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:
9: from Ft.Xml import EMPTY_NAMESPACE, Parse
10: import Ft.Xml.Domlette
11: import os.path
12: import sys
13: import urllib
14: import urllib2
15: import logging
16: import math
17: import urlparse
18: import cStringIO
19:
20: def logger(txt,method,txt2):
21: """logging"""
22: logging.info(txt+ txt2)
23:
24:
25: def getInt(number, default=0):
26: """returns always an int (0 in case of problems)"""
27: try:
28: return int(number)
29: except:
30: return int(default)
31:
32: def getTextFromNode(nodename):
33: """get the cdata content of a node"""
34: if nodename is None:
35: return ""
36: nodelist=nodename.childNodes
37: rc = ""
38: for node in nodelist:
39: if node.nodeType == node.TEXT_NODE:
40: rc = rc + node.data
41: return rc
42:
43: def serializeNode(node, encoding='utf-8'):
44: """returns a string containing node as XML"""
45: buf = cStringIO.StringIO()
46: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
47: s = buf.getvalue()
48: buf.close()
49: return s
50:
51:
52: def getParentDir(path):
53: """returns pathname shortened by one"""
54: return '/'.join(path.split('/')[0:-1])
55:
56:
57: def getHttpData(url, data=None, num_tries=3, timeout=10):
58: """returns result from url+data HTTP request"""
59: # we do GET (by appending data to url)
60: if isinstance(data, str) or isinstance(data, unicode):
61: # if data is string then append
62: url = "%s?%s"%(url,data)
63: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
64: # urlencode
65: url = "%s?%s"%(url,urllib.urlencode(data))
66:
67: response = None
68: errmsg = None
69: for cnt in range(num_tries):
70: try:
71: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
72: if sys.version_info < (2, 6):
73: # set timeout on socket -- ugly :-(
74: import socket
75: socket.setdefaulttimeout(float(timeout))
76: response = urllib2.urlopen(url)
77: else:
78: response = urllib2.urlopen(url,timeout=float(timeout))
79: # check result?
80: break
81: except urllib2.HTTPError, e:
82: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
83: errmsg = str(e)
84: # stop trying
85: break
86: except urllib2.URLError, e:
87: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
88: errmsg = str(e)
89: # stop trying
90: #break
91:
92: if response is not None:
93: data = response.read()
94: response.close()
95: return data
96:
97: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
98: #return None
99:
100:
101:
102: ##
103: ## documentViewer class
104: ##
105: class documentViewer(Folder):
106: """document viewer"""
107: meta_type="Document viewer"
108:
109: security=ClassSecurityInfo()
110: manage_options=Folder.manage_options+(
111: {'label':'main config','action':'changeDocumentViewerForm'},
112: )
113:
114: # templates and forms
115: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
116: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
117: toc_text = PageTemplateFile('zpt/toc_text', globals())
118: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
119: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
120: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
121: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
122: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
123: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
124: head_main = PageTemplateFile('zpt/head_main', globals())
125: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
126: info_xml = PageTemplateFile('zpt/info_xml', globals())
127:
128:
129: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
130: security.declareProtected('View management screens','changeDocumentViewerForm')
131: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
132:
133:
134: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
135: """init document viewer"""
136: self.id=id
137: self.title=title
138: self.thumbcols = thumbcols
139: self.thumbrows = thumbrows
140: # authgroups is list of authorized groups (delimited by ,)
141: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
142: # create template folder so we can always use template.something
143:
144: templateFolder = Folder('template')
145: #self['template'] = templateFolder # Zope-2.12 style
146: self._setObject('template',templateFolder) # old style
147: try:
148: import MpdlXmlTextServer
149: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
150: #templateFolder['fulltextclient'] = xmlRpcClient
151: templateFolder._setObject('fulltextclient',textServer)
