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: logging.debug("BROWSER VERSION: %s"%(bt))
323: return bt
324:
325: def findDigilibUrl(self):
326: """try to get the digilib URL from zogilib"""
327: url = self.template.zogilib.getDLBaseUrl()
328: return url
329:
330: def getDocumentViewerURL(self):
331: """returns the URL of this instance"""
332: return self.absolute_url()
333:
334: def getStyle(self, idx, selected, style=""):
335: """returns a string with the given style and append 'sel' if path == selected."""
336: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
337: if idx == selected:
338: return style + 'sel'
339: else:
340: return style
341:
342: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
343: """returns URL to documentviewer with parameter param set to val or from dict params"""
344: # copy existing request params
345: urlParams=self.REQUEST.form.copy()
346: # change single param
347: if param is not None:
348: if val is None:
349: if urlParams.has_key(param):
350: del urlParams[param]
351: else:
352: urlParams[param] = str(val)
353:
354: # change more params
355: if params is not None:
356: for k in params.keys():
357: v = params[k]
358: if v is None:
359: # val=None removes param
360: if urlParams.has_key(k):
361: del urlParams[k]
362:
363: else:
364: urlParams[k] = v
365:
366: # FIXME: does this belong here?
367: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
368: urlParams["mode"] = "imagepath"
369: urlParams["url"] = getParentDir(urlParams["url"])
370:
371: # quote values and assemble into query string (not escaping '/')
372: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
373: #ps = urllib.urlencode(urlParams)
374: if baseUrl is None:
375: baseUrl = self.REQUEST['URL1']
376:
377: url = "%s?%s"%(baseUrl, ps)
378: return url
379:
380:
381: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
382: """link to documentviewer with parameter param set to val"""
383: return self.getLink(param, val, params, baseUrl, '&')
384:
385: def getInfo_xml(self,url,mode):
386: """returns info about the document as XML"""
387:
388: if not self.digilibBaseUrl:
389: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
390:
391: docinfo = self.getDocinfo(mode=mode,url=url)
392: pt = getattr(self.template, 'info_xml')
393: return pt(docinfo=docinfo)
394:
395: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
396: """returns new option state"""
397: if not self.REQUEST.SESSION.has_key(optionName):
398: # not in session -- initial
399: opt = {'lastState': newState, 'state': initialState}
400: else:
401: opt = self.REQUEST.SESSION.get(optionName)
402: if opt['lastState'] != newState:
403: # state in session has changed -- toggle
404: opt['state'] = not opt['state']
405: opt['lastState'] = newState
406:
407: self.REQUEST.SESSION[optionName] = opt
408: return opt['state']
409:
410: def isAccessible(self, docinfo):
411: """returns if access to the resource is granted"""
412: access = docinfo.get('accessType', None)
413: logging.debug("documentViewer (accessOK) access type %s"%access)
414: if access is not None and access == 'free':
415: logging.debug("documentViewer (accessOK) access is free")
416: return True
417: elif access is None or access in self.authgroups:
418: # only local access -- only logged in users
419: user = getSecurityManager().getUser()
420: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
421: if user is not None:
422: #print "user: ", user
423: return (user.getUserName() != "Anonymous User")
424: else:
425: return False
426:
427: logging.error("documentViewer (accessOK) unknown access type %s"%access)
428: return False
429:
430:
431: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
432: """gibt param von dlInfo aus"""
433: if docinfo is None:
434: docinfo = {}
435:
436: for x in range(cut):
437:
438: path=getParentDir(path)
439:
440: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
441:
442: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
443:
444: txt = getHttpData(infoUrl)
445: if txt is None:
446: raise IOError("Unable to get dir-info from %s"%(infoUrl))
447:
448: dom = Parse(txt)
449: sizes=dom.xpath("//dir/size")
450: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
451:
452: if sizes:
453: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
454: else:
455: docinfo['numPages'] = 0
456:
457: # TODO: produce and keep list of image names and numbers
458:
459: return docinfo
460:
461: def getIndexMetaPath(self,url):
462: """gib nur den Pfad zurueck"""
