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 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_text = PageTemplateFile('zpt/page_main_text', globals())
151: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
152: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
153: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
154: head_main = PageTemplateFile('zpt/head_main', globals())
155: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
156: info_xml = PageTemplateFile('zpt/info_xml', globals())
157:
158:
159: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
160: security.declareProtected('View management screens','changeDocumentViewerForm')
161: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
162:
163:
164: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
165: """init document viewer"""
166: self.id=id
167: self.title=title
168: self.thumbcols = thumbcols
169: self.thumbrows = thumbrows
170: # authgroups is list of authorized groups (delimited by ,)
171: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
172: # create template folder so we can always use template.something
173:
174: templateFolder = Folder('template')
175: #self['template'] = templateFolder # Zope-2.12 style
176: self._setObject('template',templateFolder) # old style
177: try:
178: import MpdlXmlTextServer
179: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
180: #templateFolder['fulltextclient'] = xmlRpcClient
181: templateFolder._setObject('fulltextclient',textServer)
182: except Exception, e:
183: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
184: try:
185: from Products.zogiLib.zogiLib import zogiLib
186: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
187: #templateFolder['zogilib'] = zogilib
188: templateFolder._setObject('zogilib',zogilib)
189: except Exception, e:
190: logging.error("Unable to create zogiLib for zogilib: "+str(e))
191:
192:
193: # proxy text server methods to fulltextclient
194: def getTextPage(self, **args):
195: """get page"""
196: return self.template.fulltextclient.getTextPage(**args)
197:
198: def getQuery(self, **args):
199: """get query"""
200: return self.template.fulltextclient.getQuery(**args)
201:
202: def getPDF(self, **args):
203: """get query"""
204: return self.template.fulltextclient.getPDF(**args)
205:
206: def getSearch(self, **args):
207: """get search"""
208: return self.template.fulltextclient.getSearch(**args)
209:
210: def getGisPlaces(self, **args):
211: """get gis places"""
212: return self.template.fulltextclient.getGisPlaces(**args)
213:
214: def getAllGisPlaces(self, **args):
215: """get all gis places """
216: return self.template.fulltextclient.getAllGisPlaces(**args)
217:
218: def getOrigPages(self, **args):
219: """get original page number """
220: return self.template.fulltextclient.getOrigPages(**args)
221:
222: def getNumPages(self, docinfo):
223: """get numpages"""
224: return self.template.fulltextclient.getNumPages(docinfo)
225:
226: def getNumTextPages(self, docinfo):
227: """get numpages text"""
228: return self.template.fulltextclient.getNumTextPages(docinfo)
229:
230: def getTranslate(self, **args):
231: """get translate"""
232: return self.template.fulltextclient.getTranslate(**args)
233:
234: def getLemma(self, **args):
235: """get lemma"""
236: return self.template.fulltextclient.getLemma(**args)
237:
238: def getToc(self, **args):
239: """get toc"""
240: return self.template.fulltextclient.getToc(**args)
241:
242: def getTocPage(self, **args):
243: """get tocpage"""
244: return self.template.fulltextclient.getTocPage(**args)
245:
246:
247: security.declareProtected('View','thumbs_rss')
248: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
249: '''
250: view it
251: @param mode: defines how to access the document behind url
252: @param url: url which contains display information
253: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
254:
255: '''
256: logging.debug("HHHHHHHHHHHHHH:load the rss")
257: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
258:
259: if not hasattr(self, 'template'):
260: # create template folder if it doesn't exist
261: self.manage_addFolder('template')
262:
263: if not self.digilibBaseUrl:
264: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
265:
266: docinfo = self.getDocinfo(mode=mode,url=url)
267: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
268: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
269: ''' ZDES '''
270: pt = getattr(self.template, 'thumbs_main_rss')
271:
272: if viewMode=="auto": # automodus gewaehlt
273: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
274: viewMode="text"
275: else:
276: viewMode="images"
277:
278: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
279:
280: security.declareProtected('View','index_html')
281: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
282: '''
283: view it
284: @param mode: defines how to access the document behind url
285: @param url: url which contains display information
286: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
287: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
288: @param characterNormalization type of text display (reg, norm, none)
289: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
290: '''
291:
292: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
293:
294: if not hasattr(self, 'template'):
295: # this won't work
296: logging.error("template folder missing!")
297: return "ERROR: template folder missing!"