152: except Exception, e:
153: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
154: try:
155: from Products.zogiLib.zogiLib import zogiLib
156: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
157: #templateFolder['zogilib'] = zogilib
158: templateFolder._setObject('zogilib',zogilib)
159: except Exception, e:
160: logging.error("Unable to create zogiLib for zogilib: "+str(e))
161:
162:
163: # proxy text server methods to fulltextclient
164: def getTextPage(self, **args):
165: """get page"""
166: return self.template.fulltextclient.getTextPage(**args)
167:
168: def getQuery(self, **args):
169: """get query"""
170: return self.template.fulltextclient.getQuery(**args)
171:
172: def getSearch(self, **args):
173: """get search"""
174: return self.template.fulltextclient.getSearch(**args)
175:
176: def getNumPages(self, docinfo):
177: """get numpages"""
178: return self.template.fulltextclient.getNumPages(docinfo)
179:
180: def getTranslate(self, **args):
181: """get translate"""
182: return self.template.fulltextclient.getTranslate(**args)
183:
184: def getLemma(self, **args):
185: """get lemma"""
186: return self.template.fulltextclient.getLemma(**args)
187:
188: def getToc(self, **args):
189: """get toc"""
190: return self.template.fulltextclient.getToc(**args)
191:
192: def getTocPage(self, **args):
193: """get tocpage"""
194: return self.template.fulltextclient.getTocPage(**args)
195:
196:
197: security.declareProtected('View','thumbs_rss')
198: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
199: '''
200: view it
201: @param mode: defines how to access the document behind url
202: @param url: url which contains display information
203: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
204:
205: '''
206: logging.debug("HHHHHHHHHHHHHH:load the rss")
207: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
208:
209: if not hasattr(self, 'template'):
210: # create template folder if it doesn't exist
211: self.manage_addFolder('template')
212:
213: if not self.digilibBaseUrl:
214: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
215:
216: docinfo = self.getDocinfo(mode=mode,url=url)
217: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
218: pt = getattr(self.template, 'thumbs_main_rss')
219:
220: if viewMode=="auto": # automodus gewaehlt
221: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
222: viewMode="text"
223: else:
224: viewMode="images"
225:
226: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
227:
228: security.declareProtected('View','index_html')
229: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
230: '''
231: view it
232: @param mode: defines how to access the document behind url
233: @param url: url which contains display information
234: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
235: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
236: @param characterNormalization type of text display (reg, norm, none)
237: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
238: '''
239:
240: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
241:
242: if not hasattr(self, 'template'):
243: # this won't work
244: logging.error("template folder missing!")
245: return "ERROR: template folder missing!"
246:
247: if not getattr(self, 'digilibBaseUrl', None):
248: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
249:
250: docinfo = self.getDocinfo(mode=mode,url=url)
251:
252: if tocMode != "thumbs":
253: # get table of contents
254: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
255:
256: if viewMode=="auto": # automodus gewaehlt
257: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
258: viewMode="text_dict"
259: else:
260: viewMode="images"
261:
262: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
263:
264: pt = getattr(self.template, 'viewer_main')
265: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
266:
267: def generateMarks(self,mk):
268: ret=""
269: if mk is None:
270: return ""
271: if not isinstance(mk, list):
272: mk=[mk]
273: for m in mk:
274: ret+="mk=%s"%m
275: return ret
276:
277:
278: def findDigilibUrl(self):
279: """try to get the digilib URL from zogilib"""
280: url = self.template.zogilib.getDLBaseUrl()
281: return url
282:
283: def getDocumentViewerURL(self):
284: """returns the URL of this instance"""
285: return self.absolute_url()
286:
287: def getStyle(self, idx, selected, style=""):
288: """returns a string with the given style and append 'sel' if path == selected."""
