1: from OFS.Folder import Folder
2: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
4: from AccessControl import ClassSecurityInfo
5: from AccessControl import getSecurityManager
6: from Globals import package_home
7:
8: #from Ft.Xml import EMPTY_NAMESPACE, Parse
9: #import Ft.Xml.Domlette
10:
11: import xml.etree.ElementTree as ET
12:
13: import os.path
14: import sys
15: import urllib
16: import logging
17: import math
18: import urlparse
19: import re
20: import string
21:
22: from SrvTxtUtils import getInt, getText, getHttpData
23:
24: def logger(txt,method,txt2):
25: """logging"""
26: logging.info(txt+ txt2)
27:
28:
29: def serializeNode(node, encoding="utf-8"):
30: """returns a string containing node as XML"""
31: s = ET.tostring(node)
32:
33: # 4Suite:
34: # stream = cStringIO.StringIO()
35: # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
36: # s = stream.getvalue()
37: # stream.close()
38: return s
39:
40: def browserCheck(self):
41: """check the browsers request to find out the browser type"""
42: bt = {}
43: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
44: bt['ua'] = ua
45: bt['isIE'] = False
46: bt['isN4'] = False
47: bt['versFirefox']=""
48: bt['versIE']=""
49: bt['versSafariChrome']=""
50: bt['versOpera']=""
51:
52: if string.find(ua, 'MSIE') > -1:
53: bt['isIE'] = True
54: else:
55: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
56: # Safari oder Chrome identification
57: try:
58: nav = ua[string.find(ua, '('):]
59: nav1=ua[string.find(ua,')'):]
60: nav2=nav1[string.find(nav1,'('):]
61: nav3=nav2[string.find(nav2,')'):]
62: ie = string.split(nav, "; ")[1]
63: ie1 =string.split(nav1, " ")[2]
64: ie2 =string.split(nav3, " ")[1]
65: ie3 =string.split(nav3, " ")[2]
66: if string.find(ie3, "Safari") >-1:
67: bt['versSafariChrome']=string.split(ie2, "/")[1]
68: except: pass
69: # IE identification
70: try:
71: nav = ua[string.find(ua, '('):]
72: ie = string.split(nav, "; ")[1]
73: if string.find(ie, "MSIE") > -1:
74: bt['versIE'] = string.split(ie, " ")[1]
75: except:pass
76: # Firefox identification
77: try:
78: nav = ua[string.find(ua, '('):]
79: nav1=ua[string.find(ua,')'):]
80: if string.find(ie1, "Firefox") >-1:
81: nav5= string.split(ie1, "/")[1]
82: logging.debug("FIREFOX: %s"%(nav5))
83: bt['versFirefox']=nav5[0:3]
84: except:pass
85: #Opera identification
86: try:
87: if string.find(ua,"Opera") >-1:
88: nav = ua[string.find(ua, '('):]
89: nav1=nav[string.find(nav,')'):]
90: bt['versOpera']=string.split(nav1,"/")[2]
91: except:pass
92:
93: bt['isMac'] = string.find(ua, 'Macintosh') > -1
94: bt['isWin'] = string.find(ua, 'Windows') > -1
95: bt['isIEWin'] = bt['isIE'] and bt['isWin']
96: bt['isIEMac'] = bt['isIE'] and bt['isMac']
97: bt['staticHTML'] = False
98:
99: return bt
100:
101: def getParentPath(path, cnt=1):
102: """returns pathname shortened by cnt"""
103: # make sure path doesn't end with /
104: path = path.rstrip('/')
105: # split by /, shorten, and reassemble
106: return '/'.join(path.split('/')[0:-cnt])
107:
108:
109: ##
110: ## documentViewer class
111: ##
112: class documentViewer(Folder):
113: """document viewer"""
114: meta_type="Document viewer"
115:
116: security=ClassSecurityInfo()
117: manage_options=Folder.manage_options+(
118: {'label':'main config','action':'changeDocumentViewerForm'},
119: )
120:
121: metadataService = None
122: """MetaDataFolder instance"""
123:
124: # templates and forms
125: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
126: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
127: toc_text = PageTemplateFile('zpt/toc_text', globals())
128: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
129: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
130: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
131: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
132: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
133: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
134: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
135: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
136: head_main = PageTemplateFile('zpt/head_main', globals())
137: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
138: info_xml = PageTemplateFile('zpt/info_xml', globals())
139:
140:
141: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
142:
143:
144: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
145: """init document viewer"""
146: self.id=id
147: self.title=title
148: self.thumbcols = thumbcols
