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