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:
16: import urllib2
17: import logging
18: import math
19: import urlparse
20: import cStringIO
21: import re
22:
23:
24: def logger(txt,method,txt2):
25: """logging"""
26: logging.info(txt+ txt2)
27:
28:
29: def getInt(number, default=0):
30: """returns always an int (0 in case of problems)"""
31: try:
32: return int(number)
33: except:
34: return int(default)
35:
36: def getTextFromNode(nodename):
37: """get the cdata content of a node"""
38: if nodename is None:
39: return ""
40: nodelist=nodename.childNodes
41: rc = ""
42: for node in nodelist:
43: if node.nodeType == node.TEXT_NODE:
44: rc = rc + node.data
45: return rc
46:
47: def serializeNode(node, encoding='utf-8'):
48: """returns a string containing node as XML"""
49: buf = cStringIO.StringIO()
50: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
51: s = buf.getvalue()
52: buf.close()
53: return s
54:
55: def getBrowserType(self):
56: """get browser type object"""
57: if self.REQUEST.SESSION.has_key('browserType'):
58: return self.REQUEST.SESSION['browserType']
59: else:
60: bt = browserCheck(self)
61: self.REQUEST.SESSION.set('browserType', bt)
62: logging.debug("documentViewer (BROWSER TYPE) bt %s"%bt)
63: return bt
64:
65:
66: def getParentDir(path):
67: """returns pathname shortened by one"""
68: return '/'.join(path.split('/')[0:-1])
69:
70:
71: def getHttpData(url, data=None, num_tries=3, timeout=10):
72: """returns result from url+data HTTP request"""
73: # we do GET (by appending data to url)
74: if isinstance(data, str) or isinstance(data, unicode):
75: # if data is string then append
76: url = "%s?%s"%(url,data)
77: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
78: # urlencode
79: url = "%s?%s"%(url,urllib.urlencode(data))
80:
81: response = None
82: errmsg = None
83: for cnt in range(num_tries):
84: try:
85: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
86: if sys.version_info < (2, 6):
87: # set timeout on socket -- ugly :-(
88: import socket
89: socket.setdefaulttimeout(float(timeout))
90: response = urllib2.urlopen(url)
91: else:
92: response = urllib2.urlopen(url,timeout=float(timeout))
93: # check result?
94: break
95: except urllib2.HTTPError, e:
96: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
97: errmsg = str(e)
98: # stop trying
99: break
100: except urllib2.URLError, e:
101: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
102: errmsg = str(e)
103: # stop trying
104: #break
105:
106: if response is not None:
107: data = response.read()
108: response.close()
109: return data
110:
111: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
112: #return None
113:
114:
115:
116: ##
117: ## documentViewer class
118: ##
119: class documentViewer(Folder):
120: """document viewer"""
121: meta_type="Document viewer"
122:
123: security=ClassSecurityInfo()
124: manage_options=Folder.manage_options+(
125: {'label':'main config','action':'changeDocumentViewerForm'},
126: )
127:
128: # templates and forms
129: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
130: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
131: toc_text = PageTemplateFile('zpt/toc_text', globals())
132: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
133: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
134: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
135: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
136: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
137: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
138: head_main = PageTemplateFile('zpt/head_main', globals())
139: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
140: info_xml = PageTemplateFile('zpt/info_xml', globals())
141:
142:
143: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
144: security.declareProtected('View management screens','changeDocumentViewerForm')
145: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
146:
147:
148: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
149: """init document viewer"""
150: self.id=id
151: self.title=title
152: self.thumbcols = thumbcols
153: self.thumbrows = thumbrows
154: # authgroups is list of authorized groups (delimited by ,)
155: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
156: # create template folder so we can always use template.something
157:
158: templateFolder = Folder('template')
159: #self['template'] = templateFolder # Zope-2.12 style
160: self._setObject('template',templateFolder) # old style
161: try:
162: import MpdlXmlTextServer
163: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
164: #templateFolder['fulltextclient'] = xmlRpcClient
165: templateFolder._setObject('fulltextclient',textServer)
166: except Exception, e:
167: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
168: try:
169: from Products.zogiLib.zogiLib import zogiLib
170: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
