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_double = PageTemplateFile('zpt/page_main_double', globals())
151: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
152: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
153: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
154: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
155: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
156: head_main = PageTemplateFile('zpt/head_main', globals())
157: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
158: info_xml = PageTemplateFile('zpt/info_xml', globals())
159:
160:
161: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
162: security.declareProtected('View management screens','changeDocumentViewerForm')
163: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
164:
165:
166: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
167: """init document viewer"""
168: self.id=id
169: self.title=title
170: self.thumbcols = thumbcols
171: self.thumbrows = thumbrows
172: # authgroups is list of authorized groups (delimited by ,)
173: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
174: # create template folder so we can always use template.something
175:
176: templateFolder = Folder('template')
177: #self['template'] = templateFolder # Zope-2.12 style
178: self._setObject('template',templateFolder) # old style
179: try:
180: import MpdlXmlTextServer
181: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
182: #templateFolder['fulltextclient'] = xmlRpcClient
183: templateFolder._setObject('fulltextclient',textServer)
184: except Exception, e:
185: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
186: try:
187: from Products.zogiLib.zogiLib import zogiLib
188: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
189: #templateFolder['zogilib'] = zogilib
190: templateFolder._setObject('zogilib',zogilib)
191: except Exception, e:
192: logging.error("Unable to create zogiLib for zogilib: "+str(e))
193:
194:
195: # proxy text server methods to fulltextclient
196: def getTextPage(self, **args):
197: """get page"""
198: return self.template.fulltextclient.getTextPage(**args)
199:
200: def getQuery(self, **args):
201: """get query"""
202: return self.template.fulltextclient.getQuery(**args)
203:
204: def getQueryResultHits(self, **args):
205: """get query"""
206: return self.template.fulltextclient.getQueryResultHits(**args)
207:
208: def getQueryResultHitsText(self, **args):
209: """get query"""
210: return self.template.fulltextclient.getQueryResultHitsText(**args)
211:
212: def getQueryResultHitsFigures(self, **args):
213: """get query"""
214: return self.template.fulltextclient.getQueryResultHitsFigures(**args)
215:
216: def getSearch(self, **args):
217: """get search"""
218: return self.template.fulltextclient.getSearch(**args)
219:
220: def getGisPlaces(self, **args):
221: """get gis places"""
222: return self.template.fulltextclient.getGisPlaces(**args)
223:
224: def getAllGisPlaces(self, **args):
225: """get all gis places """
226: return self.template.fulltextclient.getAllGisPlaces(**args)
227:
228: def getOrigPages(self, **args):
229: """get original page number """
230: return self.template.fulltextclient.getOrigPages(**args)
231:
232: def getAllPlaces(self, **args):
233: """get original page number """
234: return self.template.fulltextclient.getAllPlaces(**args)
235:
236: def getTocEntries(self, **args):
237: """get original page number """
238: return self.template.fulltextclient.getTocEntries(**args)
239:
240: def getFigureEntries(self, **args):
241: """get original page number """
242: return self.template.fulltextclient.getFigureEntries(**args)
243:
244: def getNumPages(self, docinfo):
245: """get numpages"""
246: return self.template.fulltextclient.getNumPages(docinfo)
247:
248: def getNumTextPages(self, docinfo):
249: """get numpages text"""
250: return self.template.fulltextclient.getNumTextPages(docinfo)
251:
252: def getTranslate(self, **args):
253: """get translate"""
254: return self.template.fulltextclient.getTranslate(**args)
255:
256: def getLemma(self, **args):
257: """get lemma"""
258: return self.template.fulltextclient.getLemma(**args)
259:
260: def getToc(self, **args):
261: """get toc"""
262: return self.template.fulltextclient.getToc(**args)
263:
264: def getTocPage(self, **args):
265: """get tocpage"""
266: return self.template.fulltextclient.getTocPage(**args)
267:
268:
269: security.declareProtected('View','thumbs_rss')
270: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
271: '''
272: view it
273: @param mode: defines how to access the document behind url
274: @param url: url which contains display information
275: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
276:
277: '''
278: logging.debug("HHHHHHHHHHHHHH:load the rss")
279: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
280:
281: if not hasattr(self, 'template'):
282: # create template folder if it doesn't exist
283: self.manage_addFolder('template')
284:
285: if not self.digilibBaseUrl:
286: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
287:
288: docinfo = self.getDocinfo(mode=mode,url=url)
289: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
290: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
291: ''' ZDES '''
292: pt = getattr(self.template, 'thumbs_main_rss')
293:
294: if viewMode=="auto": # automodus gewaehlt
295: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
296: viewMode="text"
297: else:
298: viewMode="images"
299:
300: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
301:
302: security.declareProtected('View','index_html')
303: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
304: '''
305: view it
306: @param mode: defines how to access the document behind url
307: @param url: url which contains display information
308: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
309: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
310: @param characterNormalization type of text display (reg, norm, none)
311: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
312: '''
313:
314: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
315:
316: if not hasattr(self, 'template'):
317: # this won't work
318: logging.error("template folder missing!")
