Annotation of documentViewer/documentViewer.py, revision 1.172
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:
1.170 abukhman 46: def serializeNode(node, encoding="utf-8"):
1.43 casties 47: """returns a string containing node as XML"""
1.170 abukhman 48: stream = cStringIO.StringIO()
1.171 abukhman 49: #logging.debug("BUF: %s"%(stream))
1.172 ! abukhman 50: Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
1.170 abukhman 51: s = stream.getvalue()
1.171 abukhman 52: #logging.debug("BUF: %s"%(s))
1.170 abukhman 53: stream.close()
1.43 casties 54: return s
55:
1.148 abukhman 56: def browserCheck(self):
57: """check the browsers request to find out the browser type"""
58: bt = {}
59: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
60: bt['ua'] = ua
61: bt['isIE'] = False
62: bt['isN4'] = False
1.165 abukhman 63: bt['versFirefox']=""
64: bt['versIE']=""
65: bt['versSafariChrome']=""
66: bt['versOpera']=""
67:
1.148 abukhman 68: if string.find(ua, 'MSIE') > -1:
69: bt['isIE'] = True
70: else:
71: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
1.165 abukhman 72: # Safari oder Chrome identification
73: try:
74: nav = ua[string.find(ua, '('):]
75: nav1=ua[string.find(ua,')'):]
76: nav2=nav1[string.find(nav1,'('):]
77: nav3=nav2[string.find(nav2,')'):]
78: ie = string.split(nav, "; ")[1]
79: ie1 =string.split(nav1, " ")[2]
80: ie2 =string.split(nav3, " ")[1]
81: ie3 =string.split(nav3, " ")[2]
82: if string.find(ie3, "Safari") >-1:
83: bt['versSafariChrome']=string.split(ie2, "/")[1]
84: except: pass
85: # IE identification
1.148 abukhman 86: try:
87: nav = ua[string.find(ua, '('):]
88: ie = string.split(nav, "; ")[1]
89: if string.find(ie, "MSIE") > -1:
90: bt['versIE'] = string.split(ie, " ")[1]
1.165 abukhman 91: except:pass
92: # Firefox identification
93: try:
94: nav = ua[string.find(ua, '('):]
95: nav1=ua[string.find(ua,')'):]
96: if string.find(ie1, "Firefox") >-1:
97: nav5= string.split(ie1, "/")[1]
98: logging.debug("FIREFOX: %s"%(nav5))
1.166 abukhman 99: bt['versFirefox']=nav5[0:3]
1.165 abukhman 100: except:pass
101: #Opera identification
102: try:
103: if string.find(ua,"Opera") >-1:
104: nav = ua[string.find(ua, '('):]
105: nav1=nav[string.find(nav,')'):]
106: bt['versOpera']=string.split(nav1,"/")[2]
107: except:pass
1.148 abukhman 108:
109: bt['isMac'] = string.find(ua, 'Macintosh') > -1
110: bt['isWin'] = string.find(ua, 'Windows') > -1
111: bt['isIEWin'] = bt['isIE'] and bt['isWin']
112: bt['isIEMac'] = bt['isIE'] and bt['isMac']
113: bt['staticHTML'] = False
114:
115: return bt
1.118 abukhman 116:
117:
1.9 casties 118: def getParentDir(path):
119: """returns pathname shortened by one"""
120: return '/'.join(path.split('/')[0:-1])
121:
122:
1.70 casties 123: def getHttpData(url, data=None, num_tries=3, timeout=10):
124: """returns result from url+data HTTP request"""
125: # we do GET (by appending data to url)
126: if isinstance(data, str) or isinstance(data, unicode):
127: # if data is string then append
128: url = "%s?%s"%(url,data)
129: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
130: # urlencode
131: url = "%s?%s"%(url,urllib.urlencode(data))
132:
133: response = None
134: errmsg = None
135: for cnt in range(num_tries):
136: try:
1.95 abukhman 137: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
1.70 casties 138: if sys.version_info < (2, 6):
139: # set timeout on socket -- ugly :-(
140: import socket
141: socket.setdefaulttimeout(float(timeout))
142: response = urllib2.urlopen(url)
143: else:
144: response = urllib2.urlopen(url,timeout=float(timeout))
145: # check result?