171: #templateFolder['zogilib'] = zogilib
172: templateFolder._setObject('zogilib',zogilib)
173: except Exception, e:
174: logging.error("Unable to create zogiLib for zogilib: "+str(e))
175:
176:
177: # proxy text server methods to fulltextclient
178: def getTextPage(self, **args):
179: """get page"""
180: return self.template.fulltextclient.getTextPage(**args)
181:
182: def getQuery(self, **args):
183: """get query"""
184: return self.template.fulltextclient.getQuery(**args)
185:
186: def getSearch(self, **args):
187: """get search"""
188: return self.template.fulltextclient.getSearch(**args)
189:
190: def getGisPlaces(self, **args):
191: """get gis places"""
192: return self.template.fulltextclient.getGisPlaces(**args)
193:
194: def getAllGisPlaces(self, **args):
195: """get all gis places """
196: return self.template.fulltextclient.getAllGisPlaces(**args)
197:
198: def getOrigPages(self, **args):
199: """get original page number """
200: return self.template.fulltextclient.getOrigPages(**args)
201:
202: def getNumPages(self, docinfo):
203: """get numpages"""
204: return self.template.fulltextclient.getNumPages(docinfo)
205:
206: def getNumTextPages(self, docinfo):
207: """get numpages text"""
208: return self.template.fulltextclient.getNumTextPages(docinfo)
209:
210: def getTranslate(self, **args):
211: """get translate"""
212: return self.template.fulltextclient.getTranslate(**args)
213:
214: def getLemma(self, **args):
215: """get lemma"""
216: return self.template.fulltextclient.getLemma(**args)
217:
218: def getToc(self, **args):
219: """get toc"""
220: return self.template.fulltextclient.getToc(**args)
221:
222: def getTocPage(self, **args):
223: """get tocpage"""
224: return self.template.fulltextclient.getTocPage(**args)
225:
226:
227: security.declareProtected('View','thumbs_rss')
228: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
229: '''
230: view it
231: @param mode: defines how to access the document behind url
232: @param url: url which contains display information
233: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
234:
235: '''
236: logging.debug("HHHHHHHHHHHHHH:load the rss")
237: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
238:
239: if not hasattr(self, 'template'):
240: # create template folder if it doesn't exist
241: self.manage_addFolder('template')
242:
243: if not self.digilibBaseUrl:
244: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
245:
246: docinfo = self.getDocinfo(mode=mode,url=url)
247: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
248: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
249: ''' ZDES '''
250: pt = getattr(self.template, 'thumbs_main_rss')
251:
252: if viewMode=="auto": # automodus gewaehlt
253: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
254: viewMode="text"
255: else:
256: viewMode="images"
257:
258: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
259:
260: security.declareProtected('View','index_html')
261: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
262: '''
263: view it
264: @param mode: defines how to access the document behind url
265: @param url: url which contains display information
266: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
267: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
268: @param characterNormalization type of text display (reg, norm, none)
269: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
270: '''
271:
272: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
273:
274: if not hasattr(self, 'template'):
275: # this won't work
276: logging.error("template folder missing!")
277: return "ERROR: template folder missing!"
278:
279: if not getattr(self, 'digilibBaseUrl', None):
280: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
281:
282: docinfo = self.getDocinfo(mode=mode,url=url)
283:
284: if tocMode != "thumbs":
285: # get table of contents
286: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
287:
288: if viewMode=="auto": # automodus gewaehlt
289: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
290: viewMode="text_dict"
291: else:
292: viewMode="images"
293:
294: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
295:
296: pt = getattr(self.template, 'viewer_main')
297: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
298:
299: def generateMarks(self,mk):
300: ret=""
301: if mk is None:
302: return ""
303: if not isinstance(mk, list):
304: mk=[mk]
305: for m in mk:
306: ret+="mk=%s"%m
307: return ret
308:
309:
310: def findDigilibUrl(self):
311: """try to get the digilib URL from zogilib"""
312: url = self.template.zogilib.getDLBaseUrl()
313: return url
314:
315: def getDocumentViewerURL(self):
316: """returns the URL of this instance"""
317: return self.absolute_url()
318:
319: def getStyle(self, idx, selected, style=""):
320: """returns a string with the given style and append 'sel' if path == selected."""