319: return "ERROR: template folder missing!"
320:
321: if not getattr(self, 'digilibBaseUrl', None):
322: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
323:
324: docinfo = self.getDocinfo(mode=mode,url=url)
325:
326: if tocMode != "thumbs":
327: # get table of contents
328: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
329:
330: if viewMode=="auto": # automodus gewaehlt
331: if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
332: viewMode="text_dict"
333: else:
334: viewMode="images"
335:
336: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
337:
338: pt = getattr(self.template, 'viewer_main')
339: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
340:
341: def generateMarks(self,mk):
342: ret=""
343: if mk is None:
344: return ""
345: if not isinstance(mk, list):
346: mk=[mk]
347: for m in mk:
348: ret+="mk=%s"%m
349: return ret
350:
351:
352: def getBrowser(self):
353: """getBrowser the version of browser """
354: names=""
355: names = browserCheck(self)
356: return names
357:
358: def findDigilibUrl(self):
359: """try to get the digilib URL from zogilib"""
360: url = self.template.zogilib.getDLBaseUrl()
361: return url
362:
363: def getDocumentViewerURL(self):
364: """returns the URL of this instance"""
365: return self.absolute_url()
366:
367: def getStyle(self, idx, selected, style=""):
368: """returns a string with the given style and append 'sel' if path == selected."""
369: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
370: if idx == selected:
371: return style + 'sel'
372: else:
373: return style
374:
375: def getLink(self,param=None,val=None):
376: """link to documentviewer with parameter param set to val"""
377: params=self.REQUEST.form.copy()
378: if param is not None:
379: if val is None:
380: if params.has_key(param):
381: del params[param]
382: else:
383: params[param] = str(val)
384:
385: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
386: params["mode"] = "imagepath"
387: params["url"] = getParentDir(params["url"])
388:
389: # quote values and assemble into query string
390: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
391: ps = urllib.urlencode(params)
392: url=self.REQUEST['URL1']+"?"+ps
393: return url
394:
395: def getLinkAmp(self,param=None,val=None):
396: """link to documentviewer with parameter param set to val"""
397: params=self.REQUEST.form.copy()
398: if param is not None:
399: if val is None:
400: if params.has_key(param):
401: del params[param]
402: else:
403: params[param] = str(val)
404:
405: # quote values and assemble into query string
406: logging.debug("XYXXXXX: %s"%repr(params.items()))
407: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
408: url=self.REQUEST['URL1']+"?"+ps
409: return url
410:
411: def getInfo_xml(self,url,mode):
412: """returns info about the document as XML"""
413:
414: if not self.digilibBaseUrl:
415: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
416:
417: docinfo = self.getDocinfo(mode=mode,url=url)
418: pt = getattr(self.template, 'info_xml')
419: return pt(docinfo=docinfo)
420:
421: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
422: """returns new option state"""
423: if not self.REQUEST.SESSION.has_key(optionName):
424: # not in session -- initial
425: opt = {'lastState': newState, 'state': initialState}
426: else:
427: opt = self.REQUEST.SESSION.get(optionName)
428: if opt['lastState'] != newState:
429: # state in session has changed -- toggle
430: opt['state'] = not opt['state']
431: opt['lastState'] = newState
432:
433: self.REQUEST.SESSION[optionName] = opt
434: return opt['state']
435:
436: def isAccessible(self, docinfo):
437: """returns if access to the resource is granted"""
438: access = docinfo.get('accessType', None)
439: logging.debug("documentViewer (accessOK) access type %s"%access)
440: if access is not None and access == 'free':
441: logging.debug("documentViewer (accessOK) access is free")
442: return True
443: elif access is None or access in self.authgroups:
444: # only local access -- only logged in users
445: user = getSecurityManager().getUser()
446: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
447: if user is not None:
448: #print "user: ", user
449: return (user.getUserName() != "Anonymous User")
450: else:
451: return False
452:
453: logging.error("documentViewer (accessOK) unknown access type %s"%access)
454: return False
455:
456:
457: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
458: """gibt param von dlInfo aus"""
459: if docinfo is None:
460: docinfo = {}
461:
462: for x in range(cut):
463:
464: path=getParentDir(path)
465:
466: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
467:
468: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
469:
470: txt = getHttpData(infoUrl)
471: if txt is None:
472: raise IOError("Unable to get dir-info from %s"%(infoUrl))
473:
474: dom = Parse(txt)
475: sizes=dom.xpath("//dir/size")
476: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
