # fix URLs starting with /mpiwg/online
771: if textUrl.startswith("/mpiwg/online"):
772: textUrl = textUrl.replace("/mpiwg/online", '', 1)
773:
774: docinfo['textURL'] = textUrl
775:
1.70 casties 776: # new style text-url-path
1.43 casties 777: textUrls = dom.xpath("//texttool/text-url-path")
778: if textUrls and (len(textUrls) > 0):
779: textUrl = getTextFromNode(textUrls[0])
1.51 casties 780: docinfo['textURLPath'] = textUrl
1.163 abukhman 781: #if not docinfo['imagePath']:
1.51 casties 782: # text-only, no page images
1.163 abukhman 783: #docinfo = self.getNumTextPages(docinfo)
784:
1.43 casties 785:
786: presentationUrls = dom.xpath("//texttool/presentation")
787: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 788: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.147 abukhman 789:
1.43 casties 790:
791: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
792: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
793: # durch den relativen Pfad auf die presentation infos
794: presentationPath = getTextFromNode(presentationUrls[0])
795: if url.endswith("index.meta"):
796: presentationUrl = url.replace('index.meta', presentationPath)
797: else:
798: presentationUrl = url + "/" + presentationPath
1.51 casties 799:
1.43 casties 800: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
801:
802: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 803:
1.43 casties 804: return docinfo
1.3 casties 805:
1.20 dwinter 806:
807: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
808: """gets the bibliographical information from the preseantion entry in texttools
809: """
810: dom=self.getPresentationInfoXML(url)
1.29 casties 811: try:
812: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
813: except:
814: pass
815: try:
816: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
817: except:
818: pass
819: try:
820: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
821: except:
822: pass
1.20 dwinter 823: return docinfo
824:
1.33 dwinter 825: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 826: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 827: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 828: if docinfo is None:
829: docinfo = {}
1.6 casties 830: path=path.replace("/mpiwg/online","")
1.3 casties 831: docinfo['imagePath'] = path
1.35 dwinter 832: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 833:
1.39 dwinter 834: pathorig=path
1.38 dwinter 835: for x in range(cut):
836: path=getParentDir(path)
1.95 abukhman 837: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 838: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 839: docinfo['imageURL'] = imageUrl
840:
1.39 dwinter 841: #path ist the path to the images it assumes that the index.meta file is one level higher.
842: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
843: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 844: return docinfo
845:
1.2 dwinter 846:
1.3 casties 847: def getDocinfo(self, mode, url):
848: """returns docinfo depending on mode"""
1.95 abukhman 849: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 850: # look for cached docinfo in session
1.21 dwinter 851: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 852: docinfo = self.REQUEST.SESSION['docinfo']
853: # check if its still current
854: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 855: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 856: return docinfo
857: # new docinfo
858: docinfo = {'mode': mode, 'url': url}
859: if mode=="texttool": #index.meta with texttool information
860: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
861: elif mode=="imagepath":
862: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 863: elif mode=="filepath":
1.37 dwinter 864: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 865: else:
1.95 abukhman 866: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 867: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.159 casties 868:
869: # FIXME: fake texturlpath
870: if not docinfo.has_key('textURLPath'):
871: docinfo['textURLPath'] = None
872:
1.95 abukhman 873: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.142 abukhman 874: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
1.3 casties 875: self.REQUEST.SESSION['docinfo'] = docinfo
876: return docinfo
1.69 abukhman 877:
1.158 casties 878: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 879: """returns pageinfo with the given parameters"""
880: pageinfo = {}
1.4 casties 881: current = getInt(current)
1.132 abukhman 882:
1.4 casties 883: pageinfo['current'] = current
884: rows = int(rows or self.thumbrows)
885: pageinfo['rows'] = rows
886: cols = int(cols or self.thumbcols)
887: pageinfo['cols'] = cols
888: grpsize = cols * rows
889: pageinfo['groupsize'] = grpsize
1.28 casties 890: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
891: # int(current / grpsize) * grpsize +1))
1.3 casties 892: pageinfo['start'] = start
1.4 casties 893: pageinfo['end'] = start + grpsize
1.44 casties 894: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 895: np = int(docinfo['numPages'])
896: pageinfo['end'] = min(pageinfo['end'], np)
897: pageinfo['numgroups'] = int(np / grpsize)
898: if np % grpsize > 0:
1.69 abukhman 899: pageinfo['numgroups'] += 1
1.44 casties 900: pageinfo['viewMode'] = viewMode
901: pageinfo['tocMode'] = tocMode
1.161 abukhman 902: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
1.156 abukhman 903: pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','')
904: pageinfo['query'] = self.REQUEST.get('query','')
1.146 abukhman 905: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 906: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 907: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.146 abukhman 908: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 909: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 910: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 911: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.163 abukhman 912:
1.48 abukhman 913: toc = int (pageinfo['tocPN'])
914: pageinfo['textPages'] =int (toc)
1.90 abukhman 915:
1.142 abukhman 916:
1.123 abukhman 917:
1.48 abukhman 918: if 'tocSize_%s'%tocMode in docinfo:
919: tocSize = int(docinfo['tocSize_%s'%tocMode])
920: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 921: # cached toc
1.48 abukhman 922: if tocSize%tocPageSize>0:
923: tocPages=tocSize/tocPageSize+1
924: else:
925: tocPages=tocSize/tocPageSize
1.69 abukhman 926: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 927: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 928: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 929: return pageinfo
930:
1.69 abukhman 931: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 932: """init document viewer"""
933: self.title=title
934: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 935: self.thumbrows = thumbrows
936: self.thumbcols = thumbcols
1.8 casties 937: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 938: if RESPONSE is not None:
939: RESPONSE.redirect('manage_main')
1.1 dwinter 940:
941: def manage_AddDocumentViewerForm(self):
942: """add the viewer form"""
1.3 casties 943: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 944: return pt()
945:
1.43 casties 946: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 947: """add the viewer"""
1.43 casties 948: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 949: self._setObject(id,newObj)
950:
951: if RESPONSE is not None:
952: RESPONSE.redirect('manage_main')
1.3 casties 953:
954: ## DocumentViewerTemplate class
955: class DocumentViewerTemplate(ZopePageTemplate):
956: """Template for document viewer"""
957: meta_type="DocumentViewer Template"
958:
959:
960: def manage_addDocumentViewerTemplateForm(self):
961: """Form for adding"""
962: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
963: return pt()
964:
965: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
966: REQUEST=None, submit=None):
967: "Add a Page Template with optional file content."
968:
969: self._setObject(id, DocumentViewerTemplate(id))
970: ob = getattr(self, id)
1.23 dwinter 971: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 972: logging.info("txt %s:"%txt)
1.23 dwinter 973: ob.pt_edit(txt,"text/html")
1.3 casties 974: if title:
975: ob.pt_setTitle(title)
976: try:
977: u = self.DestinationURL()
978: except AttributeError:
979: u = REQUEST['URL1']
980:
981: u = "%s/%s" % (u, urllib.quote(id))
982: REQUEST.RESPONSE.redirect(u+'/manage_main')
983: return ''
984:
985:
1.14 casties 986:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>