321: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
322: if idx == selected:
323: return style + 'sel'
324: else:
325: return style
326:
327: def getLink(self,param=None,val=None):
328: """link to documentviewer with parameter param set to val"""
329: params=self.REQUEST.form.copy()
330: if param is not None:
331: if val is None:
332: if params.has_key(param):
333: del params[param]
334: else:
335: params[param] = str(val)
336:
337: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
338: params["mode"] = "imagepath"
339: params["url"] = getParentDir(params["url"])
340:
341: # quote values and assemble into query string
342: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
343: ps = urllib.urlencode(params)
344: url=self.REQUEST['URL1']+"?"+ps
345: return url
346:
347: def getLinkAmp(self,param=None,val=None):
348: """link to documentviewer with parameter param set to val"""
349: params=self.REQUEST.form.copy()
350: if param is not None:
351: if val is None:
352: if params.has_key(param):
353: del params[param]
354: else:
355: params[param] = str(val)
356:
357: # quote values and assemble into query string
358: logging.debug("XYXXXXX: %s"%repr(params.items()))
359: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
360: url=self.REQUEST['URL1']+"?"+ps
361: return url
362:
363: def getInfo_xml(self,url,mode):
364: """returns info about the document as XML"""
365:
366: if not self.digilibBaseUrl:
367: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
368:
369: docinfo = self.getDocinfo(mode=mode,url=url)
370: pt = getattr(self.template, 'info_xml')
371: return pt(docinfo=docinfo)
372:
373:
374: def isAccessible(self, docinfo):
375: """returns if access to the resource is granted"""
376: access = docinfo.get('accessType', None)
377: logging.debug("documentViewer (accessOK) access type %s"%access)
378: if access is not None and access == 'free':
379: logging.debug("documentViewer (accessOK) access is free")
380: return True
381: elif access is None or access in self.authgroups:
382: # only local access -- only logged in users
383: user = getSecurityManager().getUser()
384: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
385: if user is not None:
386: #print "user: ", user
387: return (user.getUserName() != "Anonymous User")
388: else:
389: return False
390:
391: logging.error("documentViewer (accessOK) unknown access type %s"%access)
392: return False
393:
394:
395: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
396: """gibt param von dlInfo aus"""
397: if docinfo is None:
398: docinfo = {}
399:
400: for x in range(cut):
401:
402: path=getParentDir(path)
403:
404: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
405:
406: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
407:
408: txt = getHttpData(infoUrl)
409: if txt is None:
410: raise IOError("Unable to get dir-info from %s"%(infoUrl))
411:
412: dom = Parse(txt)
413: sizes=dom.xpath("//dir/size")
414: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
415:
416: if sizes:
417: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
418: else:
419: docinfo['numPages'] = 0
420:
421: # TODO: produce and keep list of image names and numbers
422:
423: return docinfo
424:
425: def getIndexMetaPath(self,url):
426: """gib nur den Pfad zurueck"""
427: regexp = re.compile(r".*(experimental|permanent)/(.*)")
428: regpath = regexp.match(url)
429: if (regpath==None):
430: return ""
431: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
432: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
433:
434:
435:
436: def getIndexMetaUrl(self,url):
437: """returns utr of index.meta document at url"""
438:
439: metaUrl = None
440: if url.startswith("http://"):
441: # real URL
442: metaUrl = url
443: else:
444: # online path
445: server=self.digilibBaseUrl+"/servlet/Texter?fn="
446: metaUrl=server+url.replace("/mpiwg/online","")
447: if not metaUrl.endswith("index.meta"):
448: metaUrl += "/index.meta"
449:
450: return metaUrl
451:
452: def getDomFromIndexMeta(self, url):
453: """get dom from index meta"""
454: dom = None
455: metaUrl = self.getIndexMetaUrl(url)
456:
457: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
458: txt=getHttpData(metaUrl)
459: if txt is None:
460: raise IOError("Unable to read index meta from %s"%(url))
461:
462: dom = Parse(txt)