463: regexp = re.compile(r".*(experimental|permanent)/(.*)")
464: regpath = regexp.match(url)
465: if (regpath==None):
466: return ""
467: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
468: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
469:
470:
471:
472: def getIndexMetaUrl(self,url):
473: """returns utr of index.meta document at url"""
474:
475: metaUrl = None
476: if url.startswith("http://"):
477: # real URL
478: metaUrl = url
479: else:
480: # online path
481: server=self.digilibBaseUrl+"/servlet/Texter?fn="
482: metaUrl=server+url.replace("/mpiwg/online","")
483: if not metaUrl.endswith("index.meta"):
484: metaUrl += "/index.meta"
485:
486: return metaUrl
487:
488: def getDomFromIndexMeta(self, url):
489: """get dom from index meta"""
490: dom = None
491: metaUrl = self.getIndexMetaUrl(url)
492:
493: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
494: txt=getHttpData(metaUrl)
495: if txt is None:
496: raise IOError("Unable to read index meta from %s"%(url))
497:
498: dom = Parse(txt)
499: return dom
500:
501: def getPresentationInfoXML(self, url):
502: """returns dom of info.xml document at url"""
503: dom = None
504: metaUrl = None
505: if url.startswith("http://"):
506: # real URL
507: metaUrl = url
508: else:
509: # online path
510: server=self.digilibBaseUrl+"/servlet/Texter?fn="
511: metaUrl=server+url.replace("/mpiwg/online","")
512:
513: txt=getHttpData(metaUrl)
514: if txt is None:
515: raise IOError("Unable to read infoXMLfrom %s"%(url))
516:
517: dom = Parse(txt)
518: return dom
519:
520:
521: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
522: """gets authorization info from the index.meta file at path or given by dom"""
523: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
524:
525: access = None
526:
527: if docinfo is None:
528: docinfo = {}
529:
530: if dom is None:
531: for x in range(cut):
532: path=getParentDir(path)
533: dom = self.getDomFromIndexMeta(path)
534:
535: acctype = dom.xpath("//access-conditions/access/@type")
536: if acctype and (len(acctype)>0):
537: access=acctype[0].value
538: if access in ['group', 'institution']:
539: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
540:
541: docinfo['accessType'] = access
542: return docinfo
543:
544:
545: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
546: """gets bibliographical info from the index.meta file at path or given by dom"""
547: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
548:
549: if docinfo is None:
550: docinfo = {}
551:
552: if dom is None:
553: for x in range(cut):
554: path=getParentDir(path)
555: dom = self.getDomFromIndexMeta(path)
556:
557: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
558:
559: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
560: # put in all raw bib fields as dict "bib"
561: bib = dom.xpath("//bib/*")
562: if bib and len(bib)>0:
563: bibinfo = {}
564: for e in bib:
565: bibinfo[e.localName] = getTextFromNode(e)
566: docinfo['bib'] = bibinfo
567:
568: # extract some fields (author, title, year) according to their mapping
569: metaData=self.metadata.main.meta.bib
570: bibtype=dom.xpath("//bib/@type")
571: if bibtype and (len(bibtype)>0):
572: bibtype=bibtype[0].value
573: else:
574: bibtype="generic"
575:
576: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
577: docinfo['bib_type'] = bibtype
578: bibmap=metaData.generateMappingForType(bibtype)
579: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
580: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
581: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
582: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
583: try:
584: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
585: except: pass
586: try:
587: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
588: except: pass
589: try:
590: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
591: except: pass
592: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
593: try:
594: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
595: except:
596: docinfo['lang']=''
597:
598: return docinfo
599:
600:
601: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
602: """gets name info from the index.meta file at path or given by dom"""
603: if docinfo is None:
604: docinfo = {}
605:
606: if dom is None:
607: for x in range(cut):
608: path=getParentDir(path)
609: dom = self.getDomFromIndexMeta(path)
610:
611: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
612: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
613: return docinfo
