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