477:
478: if sizes:
479: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
480: else:
481: docinfo['numPages'] = 0
482:
483: # TODO: produce and keep list of image names and numbers
484:
485: return docinfo
486:
487: def getIndexMetaPath(self,url):
488: """gib nur den Pfad zurueck"""
489: regexp = re.compile(r".*(experimental|permanent)/(.*)")
490: regpath = regexp.match(url)
491: if (regpath==None):
492: return ""
493: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
494: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
495:
496:
497:
498: def getIndexMetaUrl(self,url):
499: """returns utr of index.meta document at url"""
500:
501: metaUrl = None
502: if url.startswith("http://"):
503: # real URL
504: metaUrl = url
505: else:
506: # online path
507: server=self.digilibBaseUrl+"/servlet/Texter?fn="
508: metaUrl=server+url.replace("/mpiwg/online","")
509: if not metaUrl.endswith("index.meta"):
510: metaUrl += "/index.meta"
511:
512: return metaUrl
513:
514: def getDomFromIndexMeta(self, url):
515: """get dom from index meta"""
516: dom = None
517: metaUrl = self.getIndexMetaUrl(url)
518:
519: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
520: txt=getHttpData(metaUrl)
521: if txt is None:
522: raise IOError("Unable to read index meta from %s"%(url))
523:
524: dom = Parse(txt)
525: return dom
526:
527: def getPresentationInfoXML(self, url):
528: """returns dom of info.xml document at url"""
529: dom = None
530: metaUrl = None
531: if url.startswith("http://"):
532: # real URL
533: metaUrl = url
534: else:
535: # online path
536: server=self.digilibBaseUrl+"/servlet/Texter?fn="
537: metaUrl=server+url.replace("/mpiwg/online","")
538:
539: txt=getHttpData(metaUrl)
540: if txt is None:
541: raise IOError("Unable to read infoXMLfrom %s"%(url))
542:
543: dom = Parse(txt)
544: return dom
545:
546:
547: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
548: """gets authorization info from the index.meta file at path or given by dom"""
549: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
550:
551: access = None
552:
553: if docinfo is None:
554: docinfo = {}
555:
556: if dom is None:
557: for x in range(cut):
558: path=getParentDir(path)
559: dom = self.getDomFromIndexMeta(path)
560:
561: acctype = dom.xpath("//access-conditions/access/@type")
562: if acctype and (len(acctype)>0):
563: access=acctype[0].value
564: if access in ['group', 'institution']:
565: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
566:
567: docinfo['accessType'] = access
568: return docinfo
569:
570:
571: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
572: """gets bibliographical info from the index.meta file at path or given by dom"""
573: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
574:
575: if docinfo is None:
576: docinfo = {}
577:
578: if dom is None:
579: for x in range(cut):
580: path=getParentDir(path)
581: dom = self.getDomFromIndexMeta(path)
582:
583: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
584:
585: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
586: # put in all raw bib fields as dict "bib"
587: bib = dom.xpath("//bib/*")
588: if bib and len(bib)>0:
589: bibinfo = {}
590: for e in bib:
591: bibinfo[e.localName] = getTextFromNode(e)
592: docinfo['bib'] = bibinfo
593:
594: # extract some fields (author, title, year) according to their mapping
595: metaData=self.metadata.main.meta.bib
596: bibtype=dom.xpath("//bib/@type")
597: if bibtype and (len(bibtype)>0):
598: bibtype=bibtype[0].value
599: else:
600: bibtype="generic"
601:
602: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
603: docinfo['bib_type'] = bibtype
604: bibmap=metaData.generateMappingForType(bibtype)
605: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
606: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
607: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
608: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
609: try:
610: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
611: except: pass
612: try:
613: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
614: except: pass
615: try:
616: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
617: except: pass
618: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
619: try:
620: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
621: except:
622: docinfo['lang']=''
623:
624: return docinfo
625:
626:
627: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
628: """gets name info from the index.meta file at path or given by dom"""
629: if docinfo is None:
630: docinfo = {}
631:
632: if dom is None:
633: for x in range(cut):
634: path=getParentDir(path)
635: dom = self.getDomFromIndexMeta(path)
636:
637: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
638: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
639: return docinfo
640:
641: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
642: """parse texttool tag in index meta"""