298:
299: if not getattr(self, 'digilibBaseUrl', None):
300: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
301:
302: docinfo = self.getDocinfo(mode=mode,url=url)
303:
304: if tocMode != "thumbs":
305: # get table of contents
306: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
307:
308: if viewMode=="auto": # automodus gewaehlt
309: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
310: viewMode="text_dict"
311: else:
312: viewMode="images"
313:
314: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
315:
316: pt = getattr(self.template, 'viewer_main')
317: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
318:
319: def generateMarks(self,mk):
320: ret=""
321: if mk is None:
322: return ""
323: if not isinstance(mk, list):
324: mk=[mk]
325: for m in mk:
326: ret+="mk=%s"%m
327: return ret
328:
329: def getBrowser(self):
330: """getBrowser the version of browser """
331: bt = browserCheck(self)
332: logging.debug("XXXXXXXXXXXXXXXX: %s"%bt)
333: return bt
334:
335: def findDigilibUrl(self):
336: """try to get the digilib URL from zogilib"""
337: url = self.template.zogilib.getDLBaseUrl()
338: return url
339:
340: def getDocumentViewerURL(self):
341: """returns the URL of this instance"""
342: return self.absolute_url()
343:
344: def getStyle(self, idx, selected, style=""):
345: """returns a string with the given style and append 'sel' if path == selected."""
346: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
347: if idx == selected:
348: return style + 'sel'
349: else:
350: return style
351:
352: def getLink(self,param=None,val=None):
353: """link to documentviewer with parameter param set to val"""
354: params=self.REQUEST.form.copy()
355: if param is not None:
356: if val is None:
357: if params.has_key(param):
358: del params[param]
359: else:
360: params[param] = str(val)
361:
362: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
363: params["mode"] = "imagepath"
364: params["url"] = getParentDir(params["url"])
365:
366: # quote values and assemble into query string
367: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
368: ps = urllib.urlencode(params)
369: url=self.REQUEST['URL1']+"?"+ps
370: return url
371:
372: def getLinkAmp(self,param=None,val=None):
373: """link to documentviewer with parameter param set to val"""
374: params=self.REQUEST.form.copy()
375: if param is not None:
376: if val is None:
377: if params.has_key(param):
378: del params[param]
379: else:
380: params[param] = str(val)
381:
382: # quote values and assemble into query string
383: logging.debug("XYXXXXX: %s"%repr(params.items()))
384: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
385: url=self.REQUEST['URL1']+"?"+ps
386: return url
387:
388: def getInfo_xml(self,url,mode):
389: """returns info about the document as XML"""
390:
391: if not self.digilibBaseUrl:
392: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
393:
394: docinfo = self.getDocinfo(mode=mode,url=url)
395: pt = getattr(self.template, 'info_xml')
396: return pt(docinfo=docinfo)
397:
398:
399: def isAccessible(self, docinfo):
400: """returns if access to the resource is granted"""
401: access = docinfo.get('accessType', None)
402: logging.debug("documentViewer (accessOK) access type %s"%access)
403: if access is not None and access == 'free':
404: logging.debug("documentViewer (accessOK) access is free")
405: return True
406: elif access is None or access in self.authgroups:
407: # only local access -- only logged in users
408: user = getSecurityManager().getUser()
409: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
410: if user is not None:
411: #print "user: ", user
412: return (user.getUserName() != "Anonymous User")
413: else:
414: return False
415:
416: logging.error("documentViewer (accessOK) unknown access type %s"%access)
417: return False
418:
419:
420: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
421: """gibt param von dlInfo aus"""
422: if docinfo is None:
423: docinfo = {}
424:
425: for x in range(cut):
426:
427: path=getParentDir(path)
428:
429: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
430:
431: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
432:
433: txt = getHttpData(infoUrl)
434: if txt is None:
435: raise IOError("Unable to get dir-info from %s"%(infoUrl))
436:
437: dom = Parse(txt)
438: sizes=dom.xpath("//dir/size")
439: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
440:
441: if sizes:
442: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
443: else:
444: docinfo['numPages'] = 0
445:
446: # TODO: produce and keep list of image names and numbers
447:
448: return docinfo
449:
450: def getIndexMetaPath(self,url):
451: """gib nur den Pfad zurueck"""
452: regexp = re.compile(r".*(experimental|permanent)/(.*)")
453: regpath = regexp.match(url)
454: if (regpath==None):
455: return ""
456: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
457: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
458:
459:
460:
461: def getIndexMetaUrl(self,url):
462: """returns utr of index.meta document at url"""
