1:
2: from OFS.Folder import Folder
3: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
4: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
5: from AccessControl import ClassSecurityInfo
6: from AccessControl import getSecurityManager
7: from Globals import package_home
8: from Products.zogiLib.zogiLib import browserCheck
9:
10: from Ft.Xml import EMPTY_NAMESPACE, Parse
11: import Ft.Xml.Domlette
12: import os.path
13: import sys
14: import urllib
15: import urllib2
16: import logging
17: import math
18: import urlparse
19: import cStringIO
20: import re
21: import string
22:
23: def logger(txt,method,txt2):
24: """logging"""
25: logging.info(txt+ txt2)
26:
27:
28: def getInt(number, default=0):
29: """returns always an int (0 in case of problems)"""
30: try:
31: return int(number)
32: except:
33: return int(default)
34:
35: def getTextFromNode(nodename):
36: """get the cdata content of a node"""
37: if nodename is None:
38: return ""
39: nodelist=nodename.childNodes
40: rc = ""
41: for node in nodelist:
42: if node.nodeType == node.TEXT_NODE:
43: rc = rc + node.data
44: return rc
45:
46: def serializeNode(node, encoding='utf-8'):
47: """returns a string containing node as XML"""
48: buf = cStringIO.StringIO()
49: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
50: s = buf.getvalue()
51: buf.close()
52: return s
53:
54: def browserCheck(self):
55: """check the browsers request to find out the browser type"""
56: bt = {}
57: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
58: bt['ua'] = ua
59: bt['isIE'] = False
60: bt['isN4'] = False
61: bt['versFirefox']=""
62: bt['versIE']=""
63: bt['versSafariChrome']=""
64: bt['versOpera']=""
65:
66: if string.find(ua, 'MSIE') > -1:
67: bt['isIE'] = True
68: else:
69: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
70: # Safari oder Chrome identification
71: try:
72: nav = ua[string.find(ua, '('):]
73: nav1=ua[string.find(ua,')'):]
74: nav2=nav1[string.find(nav1,'('):]
75: nav3=nav2[string.find(nav2,')'):]
76: ie = string.split(nav, "; ")[1]
77: ie1 =string.split(nav1, " ")[2]
78: ie2 =string.split(nav3, " ")[1]
79: ie3 =string.split(nav3, " ")[2]
80: if string.find(ie3, "Safari") >-1:
81: bt['versSafariChrome']=string.split(ie2, "/")[1]
82: except: pass
83: # IE identification
84: try:
85: nav = ua[string.find(ua, '('):]
86: ie = string.split(nav, "; ")[1]
87: if string.find(ie, "MSIE") > -1:
88: bt['versIE'] = string.split(ie, " ")[1]
89: except:pass
90: # Firefox identification
91: try:
92: nav = ua[string.find(ua, '('):]
93: nav1=ua[string.find(ua,')'):]
94: if string.find(ie1, "Firefox") >-1:
95: nav5= string.split(ie1, "/")[1]
96: logging.debug("FIREFOX: %s"%(nav5))
97: bt['versFirefox']=string.split(nav5, ".")[1]
98: except:pass
99: #Opera identification
100: try:
101: if string.find(ua,"Opera") >-1:
102: nav = ua[string.find(ua, '('):]
103: nav1=nav[string.find(nav,')'):]
104: bt['versOpera']=string.split(nav1,"/")[2]
105: except:pass
106:
107: bt['isMac'] = string.find(ua, 'Macintosh') > -1
108: bt['isWin'] = string.find(ua, 'Windows') > -1
109: bt['isIEWin'] = bt['isIE'] and bt['isWin']
110: bt['isIEMac'] = bt['isIE'] and bt['isMac']
111: bt['staticHTML'] = False
112:
113: return bt
114:
115:
116: def getParentDir(path):
117: """returns pathname shortened by one"""
118: return '/'.join(path.split('/')[0:-1])
119:
120:
121: def getHttpData(url, data=None, num_tries=3, timeout=10):
122: """returns result from url+data HTTP request"""
123: # we do GET (by appending data to url)
124: if isinstance(data, str) or isinstance(data, unicode):
125: # if data is string then append
126: url = "%s?%s"%(url,data)
127: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
128: # urlencode
129: url = "%s?%s"%(url,urllib.urlencode(data))
130:
131: response = None
132: errmsg = None
133: for cnt in range(num_tries):
134: try:
135: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
136: if sys.version_info < (2, 6):
137: # set timeout on socket -- ugly :-(
138: import socket
139: socket.setdefaulttimeout(float(timeout))
140: response = urllib2.urlopen(url)
141: else:
142: response = urllib2.urlopen(url,timeout=float(timeout))
143: # check result?