289: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
290: if idx == selected:
291: return style + 'sel'
292: else:
293: return style
294:
295: def getLink(self,param=None,val=None):
296: """link to documentviewer with parameter param set to val"""
297: params=self.REQUEST.form.copy()
298: if param is not None:
299: if val is None:
300: if params.has_key(param):
301: del params[param]
302: else:
303: params[param] = str(val)
304:
305: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
306: params["mode"] = "imagepath"
307: params["url"] = getParentDir(params["url"])
308:
309: # quote values and assemble into query string
310: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
311: ps = urllib.urlencode(params)
312: url=self.REQUEST['URL1']+"?"+ps
313: return url
314:
315: def getLinkAmp(self,param=None,val=None):
316: """link to documentviewer with parameter param set to val"""
317: params=self.REQUEST.form.copy()
318: if param is not None:
319: if val is None:
320: if params.has_key(param):
321: del params[param]
322: else:
323: params[param] = str(val)
324:
325: # quote values and assemble into query string
326: logging.debug("XYXXXXX: %s"%repr(params.items()))
327: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
328: url=self.REQUEST['URL1']+"?"+ps
329: return url
330:
331: def getInfo_xml(self,url,mode):
332: """returns info about the document as XML"""
333:
334: if not self.digilibBaseUrl:
335: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
336:
337: docinfo = self.getDocinfo(mode=mode,url=url)
338: pt = getattr(self.template, 'info_xml')
339: return pt(docinfo=docinfo)
340:
341:
342: def isAccessible(self, docinfo):
343: """returns if access to the resource is granted"""
344: access = docinfo.get('accessType', None)
345: logging.debug("documentViewer (accessOK) access type %s"%access)
346: if access is not None and access == 'free':
347: logging.debug("documentViewer (accessOK) access is free")
348: return True
349: elif access is None or access in self.authgroups:
350: # only local access -- only logged in users
351: user = getSecurityManager().getUser()
352: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
353: if user is not None:
354: #print "user: ", user
355: return (user.getUserName() != "Anonymous User")
356: else:
357: return False
358:
359: logging.error("documentViewer (accessOK) unknown access type %s"%access)
360: return False
361:
362:
363: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
364: """gibt param von dlInfo aus"""
365: if docinfo is None:
366: docinfo = {}
367:
368: for x in range(cut):
369:
370: path=getParentDir(path)
371:
372: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
373:
374: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
375:
376: txt = getHttpData(infoUrl)
377: if txt is None:
378: raise IOError("Unable to get dir-info from %s"%(infoUrl))
379:
380: dom = Parse(txt)
381: sizes=dom.xpath("//dir/size")
382: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
383:
384: if sizes:
385: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
386: else:
387: docinfo['numPages'] = 0
388:
389: # TODO: produce and keep list of image names and numbers
390:
391: return docinfo
392:
393:
394: def getIndexMeta(self, url):
395: """returns dom of index.meta document at url"""
396: dom = None
397: metaUrl = None
398: if url.startswith("http://"):
399: # real URL
400: metaUrl = url
401: else:
402: # online path
403: server=self.digilibBaseUrl+"/servlet/Texter?fn="
404: metaUrl=server+url.replace("/mpiwg/online","")
405: if not metaUrl.endswith("index.meta"):
406: metaUrl += "/index.meta"
407:
408: logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
409: txt=getHttpData(metaUrl)
410: if txt is None:
411: raise IOError("Unable to read index meta from %s"%(url))
412:
413: dom = Parse(txt)
414: return dom
415:
416: def getPresentationInfoXML(self, url):
417: """returns dom of info.xml document at url"""
418: dom = None
419: metaUrl = None
420: if url.startswith("http://"):
421: # real URL
422: metaUrl = url
423: else:
424: # online path
425: server=self.digilibBaseUrl+"/servlet/Texter?fn="
426: metaUrl=server+url.replace("/mpiwg/online","")
427:
428: txt=getHttpData(metaUrl)
429: if txt is None:
430: raise IOError("Unable to read infoXMLfrom %s"%(url))
431:
432: dom = Parse(txt)
433: return dom
434:
435:
436: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
437: """gets authorization info from the index.meta file at path or given by dom"""
438: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
439:
440: access = None
441:
442: if docinfo is None:
443: docinfo = {}
444:
445: if dom is None:
446: for x in range(cut):
447: path=getParentDir(path)
448: dom = self.getIndexMeta(path)
449:
450: acctype = dom.xpath("//access-conditions/access/@type")
451: if acctype and (len(acctype)>0):
452: access=acctype[0].value
453: if access in ['group', 'institution']:
454: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
455:
456: docinfo['accessType'] = access
457: return docinfo
458:
459:
460: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
461: """gets bibliographical info from the index.meta file at path or given by dom"""
462: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
463:
464: if docinfo is None:
465: docinfo = {}
466:
467: if dom is None:
468: for x in range(cut):
469: path=getParentDir(path)
470: dom = self.getIndexMeta(path)
471:
472: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
473: # put in all raw bib fields as dict "bib"
474: bib = dom.xpath("//bib/*")