463: return dom
464:
465: def getPresentationInfoXML(self, url):
466: """returns dom of info.xml document at url"""
467: dom = None
468: metaUrl = None
469: if url.startswith("http://"):
470: # real URL
471: metaUrl = url
472: else:
473: # online path
474: server=self.digilibBaseUrl+"/servlet/Texter?fn="
475: metaUrl=server+url.replace("/mpiwg/online","")
476:
477: txt=getHttpData(metaUrl)
478: if txt is None:
479: raise IOError("Unable to read infoXMLfrom %s"%(url))
480:
481: dom = Parse(txt)
482: return dom
483:
484:
485: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
486: """gets authorization info from the index.meta file at path or given by dom"""
487: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
488:
489: access = None
490:
491: if docinfo is None:
492: docinfo = {}
493:
494: if dom is None:
495: for x in range(cut):
496: path=getParentDir(path)
497: dom = self.getDomFromIndexMeta(path)
498:
499: acctype = dom.xpath("//access-conditions/access/@type")
500: if acctype and (len(acctype)>0):
501: access=acctype[0].value
502: if access in ['group', 'institution']:
503: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
504:
505: docinfo['accessType'] = access
506: return docinfo
507:
508:
509: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
510: """gets bibliographical info from the index.meta file at path or given by dom"""
511: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
512:
513: if docinfo is None:
514: docinfo = {}
515:
516: if dom is None:
517: for x in range(cut):
518: path=getParentDir(path)
519: dom = self.getDomFromIndexMeta(path)
520:
521: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
522:
523: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
524: # put in all raw bib fields as dict "bib"
525: bib = dom.xpath("//bib/*")
526: if bib and len(bib)>0:
527: bibinfo = {}
528: for e in bib:
529: bibinfo[e.localName] = getTextFromNode(e)
530: docinfo['bib'] = bibinfo
531:
532: # extract some fields (author, title, year) according to their mapping
533: metaData=self.metadata.main.meta.bib
534: bibtype=dom.xpath("//bib/@type")
535: if bibtype and (len(bibtype)>0):
536: bibtype=bibtype[0].value
537: else:
538: bibtype="generic"
539:
540: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
541: docinfo['bib_type'] = bibtype
542: bibmap=metaData.generateMappingForType(bibtype)
543: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
544: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
545: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
546: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
547: try:
548: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
549: except: pass
550: try:
551: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
552: except: pass
553: try:
554: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
555: except: pass
556: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
557: try:
558: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
559: except:
560: docinfo['lang']=''
561:
562: return docinfo
563:
564:
565: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
566: """gets name info from the index.meta file at path or given by dom"""
567: if docinfo is None:
568: docinfo = {}
569:
570: if dom is None:
571: for x in range(cut):
572: path=getParentDir(path)
573: dom = self.getDomFromIndexMeta(path)
574:
575: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
576: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
577: return docinfo
578:
579: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
580: """parse texttool tag in index meta"""
581: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
582: if docinfo is None:
583: docinfo = {}
584: if docinfo.get('lang', None) is None:
585: docinfo['lang'] = '' # default keine Sprache gesetzt
586: if dom is None:
587: dom = self.getDomFromIndexMeta(url)
588:
589: archivePath = None
590: archiveName = None
591:
592: archiveNames = dom.xpath("//resource/name")
593: if archiveNames and (len(archiveNames) > 0):
594: archiveName = getTextFromNode(archiveNames[0])
595: else:
596: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
597:
598: archivePaths = dom.xpath("//resource/archive-path")
599: if archivePaths and (len(archivePaths) > 0):
600: archivePath = getTextFromNode(archivePaths[0])