144: break
145: except urllib2.HTTPError, e:
146: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
147: errmsg = str(e)
148: # stop trying
149: break
150: except urllib2.URLError, e:
151: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
152: errmsg = str(e)
153: # stop trying
154: #break
155:
156: if response is not None:
157: data = response.read()
158: response.close()
159: return data
160:
161: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
162: #return None
163:
164:
165:
166: ##
167: ## documentViewer class
168: ##
169: class documentViewer(Folder):
170: """document viewer"""
171: meta_type="Document viewer"
172:
173: security=ClassSecurityInfo()
174: manage_options=Folder.manage_options+(
175: {'label':'main config','action':'changeDocumentViewerForm'},
176: )
177:
178: # templates and forms
179: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
180: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
181: toc_text = PageTemplateFile('zpt/toc_text', globals())
182: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
183: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
184: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
185: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
186: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
187: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
188: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
189: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
190: head_main = PageTemplateFile('zpt/head_main', globals())
191: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
192: info_xml = PageTemplateFile('zpt/info_xml', globals())
193:
194:
195: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
196: security.declareProtected('View management screens','changeDocumentViewerForm')
197: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
198:
199:
200: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
201: """init document viewer"""
202: self.id=id
203: self.title=title
204: self.thumbcols = thumbcols
205: self.thumbrows = thumbrows
206: # authgroups is list of authorized groups (delimited by ,)
207: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
208: # create template folder so we can always use template.something
209:
210: templateFolder = Folder('template')
211: #self['template'] = templateFolder # Zope-2.12 style
212: self._setObject('template',templateFolder) # old style
213: try:
214: import MpdlXmlTextServer
215: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
216: #templateFolder['fulltextclient'] = xmlRpcClient
217: templateFolder._setObject('fulltextclient',textServer)
218: except Exception, e:
219: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
220: try:
221: from Products.zogiLib.zogiLib import zogiLib
222: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
223: #templateFolder['zogilib'] = zogilib
224: templateFolder._setObject('zogilib',zogilib)
225: except Exception, e:
226: logging.error("Unable to create zogiLib for zogilib: "+str(e))
227:
228:
229: # proxy text server methods to fulltextclient
230: def getTextPage(self, **args):
231: """get page"""
232: return self.template.fulltextclient.getTextPage(**args)
233:
234: def getQuery(self, **args):
235: """get query in search"""
236: return self.template.fulltextclient.getQuery(**args)
237:
238: def getSearch(self, **args):
239: """get search"""
240: return self.template.fulltextclient.getSearch(**args)
241:
242: def getGisPlaces(self, **args):
243: """get gis places"""
244: return self.template.fulltextclient.getGisPlaces(**args)
245:
246: def getAllGisPlaces(self, **args):
247: """get all gis places """
248: return self.template.fulltextclient.getAllGisPlaces(**args)
249:
250: def getTranslate(self, **args):
251: """get translate"""
252: return self.template.fulltextclient.getTranslate(**args)
253:
254: def getLemma(self, **args):
255: """get lemma"""
256: return self.template.fulltextclient.getLemma(**args)
257:
258: def getToc(self, **args):
259: """get toc"""
260: return self.template.fulltextclient.getToc(**args)
261:
262: def getTocPage(self, **args):
263: """get tocpage"""
264: return self.template.fulltextclient.getTocPage(**args)
265:
266:
267: security.declareProtected('View','thumbs_rss')
