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