146: break
147: except urllib2.HTTPError, e:
1.95 abukhman 148: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
1.70 casties 149: errmsg = str(e)
150: # stop trying
151: break
152: except urllib2.URLError, e:
1.95 abukhman 153: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
1.70 casties 154: errmsg = str(e)
155: # stop trying
156: #break
157:
158: if response is not None:
159: data = response.read()
160: response.close()
161: return data
162:
163: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
164: #return None
1.1 dwinter 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)
1.171 abukhman 233:
234: def getOrigPages(self, **args):
235: """get page"""
236: return self.template.fulltextclient.getOrigPages(**args)
1.167 abukhman 237:
1.171 abukhman 238: def getOrigPagesNorm(self, **args):
239: """get page"""
240: return self.template.fulltextclient.getOrigPagesNorm(**args)
241:
1.70 casties 242: def getQuery(self, **args):
1.163 abukhman 243: """get query in search"""
1.70 casties 244: return self.template.fulltextclient.getQuery(**args)
1.163 abukhman 245:
1.70 casties 246: def getSearch(self, **args):
247: """get search"""
248: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 249:
250: def getGisPlaces(self, **args):
1.121 abukhman 251: """get gis places"""
1.120 abukhman 252: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 253:
254: def getAllGisPlaces(self, **args):
1.122 abukhman 255: """get all gis places """
256: return self.template.fulltextclient.getAllGisPlaces(**args)
1.163 abukhman 257:
1.70 casties 258: def getTranslate(self, **args):
259: """get translate"""
260: return self.template.fulltextclient.getTranslate(**args)
261:
262: def getLemma(self, **args):
263: """get lemma"""
264: return self.template.fulltextclient.getLemma(**args)
265:
266: def getToc(self, **args):
267: """get toc"""
268: return self.template.fulltextclient.getToc(**args)
269:
270: def getTocPage(self, **args):
271: """get tocpage"""
272: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 273:
1.70 casties 274:
1.32 dwinter 275: security.declareProtected('View','thumbs_rss')
276: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
277: '''
278: view it
279: @param mode: defines how to access the document behind url
280: @param url: url which contains display information
281: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
282:
283: '''
1.95 abukhman 284: logging.debug("HHHHHHHHHHHHHH:load the rss")
285: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 286:
287: if not hasattr(self, 'template'):
288: # create template folder if it doesn't exist
289: self.manage_addFolder('template')
290:
291: if not self.digilibBaseUrl:
292: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
293:
294: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 295: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 abukhman 296: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 297: ''' ZDES '''
1.32 dwinter 298: pt = getattr(self.template, 'thumbs_main_rss')
299:
300: if viewMode=="auto": # automodus gewaehlt
1.159 casties 301: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 302: viewMode="text"
303: else:
304: viewMode="images"
305:
306: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
307:
1.3 casties 308: security.declareProtected('View','index_html')
1.158 casties 309: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
1.3 casties 310: '''
311: view it
1.26 casties 312: @param mode: defines how to access the document behind url
1.3 casties 313: @param url: url which contains display information
1.44 casties 314: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 315: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 316: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 317: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 318: '''
319:
1.138 abukhman 320: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 321:
1.3 casties 322: if not hasattr(self, 'template'):
1.43 casties 323: # this won't work
324: logging.error("template folder missing!")
325: return "ERROR: template folder missing!"