149: self.thumbrows = thumbrows
150: # authgroups is list of authorized groups (delimited by ,)
151: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
152: # create template folder so we can always use template.something
153:
154: templateFolder = Folder('template')
155: #self['template'] = templateFolder # Zope-2.12 style
156: self._setObject('template',templateFolder) # old style
157: try:
158: import MpdlXmlTextServer
159: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
160: #templateFolder['fulltextclient'] = xmlRpcClient
161: templateFolder._setObject('fulltextclient',textServer)
162: except Exception, e:
163: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
164:
165: try:
166: from Products.zogiLib.zogiLib import zogiLib
167: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
168: #templateFolder['zogilib'] = zogilib
169: templateFolder._setObject('zogilib',zogilib)
170: except Exception, e:
171: logging.error("Unable to create zogiLib for zogilib: "+str(e))
172:
173: try:
174: # assume MetaDataFolder instance is called metadata
175: self.metadataService = getattr(self, 'metadata')
176: except Exception, e:
177: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
178:
179:
180: # proxy text server methods to fulltextclient
181: def getTextPage(self, **args):
182: """get page"""
183: return self.template.fulltextclient.getTextPage(**args)
184:
185: def getOrigPages(self, **args):
186: """get page"""
187: return self.template.fulltextclient.getOrigPages(**args)
188:
189: def getOrigPagesNorm(self, **args):
190: """get page"""
191: return self.template.fulltextclient.getOrigPagesNorm(**args)
192:
193: def getQuery(self, **args):
194: """get query in search"""
195: return self.template.fulltextclient.getQuery(**args)
196:
197: def getSearch(self, **args):
198: """get search"""
199: return self.template.fulltextclient.getSearch(**args)
200:
201: def getGisPlaces(self, **args):
202: """get gis places"""
203: return self.template.fulltextclient.getGisPlaces(**args)
204:
205: def getAllGisPlaces(self, **args):
206: """get all gis places """
207: return self.template.fulltextclient.getAllGisPlaces(**args)
208:
209: def getTranslate(self, **args):
210: """get translate"""
211: return self.template.fulltextclient.getTranslate(**args)
212:
213: def getLemma(self, **args):
214: """get lemma"""
215: return self.template.fulltextclient.getLemma(**args)
216:
217: def getLemmaQuery(self, **args):
218: """get query"""
219: return self.template.fulltextclient.getLemmaQuery(**args)
220:
221: def getLex(self, **args):
222: """get lex"""
223: return self.template.fulltextclient.getLex(**args)
224:
225: def getToc(self, **args):
226: """get toc"""
227: return self.template.fulltextclient.getToc(**args)
228:
229: def getTocPage(self, **args):
230: """get tocpage"""
231: return self.template.fulltextclient.getTocPage(**args)
232:
233:
234: security.declareProtected('View','thumbs_rss')
235: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
236: '''
237: view it
238: @param mode: defines how to access the document behind url
239: @param url: url which contains display information
240: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
241:
242: '''
243: logging.debug("HHHHHHHHHHHHHH:load the rss")
244: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
245:
246: if not hasattr(self, 'template'):
247: # create template folder if it doesn't exist
248: self.manage_addFolder('template')
249:
250: if not self.digilibBaseUrl:
251: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
252:
253: docinfo = self.getDocinfo(mode=mode,url=url)
254: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
255: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
256: ''' ZDES '''
257: pt = getattr(self.template, 'thumbs_main_rss')
258:
259: if viewMode=="auto": # automodus gewaehlt
260: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
261: viewMode="text"
262: else:
263: viewMode="images"
264:
265: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
266:
267: security.declareProtected('View','index_html')
268: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
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 auto (text,images or auto)
274: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
275: """
276:
277: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
278:
279: if not hasattr(self, 'template'):
280: # this won't work
281: logging.error("template folder missing!")