268: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
269: '''
270: view it
271: @param mode: defines how to access the document behind url
272: @param url: url which contains display information
273: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
274:
275: '''
276: logging.debug("HHHHHHHHHHHHHH:load the rss")
277: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
278:
279: if not hasattr(self, 'template'):
280: # create template folder if it doesn't exist
281: self.manage_addFolder('template')
282:
283: if not self.digilibBaseUrl:
284: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
285:
286: docinfo = self.getDocinfo(mode=mode,url=url)
287: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
288: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
289: ''' ZDES '''
290: pt = getattr(self.template, 'thumbs_main_rss')
291:
292: if viewMode=="auto": # automodus gewaehlt
293: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
294: viewMode="text"
295: else:
296: viewMode="images"
297:
298: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
299:
300: security.declareProtected('View','index_html')
301: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
302: '''
303: view it
304: @param mode: defines how to access the document behind url
305: @param url: url which contains display information
306: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
307: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
308: @param characterNormalization type of text display (reg, norm, none)
309: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
310: '''
311:
312: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
313:
314: if not hasattr(self, 'template'):
315: # this won't work
316: logging.error("template folder missing!")
317: return "ERROR: template folder missing!"
318:
319: if not getattr(self, 'digilibBaseUrl', None):
320: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
321:
322: docinfo = self.getDocinfo(mode=mode,url=url)
323:
324: if tocMode != "thumbs":
325: # get table of contents
326: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
327:
328: if viewMode=="auto": # automodus gewaehlt
329: if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
330: viewMode="text_dict"
331: else:
332: viewMode="images"
333:
334: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
335:
336: if (docinfo.get('textURLPath',None)):
337: page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo)
338: pageinfo['textPage'] = page
339: pt = getattr(self.template, 'viewer_main')
340: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
341:
342: def generateMarks(self,mk):
343: ret=""
344: if mk is None:
345: return ""
346: if not isinstance(mk, list):
347: mk=[mk]
348: for m in mk:
349: ret+="mk=%s"%m
350: return ret
351:
352:
353: def getBrowser(self):
354: """getBrowser the version of browser """
355: bt = browserCheck(self)
356: logging.debug("BROWSER VERSION: %s"%(bt))
357: return bt
358:
359: def findDigilibUrl(self):
360: """try to get the digilib URL from zogilib"""
361: url = self.template.zogilib.getDLBaseUrl()
362: return url
363:
364: def getDocumentViewerURL(self):
365: """returns the URL of this instance"""
366: return self.absolute_url()
367:
368: def getStyle(self, idx, selected, style=""):
369: """returns a string with the given style and append 'sel' if path == selected."""
370: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
371: if idx == selected:
372: return style + 'sel'
373: else:
374: return style
375:
376: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
377: """returns URL to documentviewer with parameter param set to val or from dict params"""
378: # copy existing request params
379: urlParams=self.REQUEST.form.copy()
380: # change single param
381: if param is not None:
382: if val is None:
383: if urlParams.has_key(param):
384: del urlParams[param]
385: else:
386: urlParams[param] = str(val)
387:
388: # change more params
389: if params is not None:
390: for k in params.keys():
391: v = params[k]
392: if v is None:
393: # val=None removes param
394: if urlParams.has_key(k):
395: del urlParams[k]
396:
397: else:
398: urlParams[k] = v
399:
400: # FIXME: does this belong here?