1.3 casties 326:
1.43 casties 327: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 328: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 329:
1.4 casties 330: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 331:
1.44 casties 332: if tocMode != "thumbs":
333: # get table of contents
334: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 335:
1.21 dwinter 336: if viewMode=="auto": # automodus gewaehlt
1.159 casties 337: if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.68 casties 338: viewMode="text_dict"
1.21 dwinter 339: else:
340: viewMode="images"
1.44 casties 341:
1.138 abukhman 342: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 343:
1.163 abukhman 344: if (docinfo.get('textURLPath',None)):
345: page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo)
346: pageinfo['textPage'] = page
1.167 abukhman 347: tt = getattr(self, 'template')
348: pt = getattr(tt, 'viewer_main')
1.37 dwinter 349: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 350:
1.36 dwinter 351: def generateMarks(self,mk):
352: ret=""
1.44 casties 353: if mk is None:
354: return ""
1.73 casties 355: if not isinstance(mk, list):
1.71 casties 356: mk=[mk]
1.36 dwinter 357: for m in mk:
1.37 dwinter 358: ret+="mk=%s"%m
1.36 dwinter 359: return ret
1.149 abukhman 360:
361:
1.148 abukhman 362: def getBrowser(self):
363: """getBrowser the version of browser """
1.162 casties 364: bt = browserCheck(self)
1.164 abukhman 365: logging.debug("BROWSER VERSION: %s"%(bt))
1.162 casties 366: return bt
1.148 abukhman 367:
1.43 casties 368: def findDigilibUrl(self):
369: """try to get the digilib URL from zogilib"""
370: url = self.template.zogilib.getDLBaseUrl()
371: return url
1.67 casties 372:
373: def getDocumentViewerURL(self):
374: """returns the URL of this instance"""
375: return self.absolute_url()
1.43 casties 376:
377: def getStyle(self, idx, selected, style=""):
378: """returns a string with the given style and append 'sel' if path == selected."""
379: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
380: if idx == selected:
381: return style + 'sel'
382: else:
383: return style
1.36 dwinter 384:
1.162 casties 385: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
386: """returns URL to documentviewer with parameter param set to val or from dict params"""
387: # copy existing request params
388: urlParams=self.REQUEST.form.copy()
389: # change single param
1.4 casties 390: if param is not None:
1.7 casties 391: if val is None:
1.162 casties 392: if urlParams.has_key(param):
393: del urlParams[param]
1.4 casties 394: else:
1.162 casties 395: urlParams[param] = str(val)
1.43 casties 396:
1.162 casties 397: # change more params
398: if params is not None:
399: for k in params.keys():
400: v = params[k]
401: if v is None:
402: # val=None removes param
403: if urlParams.has_key(k):
404: del urlParams[k]
405:
406: else:
407: urlParams[k] = v
408:
409: # FIXME: does this belong here?
410: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
411: urlParams["mode"] = "imagepath"
412: urlParams["url"] = getParentDir(urlParams["url"])
1.7 casties 413:
1.162 casties 414: # quote values and assemble into query string (not escaping '/')
415: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
416: #ps = urllib.urlencode(urlParams)
417: if baseUrl is None:
418: baseUrl = self.REQUEST['URL1']
419:
420: url = "%s?%s"%(baseUrl, ps)
1.4 casties 421: return url
422:
1.162 casties 423:
424: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
1.32 dwinter 425: """link to documentviewer with parameter param set to val"""
1.162 casties 426: return self.getLink(param, val, params, baseUrl, '&')
1.40 casties 427:
1.26 casties 428: def getInfo_xml(self,url,mode):
429: """returns info about the document as XML"""
430:
431: if not self.digilibBaseUrl:
432: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
433:
434: docinfo = self.getDocinfo(mode=mode,url=url)
435: pt = getattr(self.template, 'info_xml')
436: return pt(docinfo=docinfo)
437:
1.153 casties 438: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
439: """returns new option state"""
1.155 casties 440: if not self.REQUEST.SESSION.has_key(optionName):
1.153 casties 441: # not in session -- initial
442: opt = {'lastState': newState, 'state': initialState}
443: else:
1.155 casties 444: opt = self.REQUEST.SESSION.get(optionName)
1.153 casties 445: if opt['lastState'] != newState:
446: # state in session has changed -- toggle
447: opt['state'] = not opt['state']
448: opt['lastState'] = newState
449:
450: self.REQUEST.SESSION[optionName] = opt
451: return opt['state']
1.4 casties 452:
1.9 casties 453: def isAccessible(self, docinfo):