282: return "ERROR: template folder missing!"
283:
284: if not getattr(self, 'digilibBaseUrl', None):
285: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
286:
287: docinfo = self.getDocinfo(mode=mode,url=url)
288:
289: if tocMode != "thumbs":
290: # get table of contents
291: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
292:
293: # auto viewMode: text_dict if text else images
294: if viewMode=="auto":
295: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
296: #texturl gesetzt und textViewer konfiguriert
297: viewMode="text_dict"
298: else:
299: viewMode="images"
300:
301: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode)
302:
303: if viewMode != 'images' and docinfo.get('textURLPath', None):
304: # get full text page
305: page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
306: pageinfo['textPage'] = page
307:
308: # get template /template/viewer_main
309: pt = getattr(self.template, 'viewer_main')
310: # and execute with parameters
311: return pt(docinfo=docinfo, pageinfo=pageinfo, viewMode=viewMode, mk=self.generateMarks(mk))
312:
313: def generateMarks(self,mk):
314: ret=""
315: if mk is None:
316: return ""
317: if not isinstance(mk, list):
318: mk=[mk]
319: for m in mk:
320: ret+="mk=%s"%m
321: return ret
322:
323:
324: def getBrowser(self):
325: """getBrowser the version of browser """
326: bt = browserCheck(self)
327: logging.debug("BROWSER VERSION: %s"%(bt))
328: return bt
329:
330: def findDigilibUrl(self):
331: """try to get the digilib URL from zogilib"""
332: url = self.template.zogilib.getDLBaseUrl()
333: return url
334:
335: def getDocumentViewerURL(self):
336: """returns the URL of this instance"""
337: return self.absolute_url()
338:
339: def getStyle(self, idx, selected, style=""):
340: """returns a string with the given style and append 'sel' if path == selected."""
341: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
342: if idx == selected:
343: return style + 'sel'
344: else:
345: return style
346:
347: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
348: """returns URL to documentviewer with parameter param set to val or from dict params"""
349: # copy existing request params
350: urlParams=self.REQUEST.form.copy()
351: # change single param
352: if param is not None:
353: if val is None:
354: if urlParams.has_key(param):
355: del urlParams[param]
356: else:
357: urlParams[param] = str(val)
358:
359: # change more params
360: if params is not None:
361: for k in params.keys():
362: v = params[k]
363: if v is None:
364: # val=None removes param
365: if urlParams.has_key(k):
366: del urlParams[k]
367:
368: else:
369: urlParams[k] = v
370:
371: # FIXME: does this belong here?