643: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
644: if docinfo is None:
645: docinfo = {}
646: if docinfo.get('lang', None) is None:
647: docinfo['lang'] = '' # default keine Sprache gesetzt
648: if dom is None:
649: dom = self.getDomFromIndexMeta(url)
650:
651: archivePath = None
652: archiveName = None
653:
654: archiveNames = dom.xpath("//resource/name")
655: if archiveNames and (len(archiveNames) > 0):
656: archiveName = getTextFromNode(archiveNames[0])
657: else:
658: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
659:
660: archivePaths = dom.xpath("//resource/archive-path")
661: if archivePaths and (len(archivePaths) > 0):
662: archivePath = getTextFromNode(archivePaths[0])
663: # clean up archive path
664: if archivePath[0] != '/':
665: archivePath = '/' + archivePath
666: if archiveName and (not archivePath.endswith(archiveName)):
667: archivePath += "/" + archiveName
668: else:
669: # try to get archive-path from url
670: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
671: if (not url.startswith('http')):
672: archivePath = url.replace('index.meta', '')
673:
674: if archivePath is None:
675: # we balk without archive-path
676: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
677:
678: imageDirs = dom.xpath("//texttool/image")
679: if imageDirs and (len(imageDirs) > 0):
680: imageDir = getTextFromNode(imageDirs[0])
681:
682: else:
683: # we balk with no image tag / not necessary anymore because textmode is now standard
684: #raise IOError("No text-tool info in %s"%(url))
685: imageDir = ""
686: #xquery="//pb"
687: docinfo['imagePath'] = "" # keine Bilder
688: docinfo['imageURL'] = ""
689:
690: if imageDir and archivePath:
691: #print "image: ", imageDir, " archivepath: ", archivePath
692: imageDir = os.path.join(archivePath, imageDir)
693: imageDir = imageDir.replace("/mpiwg/online", '')
694: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
695: docinfo['imagePath'] = imageDir
696:
697: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
698:
699: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
700: if viewerUrls and (len(viewerUrls) > 0):
701: viewerUrl = getTextFromNode(viewerUrls[0])
702: docinfo['viewerURL'] = viewerUrl
703:
704: # old style text URL
705: textUrls = dom.xpath("//texttool/text")
706: if textUrls and (len(textUrls) > 0):
707: textUrl = getTextFromNode(textUrls[0])
708: if urlparse.urlparse(textUrl)[0] == "": #keine url
709: textUrl = os.path.join(archivePath, textUrl)
710: # fix URLs starting with /mpiwg/online
711: if textUrl.startswith("/mpiwg/online"):
712: textUrl = textUrl.replace("/mpiwg/online", '', 1)
713:
714: docinfo['textURL'] = textUrl
715:
716: # new style text-url-path
717: textUrls = dom.xpath("//texttool/text-url-path")
718: if textUrls and (len(textUrls) > 0):
719: textUrl = getTextFromNode(textUrls[0])
720: docinfo['textURLPath'] = textUrl
721: if not docinfo['imagePath']:
722: # text-only, no page images
723: docinfo = self.getNumTextPages(docinfo)
724:
725: presentationUrls = dom.xpath("//texttool/presentation")
726: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
727: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
728:
729:
730: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
731: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
732: # durch den relativen Pfad auf die presentation infos
733: presentationPath = getTextFromNode(presentationUrls[0])
734: if url.endswith("index.meta"):
735: presentationUrl = url.replace('index.meta', presentationPath)
736: else:
737: presentationUrl = url + "/" + presentationPath
738:
739: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
740:
741: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
742:
743: return docinfo
744:
745:
746: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
747: """gets the bibliographical information from the preseantion entry in texttools
748: """
749: dom=self.getPresentationInfoXML(url)
750: try:
751: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
752: except:
753: pass
754: try:
755: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
756: except:
757: pass
758: try:
759: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
760: except:
761: pass
762: return docinfo
763:
764: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
765: """path ist the path to the images it assumes that the index.meta file is one level higher."""
766: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
767: if docinfo is None:
768: docinfo = {}
769: path=path.replace("/mpiwg/online","")
770: docinfo['imagePath'] = path
771: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
772:
773: pathorig=path
774: for x in range(cut):
775: path=getParentDir(path)
776: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
777: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
778: docinfo['imageURL'] = imageUrl
779:
780: #path ist the path to the images it assumes that the index.meta file is one level higher.
