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