372: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
373: urlParams["mode"] = "imagepath"
374: urlParams["url"] = getParentPath(urlParams["url"])
375:
376: # quote values and assemble into query string (not escaping '/')
377: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
378: #ps = urllib.urlencode(urlParams)
379: if baseUrl is None:
380: baseUrl = self.REQUEST['URL1']
381:
382: url = "%s?%s"%(baseUrl, ps)
383: return url
384:
385:
386: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
387: """link to documentviewer with parameter param set to val"""
388: return self.getLink(param, val, params, baseUrl, '&')
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: if not self.REQUEST.SESSION.has_key(optionName):
403: # not in session -- initial
404: opt = {'lastState': newState, 'state': initialState}
405: else:
406: opt = self.REQUEST.SESSION.get(optionName)
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: path=getParentPath(path)
443:
444: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
445:
446: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
447:
448: txt = getHttpData(infoUrl)
449: if txt is None:
450: raise IOError("Unable to get dir-info from %s"%(infoUrl))
451:
452: dom = ET.fromstring(txt)
453: #dom = Parse(txt)
454: size=getText(dom.find("size"))
455: #sizes=dom.xpath("//dir/size")
456: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size)
457:
458: if size:
459: docinfo['numPages'] = int(size)
460: else:
461: docinfo['numPages'] = 0
462:
463: # TODO: produce and keep list of image names and numbers
464:
465: return docinfo
466:
467: def getIndexMetaPath(self,url):
468: """gib nur den Pfad zurueck"""
469: regexp = re.compile(r".*(experimental|permanent)/(.*)")
470: regpath = regexp.match(url)
471: if (regpath==None):
472: return ""
473: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
474: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
475:
476:
477:
478: def getIndexMetaUrl(self,url):
479: """returns utr of index.meta document at url"""
480:
481: metaUrl = None
482: if url.startswith("http://"):
483: # real URL
484: metaUrl = url
485: else:
486: # online path
487: server=self.digilibBaseUrl+"/servlet/Texter?fn="
488: metaUrl=server+url.replace("/mpiwg/online","")
489: if not metaUrl.endswith("index.meta"):
490: metaUrl += "/index.meta"
491:
492: return metaUrl
493:
494: def getDomFromIndexMeta(self, url):
495: """get dom from index meta"""
496: dom = None
497: metaUrl = self.getIndexMetaUrl(url)
498:
499: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
500: txt=getHttpData(metaUrl)
501: if txt is None:
502: raise IOError("Unable to read index meta from %s"%(url))
503:
504: dom = ET.fromstring(txt)
505: #dom = Parse(txt)
506: return dom
507:
508: def getPresentationInfoXML(self, url):
509: """returns dom of info.xml document at url"""
510: dom = None
511: metaUrl = None
512: if url.startswith("http://"):
513: # real URL
514: metaUrl = url
515: else:
516: # online path
517: server=self.digilibBaseUrl+"/servlet/Texter?fn="
518: metaUrl=server+url.replace("/mpiwg/online","")
519:
520: txt=getHttpData(metaUrl)
521: if txt is None:
522: raise IOError("Unable to read infoXMLfrom %s"%(url))
523:
524: dom = ET.fromstring(txt)
525: #dom = Parse(txt)
526: return dom
527:
528:
529: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
530: """gets authorization info from the index.meta file at path or given by dom"""
531: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
532:
533: access = None
534:
535: if docinfo is None:
536: docinfo = {}
537:
538: if dom is None:
539: for x in range(cut):
540: path=getParentPath(path)
541: dom = self.getDomFromIndexMeta(path)
542:
543: acc = dom.find(".//access-conditions/access")
544: if acc is not None:
545: acctype = acc.get('type')
546: #acctype = dom.xpath("//access-conditions/access/@type")
547: if acctype:
548: access=acctype
549: if access in ['group', 'institution']:
550: access = dom.find(".//access-conditions/access/name").text.lower()
551:
552: docinfo['accessType'] = access
553: return docinfo
554:
555:
556: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
557: """gets bibliographical info from the index.meta file at path or given by dom"""
558: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
559:
560: if docinfo is None:
561: docinfo = {}
562:
563: if dom is None:
564: for x in range(cut):
565: path=getParentDir(path)
566: dom = self.getDomFromIndexMeta(path)
567:
568: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
569:
570: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
571: if self.metadataService is not None:
572: # put all raw bib fields in dict "bib"
573: bib = self.metadataService.getBibData(dom=dom)
574: docinfo['bib'] = bib
575: bibtype = bib.get('@type', None)
576: docinfo['bib_type'] = bibtype
577: # also store DC metadata for convenience
578: dc = self.metadataService.getDCMappedData(bib)
579: docinfo['creator'] = dc.get('creator',None)
580: docinfo['title'] = dc.get('title',None)
581: docinfo['date'] = dc.get('date',None)
582: else:
583: logging.error("MetadataService not found!")
584: return docinfo
585:
586:
587: # TODO: is this needed?