614:
615: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
616: """parse texttool tag in index meta"""
617: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
618: if docinfo is None:
619: docinfo = {}
620: if docinfo.get('lang', None) is None:
621: docinfo['lang'] = '' # default keine Sprache gesetzt
622: if dom is None:
623: dom = self.getDomFromIndexMeta(url)
624:
625: archivePath = None
626: archiveName = None
627:
628: archiveNames = dom.xpath("//resource/name")
629: if archiveNames and (len(archiveNames) > 0):
630: archiveName = getTextFromNode(archiveNames[0])
631: else:
632: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
633:
634: archivePaths = dom.xpath("//resource/archive-path")
635: if archivePaths and (len(archivePaths) > 0):
636: archivePath = getTextFromNode(archivePaths[0])
637: # clean up archive path
638: if archivePath[0] != '/':
639: archivePath = '/' + archivePath
640: if archiveName and (not archivePath.endswith(archiveName)):
641: archivePath += "/" + archiveName
642: else:
643: # try to get archive-path from url
644: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
645: if (not url.startswith('http')):
646: archivePath = url.replace('index.meta', '')
647:
648: if archivePath is None:
649: # we balk without archive-path
650: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
651:
652: imageDirs = dom.xpath("//texttool/image")
653: if imageDirs and (len(imageDirs) > 0):
654: imageDir = getTextFromNode(imageDirs[0])
655:
656: else:
657: # we balk with no image tag / not necessary anymore because textmode is now standard
658: #raise IOError("No text-tool info in %s"%(url))
659: imageDir = ""
660: #xquery="//pb"
661: docinfo['imagePath'] = "" # keine Bilder
662: docinfo['imageURL'] = ""
663:
664: if imageDir and archivePath:
665: #print "image: ", imageDir, " archivepath: ", archivePath
666: imageDir = os.path.join(archivePath, imageDir)
667: imageDir = imageDir.replace("/mpiwg/online", '')
668: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
669: docinfo['imagePath'] = imageDir
670:
671: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
672:
673: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
674: if viewerUrls and (len(viewerUrls) > 0):
675: viewerUrl = getTextFromNode(viewerUrls[0])
676: docinfo['viewerURL'] = viewerUrl
677:
678: # old style text URL
679: textUrls = dom.xpath("//texttool/text")
680: if textUrls and (len(textUrls) > 0):
681: textUrl = getTextFromNode(textUrls[0])
682: if urlparse.urlparse(textUrl)[0] == "": #keine url
683: textUrl = os.path.join(archivePath, textUrl)
684: # fix URLs starting with /mpiwg/online
685: if textUrl.startswith("/mpiwg/online"):
686: textUrl = textUrl.replace("/mpiwg/online", '', 1)
687:
688: docinfo['textURL'] = textUrl
689:
690: # new style text-url-path
691: textUrls = dom.xpath("//texttool/text-url-path")
692: if textUrls and (len(textUrls) > 0):
693: textUrl = getTextFromNode(textUrls[0])
694: docinfo['textURLPath'] = textUrl
695: #if not docinfo['imagePath']:
696: # text-only, no page images
697: #docinfo = self.getNumTextPages(docinfo)
698:
699:
700: presentationUrls = dom.xpath("//texttool/presentation")
701: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
702: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
703:
704:
705: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
706: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
707: # durch den relativen Pfad auf die presentation infos
708: presentationPath = getTextFromNode(presentationUrls[0])
709: if url.endswith("index.meta"):
710: presentationUrl = url.replace('index.meta', presentationPath)
711: else:
712: presentationUrl = url + "/" + presentationPath
713:
714: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
715:
716: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
717:
718: return docinfo
719:
720:
721: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
722: """gets the bibliographical information from the preseantion entry in texttools
723: """
724: dom=self.getPresentationInfoXML(url)
725: try:
726: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
727: except:
728: pass
729: try:
730: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
731: except:
732: pass
733: try:
734: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
735: except:
736: pass
737: return docinfo
738:
739: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
740: """path ist the path to the images it assumes that the index.meta file is one level higher."""