401: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
402: urlParams["mode"] = "imagepath"
403: urlParams["url"] = getParentDir(urlParams["url"])
404:
405: # quote values and assemble into query string (not escaping '/')
406: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
407: #ps = urllib.urlencode(urlParams)
408: if baseUrl is None:
409: baseUrl = self.REQUEST['URL1']
410:
411: url = "%s?%s"%(baseUrl, ps)
412: return url
413:
414:
415: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
416: """link to documentviewer with parameter param set to val"""
417: return self.getLink(param, val, params, baseUrl, '&')
418:
419: def getInfo_xml(self,url,mode):
420: """returns info about the document as XML"""
421:
422: if not self.digilibBaseUrl:
423: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
424:
425: docinfo = self.getDocinfo(mode=mode,url=url)
426: pt = getattr(self.template, 'info_xml')
427: return pt(docinfo=docinfo)
428:
429: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
430: """returns new option state"""
431: if not self.REQUEST.SESSION.has_key(optionName):
432: # not in session -- initial
433: opt = {'lastState': newState, 'state': initialState}
434: else:
435: opt = self.REQUEST.SESSION.get(optionName)
436: if opt['lastState'] != newState:
437: # state in session has changed -- toggle
438: opt['state'] = not opt['state']
439: opt['lastState'] = newState
440:
441: self.REQUEST.SESSION[optionName] = opt
442: return opt['state']
443:
444: def isAccessible(self, docinfo):
445: """returns if access to the resource is granted"""
446: access = docinfo.get('accessType', None)
447: logging.debug("documentViewer (accessOK) access type %s"%access)
448: if access is not None and access == 'free':
449: logging.debug("documentViewer (accessOK) access is free")
450: return True
451: elif access is None or access in self.authgroups:
452: # only local access -- only logged in users
453: user = getSecurityManager().getUser()
454: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
455: if user is not None:
456: #print "user: ", user
457: return (user.getUserName() != "Anonymous User")
458: else:
459: return False
460:
461: logging.error("documentViewer (accessOK) unknown access type %s"%access)
462: return False
463:
464:
465: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
466: """gibt param von dlInfo aus"""
467: if docinfo is None:
468: docinfo = {}
469:
470: for x in range(cut):
471:
472: path=getParentDir(path)
473:
474: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
475:
476: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
477:
478: txt = getHttpData(infoUrl)
479: if txt is None:
480: raise IOError("Unable to get dir-info from %s"%(infoUrl))
481:
482: dom = Parse(txt)
483: sizes=dom.xpath("//dir/size")
484: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
485:
486: if sizes:
487: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
488: else:
489: docinfo['numPages'] = 0
490:
491: # TODO: produce and keep list of image names and numbers
492:
493: return docinfo
494:
495: def getIndexMetaPath(self,url):
496: """gib nur den Pfad zurueck"""
497: regexp = re.compile(r".*(experimental|permanent)/(.*)")
498: regpath = regexp.match(url)
499: if (regpath==None):
500: return ""
501: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
502: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
503:
504:
505:
506: def getIndexMetaUrl(self,url):
507: """returns utr of index.meta document at url"""
508:
509: metaUrl = None
510: if url.startswith("http://"):
511: # real URL
512: metaUrl = url
513: else:
514: # online path
515: server=self.digilibBaseUrl+"/servlet/Texter?fn="
516: metaUrl=server+url.replace("/mpiwg/online","")
517: if not metaUrl.endswith("index.meta"):
518: metaUrl += "/index.meta"
519:
520: return metaUrl
521:
522: def getDomFromIndexMeta(self, url):
523: """get dom from index meta"""
524: dom = None
525: metaUrl = self.getIndexMetaUrl(url)
526:
527: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
528: txt=getHttpData(metaUrl)
529: if txt is None:
530: raise IOError("Unable to read index meta from %s"%(url))
531:
532: dom = Parse(txt)
533: return dom
534:
535: def getPresentationInfoXML(self, url):
