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: stream = cStringIO.StringIO()
49: #logging.debug("BUF: %s"%(stream))
50: Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
51: s = stream.getvalue()
52: #logging.debug("BUF: %s"%(s))
53: stream.close()
54: return s
55:
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
63: bt['versFirefox']=""
64: bt['versIE']=""
65: bt['versSafariChrome']=""
66: bt['versOpera']=""
67:
68: if string.find(ua, 'MSIE') > -1:
69: bt['isIE'] = True
70: else:
71: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
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
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]
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))
99: bt['versFirefox']=nav5[0:3]
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
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
116:
117:
118: def getParentDir(path):
119: """returns pathname shortened by one"""
120: return '/'.join(path.split('/')[0:-1])
121:
122:
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:
137: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
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:
148: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
149: errmsg = str(e)
150: # stop trying
151: break
152: except urllib2.URLError, e:
153: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
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
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 getOrigPages(self, **args):
235: """get page"""
236: return self.template.fulltextclient.getOrigPages(**args)
237:
238: def getOrigPagesNorm(self, **args):
239: """get page"""
240: return self.template.fulltextclient.getOrigPagesNorm(**args)
241:
242: def getQuery(self, **args):
243: """get query in search"""
244: return self.template.fulltextclient.getQuery(**args)
245:
246: def getSearch(self, **args):
247: """get search"""
248: return self.template.fulltextclient.getSearch(**args)
249:
250: def getGisPlaces(self, **args):
251: """get gis places"""
252: return self.template.fulltextclient.getGisPlaces(**args)
253:
254: def getAllGisPlaces(self, **args):
255: """get all gis places """
256: return self.template.fulltextclient.getAllGisPlaces(**args)
257:
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 getLemmaQuery(self, **args):
267: """get query"""
268: return self.template.fulltextclient.getLemmaQuery(**args)
269:
270: def getLex(self, **args):
271: """get lex"""
272: return self.template.fulltextclient.getLex(**args)
273:
274: def getToc(self, **args):
275: """get toc"""
276: return self.template.fulltextclient.getToc(**args)
277:
278: def getTocPage(self, **args):
279: """get tocpage"""
280: return self.template.fulltextclient.getTocPage(**args)
281:
282:
283: security.declareProtected('View','thumbs_rss')
284: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
285: '''
286: view it
287: @param mode: defines how to access the document behind url
288: @param url: url which contains display information
289: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
290:
291: '''
292: logging.debug("HHHHHHHHHHHHHH:load the rss")
293: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
294:
295: if not hasattr(self, 'template'):
296: # create template folder if it doesn't exist
297: self.manage_addFolder('template')
298:
299: if not self.digilibBaseUrl:
300: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
301:
302: docinfo = self.getDocinfo(mode=mode,url=url)
303: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
304: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
305: ''' ZDES '''
306: pt = getattr(self.template, 'thumbs_main_rss')
307:
308: if viewMode=="auto": # automodus gewaehlt
309: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
310: viewMode="text"
311: else:
312: viewMode="images"
313:
314: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
315:
316: security.declareProtected('View','index_html')
317: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
318: '''
319: view it
320: @param mode: defines how to access the document behind url
321: @param url: url which contains display information
322: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
323: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
324: @param characterNormalization type of text display (reg, norm, none)
325: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
326: '''
327:
328: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
329:
330: if not hasattr(self, 'template'):
331: # this won't work
332: logging.error("template folder missing!")
333: return "ERROR: template folder missing!"
334:
335: if not getattr(self, 'digilibBaseUrl', None):
336: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
337:
338: docinfo = self.getDocinfo(mode=mode,url=url)
339:
340: if tocMode != "thumbs":
341: # get table of contents
342: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
343:
344: if viewMode=="auto": # automodus gewaehlt
345: if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
346: viewMode="text_dict"
347: else:
348: viewMode="images"
349:
350: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
351:
352: if (docinfo.get('textURLPath',None)):
353: page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo)
354: pageinfo['textPage'] = page
355: tt = getattr(self, 'template')
356: pt = getattr(tt, 'viewer_main')
357: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
358:
359: def generateMarks(self,mk):
360: ret=""
361: if mk is None:
362: return ""
363: if not isinstance(mk, list):
364: mk=[mk]
365: for m in mk:
366: ret+="mk=%s"%m
367: return ret
368:
369:
370: def getBrowser(self):
371: """getBrowser the version of browser """
372: bt = browserCheck(self)
373: logging.debug("BROWSER VERSION: %s"%(bt))
374: return bt
375:
376: def findDigilibUrl(self):
377: """try to get the digilib URL from zogilib"""
378: url = self.template.zogilib.getDLBaseUrl()
379: return url
380:
381: def getDocumentViewerURL(self):
382: """returns the URL of this instance"""
383: return self.absolute_url()
384:
385: def getStyle(self, idx, selected, style=""):
386: """returns a string with the given style and append 'sel' if path == selected."""