1.8 casties 454: """returns if access to the resource is granted"""
455: access = docinfo.get('accessType', None)
1.95 abukhman 456: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 457: if access is not None and access == 'free':
1.95 abukhman 458: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 459: return True
1.17 casties 460: elif access is None or access in self.authgroups:
1.9 casties 461: # only local access -- only logged in users
462: user = getSecurityManager().getUser()
1.95 abukhman 463: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 464: if user is not None:
465: #print "user: ", user
466: return (user.getUserName() != "Anonymous User")
467: else:
468: return False
1.8 casties 469:
1.95 abukhman 470: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 471: return False
1.9 casties 472:
1.8 casties 473:
1.35 dwinter 474: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 475: """gibt param von dlInfo aus"""
1.7 casties 476: if docinfo is None:
477: docinfo = {}
1.35 dwinter 478:
479: for x in range(cut):
1.38 dwinter 480:
1.35 dwinter 481: path=getParentDir(path)
1.38 dwinter 482:
1.13 casties 483: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 484:
1.95 abukhman 485: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 486:
1.70 casties 487: txt = getHttpData(infoUrl)
488: if txt is None:
1.13 casties 489: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 490:
491: dom = Parse(txt)
1.10 casties 492: sizes=dom.xpath("//dir/size")
1.95 abukhman 493: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 494:
1.10 casties 495: if sizes:
496: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 497: else:
498: docinfo['numPages'] = 0
1.43 casties 499:
500: # TODO: produce and keep list of image names and numbers
1.7 casties 501:
502: return docinfo
1.8 casties 503:
1.99 dwinter 504: def getIndexMetaPath(self,url):
505: """gib nur den Pfad zurueck"""
506: regexp = re.compile(r".*(experimental|permanent)/(.*)")
507: regpath = regexp.match(url)
508: if (regpath==None):
509: return ""
1.110 abukhman 510: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 511: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
512:
1.111 abukhman 513:
514:
1.99 dwinter 515: def getIndexMetaUrl(self,url):
516: """returns utr of index.meta document at url"""
517:
1.12 casties 518: metaUrl = None
1.9 casties 519: if url.startswith("http://"):
520: # real URL
1.12 casties 521: metaUrl = url
1.9 casties 522: else:
523: # online path
524: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 525: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 526: if not metaUrl.endswith("index.meta"):
527: metaUrl += "/index.meta"
1.99 dwinter 528:
529: return metaUrl
530:
531: def getDomFromIndexMeta(self, url):
532: """get dom from index meta"""
533: dom = None
534: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 535:
1.99 dwinter 536: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 537: txt=getHttpData(metaUrl)
538: if txt is None:
1.12 casties 539: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 540:
541: dom = Parse(txt)
1.9 casties 542: return dom
1.20 dwinter 543:
544: def getPresentationInfoXML(self, url):
545: """returns dom of info.xml document at url"""
546: dom = None
547: metaUrl = None
548: if url.startswith("http://"):
549: # real URL
550: metaUrl = url
551: else:
552: # online path
553: server=self.digilibBaseUrl+"/servlet/Texter?fn="
554: metaUrl=server+url.replace("/mpiwg/online","")
555:
1.70 casties 556: txt=getHttpData(metaUrl)
557: if txt is None:
1.20 dwinter 558: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 559:
560: dom = Parse(txt)
1.20 dwinter 561: return dom
1.9 casties 562:
563:
1.33 dwinter 564: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 565: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 566: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 567:
568: access = None
569:
570: if docinfo is None:
571: docinfo = {}
572:
573: if dom is None:
1.38 dwinter 574: for x in range(cut):
1.33 dwinter 575: path=getParentDir(path)
1.99 dwinter 576: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 577:
1.8 casties 578: acctype = dom.xpath("//access-conditions/access/@type")
579: if acctype and (len(acctype)>0):
580: access=acctype[0].value
1.9 casties 581: if access in ['group', 'institution']:
1.8 casties 582: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
583:
584: docinfo['accessType'] = access
585: return docinfo
1.6 casties 586:
1.8 casties 587:
1.33 dwinter 588: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 589: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 590: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 591:
1.3 casties 592: if docinfo is None:
593: docinfo = {}
1.38 dwinter 594:
1.3 casties 595: if dom is None:
1.38 dwinter 596: for x in range(cut):
1.33 dwinter 597: path=getParentDir(path)
1.99 dwinter 598: dom = self.getDomFromIndexMeta(path)
599:
600: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 601:
1.95 abukhman 602: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 603: # put in all raw bib fields as dict "bib"
604: bib = dom.xpath("//bib/*")
605: if bib and len(bib)>0:
606: bibinfo = {}
607: for e in bib:
608: bibinfo[e.localName] = getTextFromNode(e)
609: docinfo['bib'] = bibinfo
610:
611: # extract some fields (author, title, year) according to their mapping
1.4 casties 612: metaData=self.metadata.main.meta.bib
613: bibtype=dom.xpath("//bib/@type")
614: if bibtype and (len(bibtype)>0):
615: bibtype=bibtype[0].value
1.2 dwinter 616: else:
1.4 casties 617: bibtype="generic"
1.27 casties 618:
1.4 casties 619: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 620: docinfo['bib_type'] = bibtype
1.4 casties 621: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 622: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
623: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 624: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 625: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 626: try:
627: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
628: except: pass
629: try:
630: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
631: except: pass
632: try:
633: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
634: except: pass
1.95 abukhman 635: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 636: try:
637: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
638: except:
639: docinfo['lang']=''
1.167 abukhman 640: try:
641: docinfo['city']=getTextFromNode(dom.xpath("//bib/city")[0])
642: except:
643: docinfo['city']=''
644: try:
645: docinfo['number_of_pages']=getTextFromNode(dom.xpath("//bib/number_of_pages")[0])
646: except:
647: docinfo['number_of_pages']=''
648: try:
649: docinfo['series_volume']=getTextFromNode(dom.xpath("//bib/series_volume")[0])
650: except:
651: docinfo['series_volume']=''
652: try:
653: docinfo['number_of_volumes']=getTextFromNode(dom.xpath("//bib/number_of_volumes")[0])
654: except:
655: docinfo['number_of_volumes']=''
656: try:
657: docinfo['translator']=getTextFromNode(dom.xpath("//bib/translator")[0])
658: except:
659: docinfo['translator']=''
660: try:
661: docinfo['edition']=getTextFromNode(dom.xpath("//bib/edition")[0])
662: except:
663: docinfo['edition']=''
664: try:
665: docinfo['series_author']=getTextFromNode(dom.xpath("//bib/series_author")[0])
666: except:
667: docinfo['series_author']=''
668: try:
669: docinfo['publisher']=getTextFromNode(dom.xpath("//bib/publisher")[0])
670: except:
671: docinfo['publisher']=''
672: try:
673: docinfo['series_title']=getTextFromNode(dom.xpath("//bib/series_title")[0])
674: except:
675: docinfo['series_title']=''
676: try:
677: docinfo['isbn_issn']=getTextFromNode(dom.xpath("//bib/isbn_issn")[0])
678: except:
679: docinfo['isbn_issn']=''
1.3 casties 680: return docinfo
1.42 abukhman 681:
1.104 abukhman 682:
683: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
684: """gets name info from the index.meta file at path or given by dom"""
685: if docinfo is None:
686: docinfo = {}
687:
688: if dom is None:
689: for x in range(cut):
690: path=getParentDir(path)
691: dom = self.getDomFromIndexMeta(path)
1.125 abukhman 692:
1.115 abukhman 693: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
1.116 abukhman 694: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104 abukhman 695: return docinfo
1.42 abukhman 696:
1.43 casties 697: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
698: """parse texttool tag in index meta"""
1.95 abukhman 699: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 700: if docinfo is None:
701: docinfo = {}
702: if docinfo.get('lang', None) is None:
703: docinfo['lang'] = '' # default keine Sprache gesetzt
704: if dom is None:
1.99 dwinter 705: dom = self.getDomFromIndexMeta(url)
1.43 casties 706:
707: archivePath = None
708: archiveName = None
709:
710: archiveNames = dom.xpath("//resource/name")
711: if archiveNames and (len(archiveNames) > 0):
712: archiveName = getTextFromNode(archiveNames[0])
713: else:
1.70 casties 714: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 715:
716: archivePaths = dom.xpath("//resource/archive-path")
717: if archivePaths and (len(archivePaths) > 0):
718: archivePath = getTextFromNode(archivePaths[0])
719: # clean up archive path