601: # clean up archive path
602: if archivePath[0] != '/':
603: archivePath = '/' + archivePath
604: if archiveName and (not archivePath.endswith(archiveName)):
605: archivePath += "/" + archiveName
606: else:
607: # try to get archive-path from url
608: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
609: if (not url.startswith('http')):
610: archivePath = url.replace('index.meta', '')
611:
612: if archivePath is None:
613: # we balk without archive-path
614: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
615:
616: imageDirs = dom.xpath("//texttool/image")
617: if imageDirs and (len(imageDirs) > 0):
618: imageDir = getTextFromNode(imageDirs[0])
619:
620: else:
621: # we balk with no image tag / not necessary anymore because textmode is now standard
622: #raise IOError("No text-tool info in %s"%(url))
623: imageDir = ""
624: #xquery="//pb"
625: docinfo['imagePath'] = "" # keine Bilder
626: docinfo['imageURL'] = ""
627:
628: if imageDir and archivePath:
629: #print "image: ", imageDir, " archivepath: ", archivePath
630: imageDir = os.path.join(archivePath, imageDir)
631: imageDir = imageDir.replace("/mpiwg/online", '')
632: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
633: docinfo['imagePath'] = imageDir
634:
635: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
636:
637: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
638: if viewerUrls and (len(viewerUrls) > 0):
639: viewerUrl = getTextFromNode(viewerUrls[0])
640: docinfo['viewerURL'] = viewerUrl
641:
642: # old style text URL
643: textUrls = dom.xpath("//texttool/text")
644: if textUrls and (len(textUrls) > 0):
645: textUrl = getTextFromNode(textUrls[0])
646: if urlparse.urlparse(textUrl)[0] == "": #keine url
647: textUrl = os.path.join(archivePath, textUrl)
648: # fix URLs starting with /mpiwg/online
649: if textUrl.startswith("/mpiwg/online"):
650: textUrl = textUrl.replace("/mpiwg/online", '', 1)
651:
652: docinfo['textURL'] = textUrl
653:
654: # new style text-url-path
655: textUrls = dom.xpath("//texttool/text-url-path")
656: if textUrls and (len(textUrls) > 0):
657: textUrl = getTextFromNode(textUrls[0])
658: docinfo['textURLPath'] = textUrl
659: if not docinfo['imagePath']:
660: # text-only, no page images
661: docinfo = self.getNumTextPages(docinfo)
662:
663: presentationUrls = dom.xpath("//texttool/presentation")
664: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
665: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
666: docinfo =self.getOrigPages(docinfo=docinfo)
667:
668: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
669: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
670: # durch den relativen Pfad auf die presentation infos
671: presentationPath = getTextFromNode(presentationUrls[0])
672: if url.endswith("index.meta"):
673: presentationUrl = url.replace('index.meta', presentationPath)
674: else:
675: presentationUrl = url + "/" + presentationPath
676:
677: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
678:
679: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
680:
681: return docinfo
682:
683:
684: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
685: """gets the bibliographical information from the preseantion entry in texttools
686: """
687: dom=self.getPresentationInfoXML(url)
688: try:
689: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
690: except:
691: pass
692: try:
693: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
694: except:
695: pass
696: try:
697: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
698: except:
699: pass
700: return docinfo
701:
702: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
703: """path ist the path to the images it assumes that the index.meta file is one level higher."""
704: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
705: if docinfo is None:
706: docinfo = {}
707: path=path.replace("/mpiwg/online","")
708: docinfo['imagePath'] = path
709: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
710:
711: pathorig=path
712: for x in range(cut):
713: path=getParentDir(path)
714: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
715: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
716: docinfo['imageURL'] = imageUrl
717:
718: #path ist the path to the images it assumes that the index.meta file is one level higher.