387: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
388: if idx == selected:
389: return style + 'sel'
390: else:
391: return style
392:
393: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
394: """returns URL to documentviewer with parameter param set to val or from dict params"""
395: # copy existing request params
396: urlParams=self.REQUEST.form.copy()
397: # change single param
398: if param is not None:
399: if val is None:
400: if urlParams.has_key(param):
401: del urlParams[param]
402: else:
403: urlParams[param] = str(val)
404:
405: # change more params
406: if params is not None:
407: for k in params.keys():
408: v = params[k]
409: if v is None:
410: # val=None removes param
411: if urlParams.has_key(k):
412: del urlParams[k]
413:
414: else:
415: urlParams[k] = v
416:
417: # FIXME: does this belong here?
418: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
419: urlParams["mode"] = "imagepath"
420: urlParams["url"] = getParentDir(urlParams["url"])
421:
422: # quote values and assemble into query string (not escaping '/')
423: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
424: #ps = urllib.urlencode(urlParams)
425: if baseUrl is None:
426: baseUrl = self.REQUEST['URL1']
427:
428: url = "%s?%s"%(baseUrl, ps)
429: return url
430:
431:
432: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
433: """link to documentviewer with parameter param set to val"""
434: return self.getLink(param, val, params, baseUrl, '&')
435:
436: def getInfo_xml(self,url,mode):
437: """returns info about the document as XML"""
438:
439: if not self.digilibBaseUrl:
440: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
441:
442: docinfo = self.getDocinfo(mode=mode,url=url)
443: pt = getattr(self.template, 'info_xml')
444: return pt(docinfo=docinfo)
445:
446: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
447: """returns new option state"""
448: if not self.REQUEST.SESSION.has_key(optionName):
449: # not in session -- initial
450: opt = {'lastState': newState, 'state': initialState}
451: else:
452: opt = self.REQUEST.SESSION.get(optionName)
453: if opt['lastState'] != newState:
454: # state in session has changed -- toggle
455: opt['state'] = not opt['state']
456: opt['lastState'] = newState
457:
458: self.REQUEST.SESSION[optionName] = opt
459: return opt['state']
460:
461: def isAccessible(self, docinfo):
462: """returns if access to the resource is granted"""
463: access = docinfo.get('accessType', None)
464: logging.debug("documentViewer (accessOK) access type %s"%access)
465: if access is not None and access == 'free':
466: logging.debug("documentViewer (accessOK) access is free")
467: return True
468: elif access is None or access in self.authgroups:
469: # only local access -- only logged in users
470: user = getSecurityManager().getUser()
471: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
472: if user is not None:
473: #print "user: ", user
474: return (user.getUserName() != "Anonymous User")
475: else:
476: return False
477:
478: logging.error("documentViewer (accessOK) unknown access type %s"%access)
479: return False
480:
481:
482: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
483: """gibt param von dlInfo aus"""
484: if docinfo is None:
485: docinfo = {}
486:
487: for x in range(cut):
488:
489: path=getParentDir(path)
490:
491: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
492:
493: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
494:
495: txt = getHttpData(infoUrl)
496: if txt is None:
497: raise IOError("Unable to get dir-info from %s"%(infoUrl))
498:
499: dom = Parse(txt)
500: sizes=dom.xpath("//dir/size")
501: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
502:
503: if sizes:
504: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
505: else:
506: docinfo['numPages'] = 0
507:
508: # TODO: produce and keep list of image names and numbers
509:
510: return docinfo
511:
512: def getIndexMetaPath(self,url):
513: """gib nur den Pfad zurueck"""
514: regexp = re.compile(r".*(experimental|permanent)/(.*)")
515: regpath = regexp.match(url)
516: if (regpath==None):
517: return ""
518: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
519: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
520:
521:
522:
523: def getIndexMetaUrl(self,url):
524: """returns utr of index.meta document at url"""
525:
526: metaUrl = None
527: if url.startswith("http://"):
528: # real URL
529: metaUrl = url
530: else:
531: # online path
532: server=self.digilibBaseUrl+"/servlet/Texter?fn="
533: metaUrl=server+url.replace("/mpiwg/online","")
534: if not metaUrl.endswith("index.meta"):
535: metaUrl += "/index.meta"
536:
537: return metaUrl
538:
539: def getDomFromIndexMeta(self, url):
540: """get dom from index meta"""
541: dom = None
542: metaUrl = self.getIndexMetaUrl(url)
543:
544: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
545: txt=getHttpData(metaUrl)
546: if txt is None:
547: raise IOError("Unable to read index meta from %s"%(url))
548:
549: dom = Parse(txt)
550: return dom
551:
552: def getPresentationInfoXML(self, url):
553: """returns dom of info.xml document at url"""
554: dom = None
555: metaUrl = None
556: if url.startswith("http://"):
557: # real URL
558: metaUrl = url
559: else:
560: # online path
561: server=self.digilibBaseUrl+"/servlet/Texter?fn="
562: metaUrl=server+url.replace("/mpiwg/online","")
563:
564: txt=getHttpData(metaUrl)
565: if txt is None:
566: raise IOError("Unable to read infoXMLfrom %s"%(url))
567:
568: dom = Parse(txt)
569: return dom
570:
571:
572: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
573: """gets authorization info from the index.meta file at path or given by dom"""
574: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
575:
576: access = None
577:
578: if docinfo is None:
579: docinfo = {}
580:
581: if dom is None:
582: for x in range(cut):
583: path=getParentDir(path)
584: dom = self.getDomFromIndexMeta(path)
585:
586: acctype = dom.xpath("//access-conditions/access/@type")
587: if acctype and (len(acctype)>0):
588: access=acctype[0].value
589: if access in ['group', 'institution']:
590: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
591:
592: docinfo['accessType'] = access
593: return docinfo
594:
595:
596: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
597: """gets bibliographical info from the index.meta file at path or given by dom"""
598: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
599:
600: if docinfo is None:
601: docinfo = {}
602:
603: if dom is None:
604: for x in range(cut):
605: path=getParentDir(path)
606: dom = self.getDomFromIndexMeta(path)
607:
608: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
609:
610: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
611: # put in all raw bib fields as dict "bib"
612: bib = dom.xpath("//bib/*")
613: if bib and len(bib)>0:
614: bibinfo = {}
615: for e in bib:
616: bibinfo[e.localName] = getTextFromNode(e)
617: docinfo['bib'] = bibinfo
618:
619: # extract some fields (author, title, year) according to their mapping
620: metaData=self.metadata.main.meta.bib
621: bibtype=dom.xpath("//bib/@type")
622: if bibtype and (len(bibtype)>0):
623: bibtype=bibtype[0].value
624: else:
625: bibtype="generic"
626:
627: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
628: docinfo['bib_type'] = bibtype
629: bibmap=metaData.generateMappingForType(bibtype)
630: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
631: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
632: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
633: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
634: try:
635: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
636: except: pass
637: try:
638: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
639: except: pass
640: try:
641: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
642: except: pass
643: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
644: try:
645: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
646: except:
647: docinfo['lang']=''
648: try:
649: docinfo['city']=getTextFromNode(dom.xpath("//bib/city")[0])
650: except:
651: docinfo['city']=''
652: try:
653: docinfo['number_of_pages']=getTextFromNode(dom.xpath("//bib/number_of_pages")[0])
654: except:
655: docinfo['number_of_pages']=''
656: try:
657: docinfo['series_volume']=getTextFromNode(dom.xpath("//bib/series_volume")[0])
658: except:
659: docinfo['series_volume']=''
660: try:
661: docinfo['number_of_volumes']=getTextFromNode(dom.xpath("//bib/number_of_volumes")[0])
662: except:
663: docinfo['number_of_volumes']=''
664: try:
665: docinfo['translator']=getTextFromNode(dom.xpath("//bib/translator")[0])
666: except:
667: docinfo['translator']=''
668: try:
669: docinfo['edition']=getTextFromNode(dom.xpath("//bib/edition")[0])
670: except:
671: docinfo['edition']=''
672: try:
673: docinfo['series_author']=getTextFromNode(dom.xpath("//bib/series_author")[0])
674: except:
675: docinfo['series_author']=''
676: try:
677: docinfo['publisher']=getTextFromNode(dom.xpath("//bib/publisher")[0])
678: except:
679: docinfo['publisher']=''
680: try:
681: docinfo['series_title']=getTextFromNode(dom.xpath("//bib/series_title")[0])
682: except:
683: docinfo['series_title']=''
684: try:
685: docinfo['isbn_issn']=getTextFromNode(dom.xpath("//bib/isbn_issn")[0])
686: except:
687: docinfo['isbn_issn']=''
688: return docinfo
689:
690:
691: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
692: """gets name info from the index.meta file at path or given by dom"""
693: if docinfo is None:
694: docinfo = {}
695:
696: if dom is None:
697: for x in range(cut):