588: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
589: """gets name info from the index.meta file at path or given by dom"""
590: if docinfo is None:
591: docinfo = {}
592:
593: if dom is None:
594: for x in range(cut):
595: path=getParentPath(path)
596: dom = self.getDomFromIndexMeta(path)
597:
598: docinfo['name']=getText(dom.find("name"))
599: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
600: return docinfo
601:
602:
603: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
604: """parse texttool tag in index meta"""
605: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
606: if docinfo is None:
607: docinfo = {}
608: if docinfo.get('lang', None) is None:
609: docinfo['lang'] = '' # default keine Sprache gesetzt
610: if dom is None:
611: dom = self.getDomFromIndexMeta(url)
612:
613: texttool = self.metadata.getTexttoolData(dom=dom)
614:
615: archivePath = None
616: archiveName = None
617:
618: archiveName = getText(dom.find("name"))
619: if not archiveName:
620: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
621:
622: archivePath = getText(dom.find("archive-path"))
623: if archivePath:
624: # clean up archive path
625: if archivePath[0] != '/':
626: archivePath = '/' + archivePath
627: if archiveName and (not archivePath.endswith(archiveName)):
628: archivePath += "/" + archiveName
629: else:
630: # try to get archive-path from url
631: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
632: if (not url.startswith('http')):
633: archivePath = url.replace('index.meta', '')
634:
635: if archivePath is None:
636: # we balk without archive-path
637: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
638:
639: imageDir = texttool.get('image', None)
640:
641: if not imageDir:
642: # we balk with no image tag / not necessary anymore because textmode is now standard
643: #raise IOError("No text-tool info in %s"%(url))
644: imageDir = ""
645: #xquery="//pb"
646: docinfo['imagePath'] = "" # keine Bilder
647: docinfo['imageURL'] = ""
648:
649: if imageDir and archivePath:
650: #print "image: ", imageDir, " archivepath: ", archivePath
651: imageDir = os.path.join(archivePath, imageDir)
652: imageDir = imageDir.replace("/mpiwg/online", '')
653: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
654: docinfo['imagePath'] = imageDir
655:
656: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
657:
658: viewerUrl = texttool.get('digiliburlprefix', None)
659: if viewerUrl:
660: docinfo['viewerURL'] = viewerUrl
661:
662: # old style text URL
663: textUrl = texttool.get('text', None)
664: if textUrl:
665: if urlparse.urlparse(textUrl)[0] == "": #keine url
666: textUrl = os.path.join(archivePath, textUrl)
667: # fix URLs starting with /mpiwg/online
668: if textUrl.startswith("/mpiwg/online"):
669: textUrl = textUrl.replace("/mpiwg/online", '', 1)
670:
671: docinfo['textURL'] = textUrl
672:
673: # new style text-url-path
674: textUrl = texttool.get('text-url-path', None)
675: if textUrl:
676: docinfo['textURLPath'] = textUrl
677: textUrlkurz = string.split(textUrl, ".")[0]
678: docinfo['textURLPathkurz'] = textUrlkurz
679: #if not docinfo['imagePath']:
680: # text-only, no page images
681: #docinfo = self.getNumTextPages(docinfo)
682:
683: # get bib info
684: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
685: # TODO: is this needed here?
686: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
687:
688: # TODO: what to do with presentation?
689: presentationUrl = texttool.get('presentation', None)
690: if presentationUrl: # ueberschreibe diese durch presentation informationen
691: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
692: # durch den relativen Pfad auf die presentation infos
693: presentationPath = presentationUrl
694: if url.endswith("index.meta"):
695: presentationUrl = url.replace('index.meta', presentationPath)
696: else:
697: presentationUrl = url + "/" + presentationPath
698:
699: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
700:
701: # get authorization
702: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
703:
704: return docinfo
705:
706:
707: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
708: """gets the bibliographical information from the preseantion entry in texttools
709: """
710: dom=self.getPresentationInfoXML(url)
711: docinfo['author']=getText(dom.find(".//author"))
712: docinfo['title']=getText(dom.find(".//title"))
713: docinfo['year']=getText(dom.find(".//date"))
714: return docinfo
715:
716: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
717: """path ist the path to the images it assumes that the index.meta file is one level higher."""
