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