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