698: path=getParentDir(path)
699: dom = self.getDomFromIndexMeta(path)
700:
701: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
702: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
703: return docinfo
704:
705: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
706: """parse texttool tag in index meta"""
707: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
708: if docinfo is None:
709: docinfo = {}
710: if docinfo.get('lang', None) is None:
711: docinfo['lang'] = '' # default keine Sprache gesetzt
712: if dom is None:
713: dom = self.getDomFromIndexMeta(url)
714:
715: archivePath = None
716: archiveName = None
717:
718: archiveNames = dom.xpath("//resource/name")
719: if archiveNames and (len(archiveNames) > 0):
720: archiveName = getTextFromNode(archiveNames[0])
721: else:
722: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
723:
724: archivePaths = dom.xpath("//resource/archive-path")
725: if archivePaths and (len(archivePaths) > 0):
726: archivePath = getTextFromNode(archivePaths[0])
727: # clean up archive path
728: if archivePath[0] != '/':
729: archivePath = '/' + archivePath
730: if archiveName and (not archivePath.endswith(archiveName)):
731: archivePath += "/" + archiveName
732: else:
733: # try to get archive-path from url
734: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
735: if (not url.startswith('http')):
736: archivePath = url.replace('index.meta', '')
737:
738: if archivePath is None:
739: # we balk without archive-path
740: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
741:
742: imageDirs = dom.xpath("//texttool/image")
743: if imageDirs and (len(imageDirs) > 0):
744: imageDir = getTextFromNode(imageDirs[0])
745:
746: else:
747: # we balk with no image tag / not necessary anymore because textmode is now standard
748: #raise IOError("No text-tool info in %s"%(url))
749: imageDir = ""
750: #xquery="//pb"
751: docinfo['imagePath'] = "" # keine Bilder
752: docinfo['imageURL'] = ""
753:
754: if imageDir and archivePath:
755: #print "image: ", imageDir, " archivepath: ", archivePath
756: imageDir = os.path.join(archivePath, imageDir)
757: imageDir = imageDir.replace("/mpiwg/online", '')
758: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
759: docinfo['imagePath'] = imageDir
760:
761: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
762:
763: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
764: if viewerUrls and (len(viewerUrls) > 0):
765: viewerUrl = getTextFromNode(viewerUrls[0])
766: docinfo['viewerURL'] = viewerUrl
767:
768: # old style text URL
769: textUrls = dom.xpath("//texttool/text")
770: if textUrls and (len(textUrls) > 0):
771: textUrl = getTextFromNode(textUrls[0])
772: if urlparse.urlparse(textUrl)[0] == "": #keine url
773: textUrl = os.path.join(archivePath, textUrl)
774: # fix URLs starting with /mpiwg/online
775: if textUrl.startswith("/mpiwg/online"):
776: textUrl = textUrl.replace("/mpiwg/online", '', 1)
777:
778: docinfo['textURL'] = textUrl
779:
780: # new style text-url-path
781: textUrls = dom.xpath("//texttool/text-url-path")
782: if textUrls and (len(textUrls) > 0):
783: textUrl = getTextFromNode(textUrls[0])
784: docinfo['textURLPath'] = textUrl
785: textUrlkurz = string.split(textUrl, ".")[0]
786: docinfo['textURLPathkurz'] = textUrlkurz
787: #if not docinfo['imagePath']:
788: # text-only, no page images
789: #docinfo = self.getNumTextPages(docinfo)
790:
791:
792: presentationUrls = dom.xpath("//texttool/presentation")
793: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
794: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
795:
796:
797: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
798: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
799: # durch den relativen Pfad auf die presentation infos
800: presentationPath = getTextFromNode(presentationUrls[0])
801: if url.endswith("index.meta"):
802: presentationUrl = url.replace('index.meta', presentationPath)
803: else:
804: presentationUrl = url + "/" + presentationPath
805:
806: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
807:
808: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
809:
810: return docinfo
811:
812:
813: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
814: """gets the bibliographical information from the preseantion entry in texttools
815: """
816: dom=self.getPresentationInfoXML(url)
817: try:
818: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
819: except:
820: pass
821: try:
822: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
823: except:
824: pass
825: try:
826: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
827: except:
828: pass
829: return docinfo
830:
831: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
832: """path ist the path to the images it assumes that the index.meta file is one level higher."""