718: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
719: if docinfo is None:
720: docinfo = {}
721: path=path.replace("/mpiwg/online","")
722: docinfo['imagePath'] = path
723: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
724:
725: pathorig=path
726: for x in range(cut):
727: path=getParentPath(path)
728: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
729: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
730: docinfo['imageURL'] = imageUrl
731:
732: #TODO: use getDocinfoFromIndexMeta
733: #path ist the path to the images it assumes that the index.meta file is one level higher.
734: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
735: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
736: return docinfo
737:
738:
739: def OLDgetDocinfo(self, mode, url):
740: """returns docinfo depending on mode"""
741: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
742: # look for cached docinfo in session
743: if self.REQUEST.SESSION.has_key('docinfo'):
744: docinfo = self.REQUEST.SESSION['docinfo']
745: # check if its still current
746: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
747: logging.debug("documentViewer (getdocinfo) docinfo in session. keys=%s"%docinfo.keys())
748: return docinfo
749:
750: # new docinfo
751: docinfo = {'mode': mode, 'url': url}
752: # add self url
753: docinfo['viewerUrl'] = self.getDocumentViewerURL()
754: if mode=="texttool":
755: # index.meta with texttool information
756: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
757: elif mode=="imagepath":
758: # folder with images, index.meta optional
759: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
760: elif mode=="filepath":
761: # filename
762: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
763: else:
764: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
765: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
766:
767: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
768: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
769: # store in session
770: self.REQUEST.SESSION['docinfo'] = docinfo
771: return docinfo
772:
773:
774: def getDocinfo(self, mode, url):
775: """returns docinfo depending on mode"""
776: logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
777: # look for cached docinfo in session
778: if self.REQUEST.SESSION.has_key('docinfo'):
779: docinfo = self.REQUEST.SESSION['docinfo']
780: # check if its still current
781: if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
782: logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
783: return docinfo
784:
785: # new docinfo
786: docinfo = {'mode': mode, 'url': url}
787: # add self url
788: docinfo['viewerUrl'] = self.getDocumentViewerURL()
789: # get index.meta DOM
790: docUrl = None
791: metaDom = None
792: if mode=="texttool":
793: # url points to document dir or index.meta
794: metaDom = self.metadataService.getDomFromPathOrUrl(url)
795: docUrl = url.replace('/index.meta', '')
796: if metaDom is None:
797: raise IOError("Unable to find index.meta for mode=texttool!")
798:
799: elif mode=="imagepath":
800: # url points to folder with images, index.meta optional
801: # asssume index.meta in parent dir
802: docUrl = getParentPath(url)
803: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
804:
805: elif mode=="filepath":
806: # url points to image file, index.meta optional
807: # asssume index.meta is two path segments up
808: docUrl = getParentPath(url, 2)
809: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
810:
811: else:
812: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
813: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
814:
815: docinfo['documentUrl'] = docUrl
816: # process index.meta contents
817: if metaDom is not None:
818: # document directory name and path
819: resource = self.metadataService.getResourceData(dom=metaDom)
820: if resource:
821: docinfo = self.getDocinfoFromResource(docinfo, resource)
822:
823: # texttool info
824: texttool = self.metadataService.getTexttoolData(dom=metaDom)
825: if texttool:
826: docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
827:
828: # bib info
829: bib = self.metadataService.getBibData(dom=metaDom)
830: if bib:
831: docinfo = self.getDocinfoFromBib(docinfo, bib)
832:
833: # auth info
834: access = self.metadataService.getAccessData(dom=metaDom)
835: if access:
836: docinfo = self.getDocinfoFromAccess(docinfo, access)
837:
838: # image path
839: if mode != 'texttool':
840: # override image path from texttool
841: docinfo['imagePath'] = url
842:
843: # number of images from digilib
844: if docinfo.get('imagePath', None):
845: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
846: docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
847:
848: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
849: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
850: # store in session
851: self.REQUEST.SESSION['docinfo'] = docinfo
852: return docinfo
853:
854: def getDocinfoFromResource(self, docinfo, resource):
855: """reads contents of resource element into docinfo"""
856: docName = resource.get('name', None)
857: docinfo['documentName'] = docName
858: docPath = resource.get('archive-path', None)
859: if docPath:
860: # clean up document path
861: if docPath[0] != '/':
862: docPath = '/' + docPath
863:
864: if docName and (not docPath.endswith(docName)):
865: docPath += "/" + docName
866:
867: else:
868: # use docUrl as docPath
869: docUrl = docinfo['documentURL']
870: if not docUrl.startswith('http:'):
871: docPath = docUrl
872:
873: docinfo['documentPath'] = docPath
874: return docinfo
875:
876: def getDocinfoFromTexttool(self, docinfo, texttool):
877: """reads contents of texttool element into docinfo"""
878: # image dir
879: imageDir = texttool.get('image', None)
880: docPath = docinfo.get('documentPath', None)
881: if imageDir and docPath:
882: #print "image: ", imageDir, " archivepath: ", archivePath
883: imageDir = os.path.join(docPath, imageDir)
884: imageDir = imageDir.replace('/mpiwg/online', '', 1)
885: docinfo['imagePath'] = imageDir
886:
887: # old style text URL
888: textUrl = texttool.get('text', None)
889: if textUrl and docPath:
890: if urlparse.urlparse(textUrl)[0] == "": #keine url
891: textUrl = os.path.join(docPath, textUrl)
892: # fix URLs starting with /mpiwg/online
893: textUrl = textUrl.replace('/mpiwg/online', '', 1)
894:
895: docinfo['textURL'] = textUrl
896:
897: # new style text-url-path
898: textUrl = texttool.get('text-url-path', None)
899: if textUrl:
900: docinfo['textURLPath'] = textUrl
901: #TODO: ugly:
902: #textUrlkurz = string.split(textUrl, ".")[0]
903: #docinfo['textURLPathkurz'] = textUrlkurz
904:
905: # old presentation stuff
906: presentation = texttool.get('presentation', None)
907: if presentation and docPath:
908: docinfo['presentationPath'] = os.path.join(docPath, presentation)
909:
910: return docinfo
911:
912: def getDocinfoFromBib(self, docinfo, bib):
913: """reads contents of bib element into docinfo"""
914: # put all raw bib fields in dict "bib"
915: docinfo['bib'] = bib
916: bibtype = bib.get('@type', None)
917: docinfo['bibType'] = bibtype
918: # also store DC metadata for convenience
919: dc = self.metadataService.getDCMappedData(bib)
920: docinfo['creator'] = dc.get('creator',None)
921: docinfo['title'] = dc.get('title',None)
922: docinfo['date'] = dc.get('date',None)
923: return docinfo
924:
925: def getDocinfoFromAccess(self, docinfo, acc):
926: """reads contents of access element into docinfo"""
927: #TODO: also read resource type
928: try:
929: acctype = accc['@attr']['type']
930: if acctype:
931: access=acctype
932: if access in ['group', 'institution']:
933: access = acc['name'].lower()
934:
935: docinfo['accessType'] = access
936:
937: except:
938: pass
939:
940: return docinfo
941:
942: def getDocinfoFromDigilib(self, docinfo, path):
943: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
944: # fetch data
945: txt = getHttpData(infoUrl)
946: if not txt:
947: logging.error("Unable to get dir-info from %s"%(infoUrl))
948: return docinfo
949:
950: dom = ET.fromstring(txt)
951: size = getText(dom.find("size"))
952: logging.debug("getDocinfoFromDigilib: size=%s"%size)
953: if size:
954: docinfo['numPages'] = int(size)
955: else:
956: docinfo['numPages'] = 0
957:
958: # TODO: produce and keep list of image names and numbers
959: return docinfo
960:
961:
962: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
963: """returns pageinfo with the given parameters"""
964: pageinfo = {}
965: current = getInt(current)
966:
967: pageinfo['current'] = current
968: rows = int(rows or self.thumbrows)
969: pageinfo['rows'] = rows
970: cols = int(cols or self.thumbcols)
971: pageinfo['cols'] = cols
972: grpsize = cols * rows
973: pageinfo['groupsize'] = grpsize
974: # what does this do?