720: if archivePath[0] != '/':
721: archivePath = '/' + archivePath
722: if archiveName and (not archivePath.endswith(archiveName)):
723: archivePath += "/" + archiveName
724: else:
725: # try to get archive-path from url
1.95 abukhman 726: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 727: if (not url.startswith('http')):
728: archivePath = url.replace('index.meta', '')
729:
730: if archivePath is None:
731: # we balk without archive-path
732: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
733:
734: imageDirs = dom.xpath("//texttool/image")
735: if imageDirs and (len(imageDirs) > 0):
736: imageDir = getTextFromNode(imageDirs[0])
737:
738: else:
739: # we balk with no image tag / not necessary anymore because textmode is now standard
740: #raise IOError("No text-tool info in %s"%(url))
741: imageDir = ""
742: #xquery="//pb"
743: docinfo['imagePath'] = "" # keine Bilder
744: docinfo['imageURL'] = ""
745:
746: if imageDir and archivePath:
747: #print "image: ", imageDir, " archivepath: ", archivePath
748: imageDir = os.path.join(archivePath, imageDir)
749: imageDir = imageDir.replace("/mpiwg/online", '')
750: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
751: docinfo['imagePath'] = imageDir
752:
753: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
754:
755: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
756: if viewerUrls and (len(viewerUrls) > 0):
757: viewerUrl = getTextFromNode(viewerUrls[0])
758: docinfo['viewerURL'] = viewerUrl
1.70 casties 759:
760: # old style text URL
1.43 casties 761: textUrls = dom.xpath("//texttool/text")
762: if textUrls and (len(textUrls) > 0):
763: textUrl = getTextFromNode(textUrls[0])
764: if urlparse.urlparse(textUrl)[0] == "": #keine url
765: textUrl = os.path.join(archivePath, textUrl)
766: # fix URLs starting with /mpiwg/online
767: if textUrl.startswith("/mpiwg/online"):
768: textUrl = textUrl.replace("/mpiwg/online", '', 1)
769:
770: docinfo['textURL'] = textUrl
771:
1.70 casties 772: # new style text-url-path
1.43 casties 773: textUrls = dom.xpath("//texttool/text-url-path")
774: if textUrls and (len(textUrls) > 0):
775: textUrl = getTextFromNode(textUrls[0])
1.51 casties 776: docinfo['textURLPath'] = textUrl
1.169 abukhman 777: textUrlkurz = string.split(textUrl, ".")[0]
778: docinfo['textURLPathkurz'] = textUrlkurz
1.163 abukhman 779: #if not docinfo['imagePath']:
1.51 casties 780: # text-only, no page images
1.163 abukhman 781: #docinfo = self.getNumTextPages(docinfo)
782:
1.43 casties 783:
784: presentationUrls = dom.xpath("//texttool/presentation")
785: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 786: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.147 abukhman 787:
1.43 casties 788:
789: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
790: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
791: # durch den relativen Pfad auf die presentation infos
792: presentationPath = getTextFromNode(presentationUrls[0])
793: if url.endswith("index.meta"):
794: presentationUrl = url.replace('index.meta', presentationPath)
795: else:
796: presentationUrl = url + "/" + presentationPath
1.51 casties 797:
1.43 casties 798: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
799:
800: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 801:
1.43 casties 802: return docinfo
1.3 casties 803:
1.20 dwinter 804:
805: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
806: """gets the bibliographical information from the preseantion entry in texttools
807: """
808: dom=self.getPresentationInfoXML(url)
1.29 casties 809: try:
810: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
811: except:
812: pass
813: try:
814: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
815: except:
816: pass
817: try:
818: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
819: except:
820: pass
1.20 dwinter 821: return docinfo
822:
1.33 dwinter 823: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 824: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 825: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 826: if docinfo is None:
827: docinfo = {}
1.6 casties 828: path=path.replace("/mpiwg/online","")
1.3 casties 829: docinfo['imagePath'] = path
1.35 dwinter 830: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 831:
1.39 dwinter 832: pathorig=path
1.38 dwinter 833: for x in range(cut):
834: path=getParentDir(path)
1.95 abukhman 835: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 836: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 837: docinfo['imageURL'] = imageUrl
838:
1.39 dwinter 839: #path ist the path to the images it assumes that the index.meta file is one level higher.