475: if bib and len(bib)>0:
476: bibinfo = {}
477: for e in bib:
478: bibinfo[e.localName] = getTextFromNode(e)
479: docinfo['bib'] = bibinfo
480:
481: # extract some fields (author, title, year) according to their mapping
482: metaData=self.metadata.main.meta.bib
483: bibtype=dom.xpath("//bib/@type")
484: if bibtype and (len(bibtype)>0):
485: bibtype=bibtype[0].value
486: else:
487: bibtype="generic"
488:
489: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
490: docinfo['bib_type'] = bibtype
491: bibmap=metaData.generateMappingForType(bibtype)
492: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
493: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
494: try:
495: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
496: except: pass
497: try:
498: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
499: except: pass
500: try:
501: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
502: except: pass
503: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
504: try:
505: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
506: except:
507: docinfo['lang']=''
508:
509: return docinfo
510:
511:
512: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
513: """parse texttool tag in index meta"""
514: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
515: if docinfo is None:
516: docinfo = {}
517: if docinfo.get('lang', None) is None:
518: docinfo['lang'] = '' # default keine Sprache gesetzt
519: if dom is None:
520: dom = self.getIndexMeta(url)
521:
522: archivePath = None
523: archiveName = None
524:
525: archiveNames = dom.xpath("//resource/name")
526: if archiveNames and (len(archiveNames) > 0):
527: archiveName = getTextFromNode(archiveNames[0])
528: else:
529: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
530:
531: archivePaths = dom.xpath("//resource/archive-path")
532: if archivePaths and (len(archivePaths) > 0):
533: archivePath = getTextFromNode(archivePaths[0])
534: # clean up archive path
535: if archivePath[0] != '/':
536: archivePath = '/' + archivePath
537: if archiveName and (not archivePath.endswith(archiveName)):
538: archivePath += "/" + archiveName
539: else:
540: # try to get archive-path from url
541: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
542: if (not url.startswith('http')):
543: archivePath = url.replace('index.meta', '')
544:
545: if archivePath is None:
546: # we balk without archive-path
547: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
548:
549: imageDirs = dom.xpath("//texttool/image")
550: if imageDirs and (len(imageDirs) > 0):
551: imageDir = getTextFromNode(imageDirs[0])
552:
553: else:
554: # we balk with no image tag / not necessary anymore because textmode is now standard
555: #raise IOError("No text-tool info in %s"%(url))
556: imageDir = ""
557: #xquery="//pb"
558: docinfo['imagePath'] = "" # keine Bilder
559: docinfo['imageURL'] = ""
560:
561: if imageDir and archivePath:
562: #print "image: ", imageDir, " archivepath: ", archivePath
563: imageDir = os.path.join(archivePath, imageDir)
564: imageDir = imageDir.replace("/mpiwg/online", '')
565: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
566: docinfo['imagePath'] = imageDir
567:
568: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
569:
570: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
571: if viewerUrls and (len(viewerUrls) > 0):
572: viewerUrl = getTextFromNode(viewerUrls[0])
573: docinfo['viewerURL'] = viewerUrl
574:
575: # old style text URL
576: textUrls = dom.xpath("//texttool/text")
577: if textUrls and (len(textUrls) > 0):
578: textUrl = getTextFromNode(textUrls[0])
579: if urlparse.urlparse(textUrl)[0] == "": #keine url
580: textUrl = os.path.join(archivePath, textUrl)
581: # fix URLs starting with /mpiwg/online
582: if textUrl.startswith("/mpiwg/online"):
583: textUrl = textUrl.replace("/mpiwg/online", '', 1)
584:
585: docinfo['textURL'] = textUrl
586:
587: # new style text-url-path
588: textUrls = dom.xpath("//texttool/text-url-path")
589: if textUrls and (len(textUrls) > 0):
590: textUrl = getTextFromNode(textUrls[0])
591: docinfo['textURLPath'] = textUrl
592: if not docinfo['imagePath']:
593: # text-only, no page images
594: docinfo = self.getNumPages(docinfo)
595:
596: presentationUrls = dom.xpath("//texttool/presentation")
597: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
598:
599: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
600: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
601: # durch den relativen Pfad auf die presentation infos
602: presentationPath = getTextFromNode(presentationUrls[0])
603: if url.endswith("index.meta"):
604: presentationUrl = url.replace('index.meta', presentationPath)
605: else:
606: presentationUrl = url + "/" + presentationPath
607:
608: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
609:
610: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
611:
612: return docinfo
613:
614:
615: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
616: """gets the bibliographical information from the preseantion entry in texttools
617: """
618: dom=self.getPresentationInfoXML(url)
619: try:
620: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
621: except:
622: pass
623: try:
624: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
625: except:
626: pass
627: try:
628: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
629: except:
630: pass
631: return docinfo
632:
633: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
634: """path ist the path to the images it assumes that the index.meta file is one level higher."""