975: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
976: # int(current / grpsize) * grpsize +1))
977: pageinfo['start'] = start
978: pageinfo['end'] = start + grpsize
979: if (docinfo is not None) and ('numPages' in docinfo):
980: np = int(docinfo['numPages'])
981: pageinfo['end'] = min(pageinfo['end'], np)
982: pageinfo['numgroups'] = int(np / grpsize)
983: if np % grpsize > 0:
984: pageinfo['numgroups'] += 1
985:
986: pageinfo['viewMode'] = viewMode
987: pageinfo['tocMode'] = tocMode
988: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
989: #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
990: pageinfo['query'] = self.REQUEST.get('query','')
991: pageinfo['queryType'] = self.REQUEST.get('queryType','')
992: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
993: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
994: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
995: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
996: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
997: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
998: # WTF?:
999: toc = int(pageinfo['tocPN'])
1000: pageinfo['textPages'] =int(toc)
1001:
1002: # What does this do?
1003: if 'tocSize_%s'%tocMode in docinfo:
1004: tocSize = int(docinfo['tocSize_%s'%tocMode])
1005: tocPageSize = int(pageinfo['tocPageSize'])
1006: # cached toc
1007: if tocSize%tocPageSize>0:
1008: tocPages=tocSize/tocPageSize+1
1009: else:
1010: tocPages=tocSize/tocPageSize
1011:
1012: pageinfo['tocPN'] = min(tocPages,toc)
1013:
1014: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1015: pageinfo['sn'] =self.REQUEST.get('sn','')
1016: return pageinfo
1017:
1018:
1019: security.declareProtected('View management screens','changeDocumentViewerForm')
1020: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
1021:
1022: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1023: """init document viewer"""
1024: self.title=title
1025: self.digilibBaseUrl = digilibBaseUrl
1026: self.thumbrows = thumbrows
1027: self.thumbcols = thumbcols
1028: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1029: try:
1030: # assume MetaDataFolder instance is called metadata
1031: self.metadataService = getattr(self, 'metadata')
1032: except Exception, e:
1033: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
1034:
1035: if RESPONSE is not None:
1036: RESPONSE.redirect('manage_main')
1037:
1038: def manage_AddDocumentViewerForm(self):
1039: """add the viewer form"""
1040: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1041: return pt()
1042:
1043: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1044: """add the viewer"""
1045: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1046: self._setObject(id,newObj)
1047:
1048: if RESPONSE is not None:
1049: RESPONSE.redirect('manage_main')
1050:
1051: ## DocumentViewerTemplate class
1052: class DocumentViewerTemplate(ZopePageTemplate):
1053: """Template for document viewer"""
1054: meta_type="DocumentViewer Template"
1055:
1056:
1057: def manage_addDocumentViewerTemplateForm(self):
1058: """Form for adding"""
1059: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
1060: return pt()
1061:
1062: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
1063: REQUEST=None, submit=None):
1064: "Add a Page Template with optional file content."
1065:
1066: self._setObject(id, DocumentViewerTemplate(id))
1067: ob = getattr(self, id)
1068: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1069: logging.info("txt %s:"%txt)
1070: ob.pt_edit(txt,"text/html")
1071: if title:
1072: ob.pt_setTitle(title)
1073: try:
1074: u = self.DestinationURL()
1075: except AttributeError:
1076: u = REQUEST['URL1']
1077:
1078: u = "%s/%s" % (u, urllib.quote(id))
1079: REQUEST.RESPONSE.redirect(u+'/manage_main')
1080: return ''
1081:
1082:
1083:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>