536: """returns dom of info.xml document at url"""
537: dom = None
538: metaUrl = None
539: if url.startswith("http://"):
540: # real URL
541: metaUrl = url
542: else:
543: # online path
544: server=self.digilibBaseUrl+"/servlet/Texter?fn="
545: metaUrl=server+url.replace("/mpiwg/online","")
546:
547: txt=getHttpData(metaUrl)
548: if txt is None:
549: raise IOError("Unable to read infoXMLfrom %s"%(url))
550:
551: dom = Parse(txt)
552: return dom
553:
554:
555: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
556: """gets authorization info from the index.meta file at path or given by dom"""
557: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
558:
559: access = None
560:
561: if docinfo is None:
562: docinfo = {}
563:
564: if dom is None:
565: for x in range(cut):
566: path=getParentDir(path)
567: dom = self.getDomFromIndexMeta(path)
568:
569: acctype = dom.xpath("//access-conditions/access/@type")
570: if acctype and (len(acctype)>0):
571: access=acctype[0].value
572: if access in ['group', 'institution']:
573: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
574:
575: docinfo['accessType'] = access
576: return docinfo
577:
578:
579: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
580: """gets bibliographical info from the index.meta file at path or given by dom"""
581: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
582:
583: if docinfo is None:
584: docinfo = {}
585:
586: if dom is None:
587: for x in range(cut):
588: path=getParentDir(path)
589: dom = self.getDomFromIndexMeta(path)
590:
591: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
592:
593: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
594: # put in all raw bib fields as dict "bib"
595: bib = dom.xpath("//bib/*")
596: if bib and len(bib)>0:
597: bibinfo = {}
598: for e in bib:
599: bibinfo[e.localName] = getTextFromNode(e)
600: docinfo['bib'] = bibinfo
601:
602: # extract some fields (author, title, year) according to their mapping
603: metaData=self.metadata.main.meta.bib
604: bibtype=dom.xpath("//bib/@type")
605: if bibtype and (len(bibtype)>0):
606: bibtype=bibtype[0].value
607: else:
608: bibtype="generic"
609:
610: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
611: docinfo['bib_type'] = bibtype
612: bibmap=metaData.generateMappingForType(bibtype)
613: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
614: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
615: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
616: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
617: try:
618: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
619: except: pass
620: try:
621: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
622: except: pass
623: try:
624: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
625: except: pass
626: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
627: try:
628: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
629: except:
630: docinfo['lang']=''
631:
632: return docinfo
633:
634:
635: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
636: """gets name info from the index.meta file at path or given by dom"""
637: if docinfo is None:
638: docinfo = {}
639:
640: if dom is None:
641: for x in range(cut):
642: path=getParentDir(path)
643: dom = self.getDomFromIndexMeta(path)
644:
645: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
646: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
647: return docinfo
648:
649: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
650: """parse texttool tag in index meta"""
651: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
652: if docinfo is None:
653: docinfo = {}
654: if docinfo.get('lang', None) is None:
655: docinfo['lang'] = '' # default keine Sprache gesetzt
656: if dom is None:
657: dom = self.getDomFromIndexMeta(url)
658:
659: archivePath = None
660: archiveName = None
661:
662: archiveNames = dom.xpath("//resource/name")
663: if archiveNames and (len(archiveNames) > 0):
664: archiveName = getTextFromNode(archiveNames[0])
665: else:
666: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
667:
668: archivePaths = dom.xpath("//resource/archive-path")
669: if archivePaths and (len(archivePaths) > 0):
670: archivePath = getTextFromNode(archivePaths[0])
671: # clean up archive path