741: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
742: if docinfo is None:
743: docinfo = {}
744: path=path.replace("/mpiwg/online","")
745: docinfo['imagePath'] = path
746: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
747:
748: pathorig=path
749: for x in range(cut):
750: path=getParentDir(path)
751: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
752: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
753: docinfo['imageURL'] = imageUrl
754:
755: #path ist the path to the images it assumes that the index.meta file is one level higher.
756: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
757: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
758: return docinfo
759:
760:
761: def getDocinfo(self, mode, url):
762: """returns docinfo depending on mode"""
763: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
764: # look for cached docinfo in session
765: if self.REQUEST.SESSION.has_key('docinfo'):
766: docinfo = self.REQUEST.SESSION['docinfo']
767: # check if its still current
768: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
769: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
770: return docinfo
771: # new docinfo
772: docinfo = {'mode': mode, 'url': url}
773: if mode=="texttool": #index.meta with texttool information
774: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
775: elif mode=="imagepath":
776: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
777: elif mode=="filepath":
778: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
779: else:
780: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
781: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
782:
783: # FIXME: fake texturlpath
784: if not docinfo.has_key('textURLPath'):
785: docinfo['textURLPath'] = None
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):
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','reg')
817: pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','')
818: pageinfo['query'] = self.REQUEST.get('query','')
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:
827: toc = int (pageinfo['tocPN'])
828: pageinfo['textPages'] =int (toc)
829:
830:
831:
832: if 'tocSize_%s'%tocMode in docinfo:
833: tocSize = int(docinfo['tocSize_%s'%tocMode])
834: tocPageSize = int(pageinfo['tocPageSize'])
835: # cached toc
836: if tocSize%tocPageSize>0:
837: tocPages=tocSize/tocPageSize+1
838: else:
839: tocPages=tocSize/tocPageSize
840: pageinfo['tocPN'] = min (tocPages,toc)
841: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
842: pageinfo['sn'] =self.REQUEST.get('sn','')
843: return pageinfo
844:
845: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
846: """init document viewer"""
847: self.title=title
848: self.digilibBaseUrl = digilibBaseUrl
849: self.thumbrows = thumbrows
850: self.thumbcols = thumbcols
851: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
852: if RESPONSE is not None:
853: RESPONSE.redirect('manage_main')
854:
855: def manage_AddDocumentViewerForm(self):
856: """add the viewer form"""
857: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
858: return pt()
859:
860: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
861: """add the viewer"""
862: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
863: self._setObject(id,newObj)
864:
865: if RESPONSE is not None:
866: RESPONSE.redirect('manage_main')
867:
868: ## DocumentViewerTemplate class
869: class DocumentViewerTemplate(ZopePageTemplate):
870: """Template for document viewer"""
871: meta_type="DocumentViewer Template"
872:
873:
874: def manage_addDocumentViewerTemplateForm(self):
875: """Form for adding"""
876: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
877: return pt()
878:
879: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
880: REQUEST=None, submit=None):
881: "Add a Page Template with optional file content."
882:
883: self._setObject(id, DocumentViewerTemplate(id))
884: ob = getattr(self, id)
885: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
886: logging.info("txt %s:"%txt)
887: ob.pt_edit(txt,"text/html")
888: if title:
889: ob.pt_setTitle(title)
890: try:
891: u = self.DestinationURL()
892: except AttributeError:
893: u = REQUEST['URL1']
894:
895: u = "%s/%s" % (u, urllib.quote(id))
896: REQUEST.RESPONSE.redirect(u+'/manage_main')
897: return ''
898:
899:
900:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to documentViewer.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / documentViewer