781: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
782: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
783: return docinfo
784:
785:
786: def getDocinfo(self, mode, url):
787: """returns docinfo depending on mode"""
788: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
789: # look for cached docinfo in session
790: if self.REQUEST.SESSION.has_key('docinfo'):
791: docinfo = self.REQUEST.SESSION['docinfo']
792: # check if its still current
793: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
794: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
795: return docinfo
796: # new docinfo
797: docinfo = {'mode': mode, 'url': url}
798: if mode=="texttool": #index.meta with texttool information
799: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
800: elif mode=="imagepath":
801: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
802: elif mode=="filepath":
803: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
804: else:
805: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
806: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
807:
808: # FIXME: fake texturlpath
809: if not docinfo.has_key('textURLPath'):
810: docinfo['textURLPath'] = None
811:
812: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
813: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
814: self.REQUEST.SESSION['docinfo'] = docinfo
815: return docinfo
816:
817: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
818: """returns pageinfo with the given parameters"""
819: pageinfo = {}
820: current = getInt(current)
821:
822: pageinfo['current'] = current
823: rows = int(rows or self.thumbrows)
824: pageinfo['rows'] = rows
825: cols = int(cols or self.thumbcols)
826: pageinfo['cols'] = cols
827: grpsize = cols * rows
828: pageinfo['groupsize'] = grpsize
829: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
830: # int(current / grpsize) * grpsize +1))
831: pageinfo['start'] = start
832: pageinfo['end'] = start + grpsize
833: if (docinfo is not None) and ('numPages' in docinfo):
834: np = int(docinfo['numPages'])
835: pageinfo['end'] = min(pageinfo['end'], np)
836: pageinfo['numgroups'] = int(np / grpsize)
837: if np % grpsize > 0:
838: pageinfo['numgroups'] += 1
839: pageinfo['viewMode'] = viewMode
840: pageinfo['tocMode'] = tocMode
841: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
842: pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','')
843: pageinfo['query'] = self.REQUEST.get('query','')
844: pageinfo['queryType'] = self.REQUEST.get('queryType','')
845: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
846: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
847: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
848: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
849: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
850: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
851: toc = int (pageinfo['tocPN'])
852: pageinfo['textPages'] =int (toc)
853:
854:
855:
856: if 'tocSize_%s'%tocMode in docinfo:
857: tocSize = int(docinfo['tocSize_%s'%tocMode])
858: tocPageSize = int(pageinfo['tocPageSize'])
859: # cached toc
860: if tocSize%tocPageSize>0:
861: tocPages=tocSize/tocPageSize+1
862: else:
863: tocPages=tocSize/tocPageSize
864: pageinfo['tocPN'] = min (tocPages,toc)
865: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
866: pageinfo['sn'] =self.REQUEST.get('sn','')
867: return pageinfo
868:
869: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
870: """init document viewer"""
871: self.title=title
872: self.digilibBaseUrl = digilibBaseUrl
873: self.thumbrows = thumbrows
874: self.thumbcols = thumbcols
875: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
876: if RESPONSE is not None:
877: RESPONSE.redirect('manage_main')
878:
879: def manage_AddDocumentViewerForm(self):
880: """add the viewer form"""
881: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
882: return pt()
883:
884: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
885: """add the viewer"""
886: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
887: self._setObject(id,newObj)
888:
889: if RESPONSE is not None:
890: RESPONSE.redirect('manage_main')
891:
892: ## DocumentViewerTemplate class
893: class DocumentViewerTemplate(ZopePageTemplate):
894: """Template for document viewer"""
895: meta_type="DocumentViewer Template"
896:
897:
898: def manage_addDocumentViewerTemplateForm(self):
899: """Form for adding"""
900: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
901: return pt()
902:
903: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
904: REQUEST=None, submit=None):
905: "Add a Page Template with optional file content."
906:
907: self._setObject(id, DocumentViewerTemplate(id))
908: ob = getattr(self, id)
909: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
910: logging.info("txt %s:"%txt)
911: ob.pt_edit(txt,"text/html")
912: if title:
913: ob.pt_setTitle(title)
914: try:
915: u = self.DestinationURL()
916: except AttributeError:
917: u = REQUEST['URL1']
918:
919: u = "%s/%s" % (u, urllib.quote(id))
920: REQUEST.RESPONSE.redirect(u+'/manage_main')
921: return ''
922:
923:
924:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>