672: if archivePath[0] != '/':
673: archivePath = '/' + archivePath
674: if archiveName and (not archivePath.endswith(archiveName)):
675: archivePath += "/" + archiveName
676: else:
677: # try to get archive-path from url
678: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
679: if (not url.startswith('http')):
680: archivePath = url.replace('index.meta', '')
681:
682: if archivePath is None:
683: # we balk without archive-path
684: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
685:
686: imageDirs = dom.xpath("//texttool/image")
687: if imageDirs and (len(imageDirs) > 0):
688: imageDir = getTextFromNode(imageDirs[0])
689:
690: else:
691: # we balk with no image tag / not necessary anymore because textmode is now standard
692: #raise IOError("No text-tool info in %s"%(url))
693: imageDir = ""
694: #xquery="//pb"
695: docinfo['imagePath'] = "" # keine Bilder
696: docinfo['imageURL'] = ""
697:
698: if imageDir and archivePath:
699: #print "image: ", imageDir, " archivepath: ", archivePath
700: imageDir = os.path.join(archivePath, imageDir)
701: imageDir = imageDir.replace("/mpiwg/online", '')
702: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
703: docinfo['imagePath'] = imageDir
704:
705: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
706:
707: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
708: if viewerUrls and (len(viewerUrls) > 0):
709: viewerUrl = getTextFromNode(viewerUrls[0])
710: docinfo['viewerURL'] = viewerUrl
711:
712: # old style text URL
713: textUrls = dom.xpath("//texttool/text")
714: if textUrls and (len(textUrls) > 0):
715: textUrl = getTextFromNode(textUrls[0])
716: if urlparse.urlparse(textUrl)[0] == "": #keine url
717: textUrl = os.path.join(archivePath, textUrl)
718: # fix URLs starting with /mpiwg/online
719: if textUrl.startswith("/mpiwg/online"):
720: textUrl = textUrl.replace("/mpiwg/online", '', 1)
721:
722: docinfo['textURL'] = textUrl
723:
724: # new style text-url-path
725: textUrls = dom.xpath("//texttool/text-url-path")
726: if textUrls and (len(textUrls) > 0):
727: textUrl = getTextFromNode(textUrls[0])
728: docinfo['textURLPath'] = textUrl
729: #if not docinfo['imagePath']:
730: # text-only, no page images
731: #docinfo = self.getNumTextPages(docinfo)
732:
733:
734: presentationUrls = dom.xpath("//texttool/presentation")
735: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
736: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
737:
738:
739: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
740: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
741: # durch den relativen Pfad auf die presentation infos
742: presentationPath = getTextFromNode(presentationUrls[0])
743: if url.endswith("index.meta"):
744: presentationUrl = url.replace('index.meta', presentationPath)
745: else:
746: presentationUrl = url + "/" + presentationPath
747:
748: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
749:
750: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
751:
752: return docinfo
753:
754:
755: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
756: """gets the bibliographical information from the preseantion entry in texttools
757: """
758: dom=self.getPresentationInfoXML(url)
759: try:
760: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
761: except:
762: pass
763: try:
764: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
765: except:
766: pass
767: try:
768: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
769: except:
770: pass
771: return docinfo
772:
773: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
774: """path ist the path to the images it assumes that the index.meta file is one level higher."""
775: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
776: if docinfo is None:
777: docinfo = {}
778: path=path.replace("/mpiwg/online","")
779: docinfo['imagePath'] = path
780: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
781:
782: pathorig=path
783: for x in range(cut):
784: path=getParentDir(path)
785: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
786: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
787: docinfo['imageURL'] = imageUrl
788:
789: #path ist the path to the images it assumes that the index.meta file is one level higher.