719: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
720: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
721: return docinfo
722:
723:
724: def getDocinfo(self, mode, url):
725: """returns docinfo depending on mode"""
726: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
727: # look for cached docinfo in session
728: if self.REQUEST.SESSION.has_key('docinfo'):
729: docinfo = self.REQUEST.SESSION['docinfo']
730: # check if its still current
731: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
732: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
733: return docinfo
734: # new docinfo
735: docinfo = {'mode': mode, 'url': url}
736: if mode=="texttool": #index.meta with texttool information
737: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
738: elif mode=="imagepath":
739: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
740: elif mode=="filepath":
741: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
742: else:
743: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
744: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
745:
746: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
747:
748: self.REQUEST.SESSION['docinfo'] = docinfo
749: return docinfo
750:
751: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
752: """returns pageinfo with the given parameters"""
753: pageinfo = {}
754: current = getInt(current)
755:
756: #pageinfo ['originalPage'] = self.getOrigPages(docinfo=docinfo,pageinfo=pageinfo)
757: pageinfo['current'] = current
758: rows = int(rows or self.thumbrows)
759: pageinfo['rows'] = rows
760: cols = int(cols or self.thumbcols)
761: pageinfo['cols'] = cols
762: grpsize = cols * rows
763: pageinfo['groupsize'] = grpsize
764: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
765: # int(current / grpsize) * grpsize +1))
766: pageinfo['start'] = start
767: pageinfo['end'] = start + grpsize
768: if (docinfo is not None) and ('numPages' in docinfo):
769: np = int(docinfo['numPages'])
770: pageinfo['end'] = min(pageinfo['end'], np)
771: pageinfo['numgroups'] = int(np / grpsize)
772: if np % grpsize > 0:
773: pageinfo['numgroups'] += 1
774: pageinfo['viewMode'] = viewMode
775: pageinfo['tocMode'] = tocMode
776: #pageinfo['characterNormalization'] =characterNormalization
777: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
778: pageinfo['query'] = self.REQUEST.get('query',' ')
779: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
780: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
781: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
782: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
783: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
784: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
785: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
786: toc = int (pageinfo['tocPN'])
787: pageinfo['textPages'] =int (toc)
788:
789: #logging.debug("originalPage: %s"%originalPage)
790:
791: if 'tocSize_%s'%tocMode in docinfo:
792: tocSize = int(docinfo['tocSize_%s'%tocMode])
793: tocPageSize = int(pageinfo['tocPageSize'])
794: # cached toc
795: if tocSize%tocPageSize>0:
796: tocPages=tocSize/tocPageSize+1
797: else:
798: tocPages=tocSize/tocPageSize
799: pageinfo['tocPN'] = min (tocPages,toc)
800: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
801: pageinfo['sn'] =self.REQUEST.get('sn','')
802: return pageinfo
803:
804: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
805: """init document viewer"""
806: self.title=title
807: self.digilibBaseUrl = digilibBaseUrl
808: self.thumbrows = thumbrows
809: self.thumbcols = thumbcols
810: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
811: if RESPONSE is not None:
812: RESPONSE.redirect('manage_main')
813:
814: def manage_AddDocumentViewerForm(self):
815: """add the viewer form"""
816: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
817: return pt()
818:
819: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
820: """add the viewer"""
821: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
822: self._setObject(id,newObj)
823:
824: if RESPONSE is not None:
825: RESPONSE.redirect('manage_main')
826:
827: ## DocumentViewerTemplate class
828: class DocumentViewerTemplate(ZopePageTemplate):
829: """Template for document viewer"""
830: meta_type="DocumentViewer Template"
831:
832:
833: def manage_addDocumentViewerTemplateForm(self):
834: """Form for adding"""
835: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
836: return pt()
837:
838: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
839: REQUEST=None, submit=None):
840: "Add a Page Template with optional file content."
841:
842: self._setObject(id, DocumentViewerTemplate(id))
843: ob = getattr(self, id)
844: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
845: logging.info("txt %s:"%txt)
846: ob.pt_edit(txt,"text/html")
847: if title:
848: ob.pt_setTitle(title)
849: try:
850: u = self.DestinationURL()
851: except AttributeError:
852: u = REQUEST['URL1']
853:
854: u = "%s/%s" % (u, urllib.quote(id))
855: REQUEST.RESPONSE.redirect(u+'/manage_main')
856: return ''
857:
858:
859:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>