833: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
834: if docinfo is None:
835: docinfo = {}
836: path=path.replace("/mpiwg/online","")
837: docinfo['imagePath'] = path
838: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
839:
840: pathorig=path
841: for x in range(cut):
842: path=getParentDir(path)
843: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
844: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
845: docinfo['imageURL'] = imageUrl
846:
847: #path ist the path to the images it assumes that the index.meta file is one level higher.
848: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
849: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
850: return docinfo
851:
852:
853: def getDocinfo(self, mode, url):
854: """returns docinfo depending on mode"""
855: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
856: # look for cached docinfo in session
857: if self.REQUEST.SESSION.has_key('docinfo'):
858: docinfo = self.REQUEST.SESSION['docinfo']
859: # check if its still current
860: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
861: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
862: return docinfo
863: # new docinfo
864: docinfo = {'mode': mode, 'url': url}
865: if mode=="texttool": #index.meta with texttool information
866: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
867: elif mode=="imagepath":
868: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
869: elif mode=="filepath":
870: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
871: else:
872: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
873: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
874:
875: # FIXME: fake texturlpath
876: if not docinfo.has_key('textURLPath'):
877: docinfo['textURLPath'] = None
878:
879: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
880: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
881: self.REQUEST.SESSION['docinfo'] = docinfo
882: return docinfo
883:
884: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
885: """returns pageinfo with the given parameters"""
886: pageinfo = {}
887: current = getInt(current)
888:
889: pageinfo['current'] = current
890: rows = int(rows or self.thumbrows)
891: pageinfo['rows'] = rows
892: cols = int(cols or self.thumbcols)
893: pageinfo['cols'] = cols
894: grpsize = cols * rows
895: pageinfo['groupsize'] = grpsize
896: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
897: # int(current / grpsize) * grpsize +1))
898: pageinfo['start'] = start
899: pageinfo['end'] = start + grpsize
900: if (docinfo is not None) and ('numPages' in docinfo):
901: np = int(docinfo['numPages'])
902: pageinfo['end'] = min(pageinfo['end'], np)
903: pageinfo['numgroups'] = int(np / grpsize)
904: if np % grpsize > 0:
905: pageinfo['numgroups'] += 1
906: pageinfo['viewMode'] = viewMode
907: pageinfo['tocMode'] = tocMode
908: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
909: #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
910: pageinfo['query'] = self.REQUEST.get('query','')
911: pageinfo['queryType'] = self.REQUEST.get('queryType','')
912: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
913: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
914: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
915: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
916: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
917: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
918: toc = int (pageinfo['tocPN'])
919: pageinfo['textPages'] =int (toc)
920:
921: if 'tocSize_%s'%tocMode in docinfo:
922: tocSize = int(docinfo['tocSize_%s'%tocMode])
923: tocPageSize = int(pageinfo['tocPageSize'])
924: # cached toc
925: if tocSize%tocPageSize>0:
926: tocPages=tocSize/tocPageSize+1
927: else:
928: tocPages=tocSize/tocPageSize
929: pageinfo['tocPN'] = min (tocPages,toc)
930: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
931: pageinfo['sn'] =self.REQUEST.get('sn','')
932: return pageinfo
933:
934: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
935: """init document viewer"""
936: self.title=title
937: self.digilibBaseUrl = digilibBaseUrl
938: self.thumbrows = thumbrows
939: self.thumbcols = thumbcols
940: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
941: if RESPONSE is not None:
942: RESPONSE.redirect('manage_main')
943:
944: def manage_AddDocumentViewerForm(self):
945: """add the viewer form"""
946: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
947: return pt()
948:
949: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
950: """add the viewer"""
951: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
952: self._setObject(id,newObj)
953:
954: if RESPONSE is not None:
955: RESPONSE.redirect('manage_main')
956:
957: ## DocumentViewerTemplate class
958: class DocumentViewerTemplate(ZopePageTemplate):
959: """Template for document viewer"""
960: meta_type="DocumentViewer Template"
961:
962:
963: def manage_addDocumentViewerTemplateForm(self):
964: """Form for adding"""
965: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
966: return pt()
967:
968: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
969: REQUEST=None, submit=None):
970: "Add a Page Template with optional file content."
971:
972: self._setObject(id, DocumentViewerTemplate(id))
973: ob = getattr(self, id)
974: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
975: logging.info("txt %s:"%txt)
976: ob.pt_edit(txt,"text/html")
977: if title:
978: ob.pt_setTitle(title)
979: try:
980: u = self.DestinationURL()
981: except AttributeError:
982: u = REQUEST['URL1']
983:
984: u = "%s/%s" % (u, urllib.quote(id))
985: REQUEST.RESPONSE.redirect(u+'/manage_main')
986: return ''
987:
988:
989:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to documentViewer.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / documentViewer