790: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
791: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
792: return docinfo
793:
794:
795: def getDocinfo(self, mode, url):
796: """returns docinfo depending on mode"""
797: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
798: # look for cached docinfo in session
799: if self.REQUEST.SESSION.has_key('docinfo'):
800: docinfo = self.REQUEST.SESSION['docinfo']
801: # check if its still current
802: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
803: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
804: return docinfo
805: # new docinfo
806: docinfo = {'mode': mode, 'url': url}
807: if mode=="texttool": #index.meta with texttool information
808: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
809: elif mode=="imagepath":
810: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
811: elif mode=="filepath":
812: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
813: else:
814: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
815: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
816:
817: # FIXME: fake texturlpath
818: if not docinfo.has_key('textURLPath'):
819: docinfo['textURLPath'] = None
820:
821: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
822: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
823: self.REQUEST.SESSION['docinfo'] = docinfo
824: return docinfo
825:
826: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
827: """returns pageinfo with the given parameters"""
828: pageinfo = {}
829: current = getInt(current)
830:
831: pageinfo['current'] = current
832: rows = int(rows or self.thumbrows)
833: pageinfo['rows'] = rows
834: cols = int(cols or self.thumbcols)
835: pageinfo['cols'] = cols
836: grpsize = cols * rows
837: pageinfo['groupsize'] = grpsize
838: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
839: # int(current / grpsize) * grpsize +1))
840: pageinfo['start'] = start
841: pageinfo['end'] = start + grpsize
842: if (docinfo is not None) and ('numPages' in docinfo):
843: np = int(docinfo['numPages'])
844: pageinfo['end'] = min(pageinfo['end'], np)
845: pageinfo['numgroups'] = int(np / grpsize)
846: if np % grpsize > 0:
847: pageinfo['numgroups'] += 1
848: pageinfo['viewMode'] = viewMode
849: pageinfo['tocMode'] = tocMode
850: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
851: pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','')
852: pageinfo['query'] = self.REQUEST.get('query','')
853: pageinfo['queryType'] = self.REQUEST.get('queryType','')
854: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
855: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
856: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
857: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
858: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
859: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
860:
861: toc = int (pageinfo['tocPN'])
862: pageinfo['textPages'] =int (toc)
863:
864:
865:
866: if 'tocSize_%s'%tocMode in docinfo:
867: tocSize = int(docinfo['tocSize_%s'%tocMode])
868: tocPageSize = int(pageinfo['tocPageSize'])
869: # cached toc
870: if tocSize%tocPageSize>0:
871: tocPages=tocSize/tocPageSize+1
872: else:
873: tocPages=tocSize/tocPageSize
874: pageinfo['tocPN'] = min (tocPages,toc)
875: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
876: pageinfo['sn'] =self.REQUEST.get('sn','')
877: return pageinfo
878:
879: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
880: """init document viewer"""
881: self.title=title
882: self.digilibBaseUrl = digilibBaseUrl
883: self.thumbrows = thumbrows
884: self.thumbcols = thumbcols
885: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
886: if RESPONSE is not None:
887: RESPONSE.redirect('manage_main')
888:
889: def manage_AddDocumentViewerForm(self):
890: """add the viewer form"""
891: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
892: return pt()
893:
894: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
895: """add the viewer"""
896: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
897: self._setObject(id,newObj)
898:
899: if RESPONSE is not None:
900: RESPONSE.redirect('manage_main')
901:
902: ## DocumentViewerTemplate class
903: class DocumentViewerTemplate(ZopePageTemplate):
904: """Template for document viewer"""
905: meta_type="DocumentViewer Template"
906:
907:
908: def manage_addDocumentViewerTemplateForm(self):
909: """Form for adding"""
910: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
911: return pt()
912:
913: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
914: REQUEST=None, submit=None):
915: "Add a Page Template with optional file content."
916:
917: self._setObject(id, DocumentViewerTemplate(id))
918: ob = getattr(self, id)
919: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
920: logging.info("txt %s:"%txt)
921: ob.pt_edit(txt,"text/html")
922: if title:
923: ob.pt_setTitle(title)
924: try:
925: u = self.DestinationURL()
926: except AttributeError:
927: u = REQUEST['URL1']
928:
929: u = "%s/%s" % (u, urllib.quote(id))
930: REQUEST.RESPONSE.redirect(u+'/manage_main')
931: return ''
932:
933:
934:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>