635: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
636: if docinfo is None:
637: docinfo = {}
638: path=path.replace("/mpiwg/online","")
639: docinfo['imagePath'] = path
640: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
641:
642: pathorig=path
643: for x in range(cut):
644: path=getParentDir(path)
645: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
646: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
647: docinfo['imageURL'] = imageUrl
648:
649: #path ist the path to the images it assumes that the index.meta file is one level higher.
650: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
651: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
652: return docinfo
653:
654:
655: def getDocinfo(self, mode, url):
656: """returns docinfo depending on mode"""
657: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
658: # look for cached docinfo in session
659: if self.REQUEST.SESSION.has_key('docinfo'):
660: docinfo = self.REQUEST.SESSION['docinfo']
661: # check if its still current
662: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
663: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
664: return docinfo
665: # new docinfo
666: docinfo = {'mode': mode, 'url': url}
667: if mode=="texttool": #index.meta with texttool information
668: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
669: elif mode=="imagepath":
670: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
671: elif mode=="filepath":
672: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
673: else:
674: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
675: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
676:
677: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
678: self.REQUEST.SESSION['docinfo'] = docinfo
679: return docinfo
680:
681: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
682: """returns pageinfo with the given parameters"""
683: pageinfo = {}
684: current = getInt(current)
685: pageinfo['current'] = current
686: rows = int(rows or self.thumbrows)
687: pageinfo['rows'] = rows
688: cols = int(cols or self.thumbcols)
689: pageinfo['cols'] = cols
690: grpsize = cols * rows
691: pageinfo['groupsize'] = grpsize
692: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
693: # int(current / grpsize) * grpsize +1))
694: pageinfo['start'] = start
695: pageinfo['end'] = start + grpsize
696: if (docinfo is not None) and ('numPages' in docinfo):
697: np = int(docinfo['numPages'])
698: pageinfo['end'] = min(pageinfo['end'], np)
699: pageinfo['numgroups'] = int(np / grpsize)
700: if np % grpsize > 0:
701: pageinfo['numgroups'] += 1
702: pageinfo['viewMode'] = viewMode
703: pageinfo['tocMode'] = tocMode
704: #pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','')
705: pageinfo['query'] = self.REQUEST.get('query',' ')
706: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
707: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
708: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
709: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
710: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
711: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
712: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
713: toc = int (pageinfo['tocPN'])
714: pageinfo['textPages'] =int (toc)
715:
716: if 'tocSize_%s'%tocMode in docinfo:
717: tocSize = int(docinfo['tocSize_%s'%tocMode])
718: tocPageSize = int(pageinfo['tocPageSize'])
719: # cached toc
720: if tocSize%tocPageSize>0:
721: tocPages=tocSize/tocPageSize+1
722: else:
723: tocPages=tocSize/tocPageSize
724: pageinfo['tocPN'] = min (tocPages,toc)
725: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
726: pageinfo['sn'] =self.REQUEST.get('sn','')
727: return pageinfo
728:
729: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
730: """init document viewer"""
731: self.title=title
732: self.digilibBaseUrl = digilibBaseUrl
733: self.thumbrows = thumbrows
734: self.thumbcols = thumbcols
735: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
736: if RESPONSE is not None:
737: RESPONSE.redirect('manage_main')
738:
739: def manage_AddDocumentViewerForm(self):
740: """add the viewer form"""
741: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
742: return pt()
743:
744: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
745: """add the viewer"""
746: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
747: self._setObject(id,newObj)
748:
749: if RESPONSE is not None:
750: RESPONSE.redirect('manage_main')
751:
752: ## DocumentViewerTemplate class
753: class DocumentViewerTemplate(ZopePageTemplate):
754: """Template for document viewer"""
755: meta_type="DocumentViewer Template"
756:
757:
758: def manage_addDocumentViewerTemplateForm(self):
759: """Form for adding"""
760: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
761: return pt()
762:
763: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
764: REQUEST=None, submit=None):
765: "Add a Page Template with optional file content."
766:
767: self._setObject(id, DocumentViewerTemplate(id))
768: ob = getattr(self, id)
769: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
770: logging.info("txt %s:"%txt)
771: ob.pt_edit(txt,"text/html")
772: if title:
773: ob.pt_setTitle(title)
774: try:
775: u = self.DestinationURL()
776: except AttributeError:
777: u = REQUEST['URL1']
778:
779: u = "%s/%s" % (u, urllib.quote(id))
780: REQUEST.RESPONSE.redirect(u+'/manage_main')
781: return ''
782:
783:
784:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>