840: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
841: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 842: return docinfo
843:
1.2 dwinter 844:
1.3 casties 845: def getDocinfo(self, mode, url):
846: """returns docinfo depending on mode"""
1.95 abukhman 847: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 848: # look for cached docinfo in session
1.21 dwinter 849: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 850: docinfo = self.REQUEST.SESSION['docinfo']
851: # check if its still current
852: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 853: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 854: return docinfo
855: # new docinfo
856: docinfo = {'mode': mode, 'url': url}
857: if mode=="texttool": #index.meta with texttool information
858: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
859: elif mode=="imagepath":
860: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 861: elif mode=="filepath":
1.37 dwinter 862: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 863: else:
1.95 abukhman 864: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 865: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.159 casties 866:
867: # FIXME: fake texturlpath
868: if not docinfo.has_key('textURLPath'):
869: docinfo['textURLPath'] = None
870:
1.95 abukhman 871: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.142 abukhman 872: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
1.3 casties 873: self.REQUEST.SESSION['docinfo'] = docinfo
874: return docinfo
1.69 abukhman 875:
1.158 casties 876: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 877: """returns pageinfo with the given parameters"""
878: pageinfo = {}
1.4 casties 879: current = getInt(current)
1.132 abukhman 880:
1.4 casties 881: pageinfo['current'] = current
882: rows = int(rows or self.thumbrows)
883: pageinfo['rows'] = rows
884: cols = int(cols or self.thumbcols)
885: pageinfo['cols'] = cols
886: grpsize = cols * rows
887: pageinfo['groupsize'] = grpsize
1.28 casties 888: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
889: # int(current / grpsize) * grpsize +1))
1.3 casties 890: pageinfo['start'] = start
1.4 casties 891: pageinfo['end'] = start + grpsize
1.44 casties 892: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 893: np = int(docinfo['numPages'])
894: pageinfo['end'] = min(pageinfo['end'], np)
895: pageinfo['numgroups'] = int(np / grpsize)
896: if np % grpsize > 0:
1.69 abukhman 897: pageinfo['numgroups'] += 1
1.44 casties 898: pageinfo['viewMode'] = viewMode
899: pageinfo['tocMode'] = tocMode
1.161 abukhman 900: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
1.172 ! abukhman 901: pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
1.156 abukhman 902: pageinfo['query'] = self.REQUEST.get('query','')
1.146 abukhman 903: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 904: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 905: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.146 abukhman 906: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 907: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 908: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.170 abukhman 909: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 910: toc = int (pageinfo['tocPN'])
911: pageinfo['textPages'] =int (toc)
1.90 abukhman 912:
1.48 abukhman 913: if 'tocSize_%s'%tocMode in docinfo:
914: tocSize = int(docinfo['tocSize_%s'%tocMode])
915: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 916: # cached toc
1.48 abukhman 917: if tocSize%tocPageSize>0:
918: tocPages=tocSize/tocPageSize+1
919: else:
920: tocPages=tocSize/tocPageSize
1.69 abukhman 921: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 922: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 923: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 924: return pageinfo
925:
1.69 abukhman 926: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 927: """init document viewer"""
928: self.title=title
929: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 930: self.thumbrows = thumbrows
931: self.thumbcols = thumbcols
1.8 casties 932: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 933: if RESPONSE is not None:
934: RESPONSE.redirect('manage_main')
1.1 dwinter 935:
936: def manage_AddDocumentViewerForm(self):
937: """add the viewer form"""
1.3 casties 938: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 939: return pt()
940:
1.43 casties 941: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 942: """add the viewer"""
1.43 casties 943: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 944: self._setObject(id,newObj)
945:
946: if RESPONSE is not None:
947: RESPONSE.redirect('manage_main')
1.3 casties 948:
949: ## DocumentViewerTemplate class
950: class DocumentViewerTemplate(ZopePageTemplate):
951: """Template for document viewer"""
952: meta_type="DocumentViewer Template"
953:
954:
955: def manage_addDocumentViewerTemplateForm(self):
956: """Form for adding"""
957: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
958: return pt()
959:
960: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
961: REQUEST=None, submit=None):
962: "Add a Page Template with optional file content."
963:
964: self._setObject(id, DocumentViewerTemplate(id))
965: ob = getattr(self, id)
1.23 dwinter 966: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 967: logging.info("txt %s:"%txt)
1.23 dwinter 968: ob.pt_edit(txt,"text/html")
1.3 casties 969: if title:
970: ob.pt_setTitle(title)
971: try:
972: u = self.DestinationURL()
973: except AttributeError:
974: u = REQUEST['URL1']
975:
976: u = "%s/%s" % (u, urllib.quote(id))
977: REQUEST.RESPONSE.redirect(u+'/manage_main')
978: return ''
979:
980:
1.14 casties 981:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>