463:
464: metaUrl = None
465: if url.startswith("http://"):
466: # real URL
467: metaUrl = url
468: else:
469: # online path
470: server=self.digilibBaseUrl+"/servlet/Texter?fn="
471: metaUrl=server+url.replace("/mpiwg/online","")
472: if not metaUrl.endswith("index.meta"):
473: metaUrl += "/index.meta"
474:
475: return metaUrl
476:
477: def getDomFromIndexMeta(self, url):
478: """get dom from index meta"""
479: dom = None
480: metaUrl = self.getIndexMetaUrl(url)
481:
482: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
483: txt=getHttpData(metaUrl)
484: if txt is None:
485: raise IOError("Unable to read index meta from %s"%(url))
486:
487: dom = Parse(txt)
488: return dom
489:
490: def getPresentationInfoXML(self, url):
491: """returns dom of info.xml document at url"""
492: dom = None
493: metaUrl = None
494: if url.startswith("http://"):
495: # real URL
496: metaUrl = url
497: else:
498: # online path
499: server=self.digilibBaseUrl+"/servlet/Texter?fn="
500: metaUrl=server+url.replace("/mpiwg/online","")
501:
502: txt=getHttpData(metaUrl)
503: if txt is None:
504: raise IOError("Unable to read infoXMLfrom %s"%(url))
505:
506: dom = Parse(txt)
507: return dom
508:
509:
510: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
511: """gets authorization info from the index.meta file at path or given by dom"""
512: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
513:
514: access = None
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: acctype = dom.xpath("//access-conditions/access/@type")
525: if acctype and (len(acctype)>0):
526: access=acctype[0].value
527: if access in ['group', 'institution']:
528: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
529:
530: docinfo['accessType'] = access
531: return docinfo
532:
533:
534: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
535: """gets bibliographical info from the index.meta file at path or given by dom"""
536: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
537:
538: if docinfo is None:
539: docinfo = {}
540:
541: if dom is None:
542: for x in range(cut):
543: path=getParentDir(path)
544: dom = self.getDomFromIndexMeta(path)
545:
546: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
547:
548: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
549: # put in all raw bib fields as dict "bib"
550: bib = dom.xpath("//bib/*")
551: if bib and len(bib)>0:
552: bibinfo = {}
553: for e in bib:
554: bibinfo[e.localName] = getTextFromNode(e)
555: docinfo['bib'] = bibinfo
556:
557: # extract some fields (author, title, year) according to their mapping
558: metaData=self.metadata.main.meta.bib
559: bibtype=dom.xpath("//bib/@type")
560: if bibtype and (len(bibtype)>0):
561: bibtype=bibtype[0].value
562: else:
563: bibtype="generic"
564:
565: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
566: docinfo['bib_type'] = bibtype
567: bibmap=metaData.generateMappingForType(bibtype)
568: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
569: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
570: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
571: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
572: try:
573: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
574: except: pass
575: try:
576: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
577: except: pass
578: try:
579: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
580: except: pass
581: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
582: try:
583: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
584: except:
585: docinfo['lang']=''
586:
587: return docinfo
588:
589:
590: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
591: """gets name info from the index.meta file at path or given by dom"""
592: if docinfo is None:
593: docinfo = {}
594:
595: if dom is None:
596: for x in range(cut):
597: path=getParentDir(path)
598: dom = self.getDomFromIndexMeta(path)
599:
600: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
601: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
602: return docinfo
603:
604: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
605: """parse texttool tag in index meta"""
606: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
607: if docinfo is None:
608: docinfo = {}
609: if docinfo.get('lang', None) is None:
610: docinfo['lang'] = '' # default keine Sprache gesetzt
611: if dom is None:
612: dom = self.getDomFromIndexMeta(url)
613:
614: archivePath = None
615: archiveName = None
616:
617: archiveNames = dom.xpath("//resource/name")
618: if archiveNames and (len(archiveNames) > 0):
619: archiveName = getTextFromNode(archiveNames[0])
620: else:
621: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
622:
623: archivePaths = dom.xpath("//resource/archive-path")
624: if archivePaths and (len(archivePaths) > 0):
625: archivePath = getTextFromNode(archivePaths[0])
626: # clean up archive path
627: if archivePath[0] != '/':
628: archivePath = '/' + archivePath
629: if archiveName and (not archivePath.endswith(archiveName)):
630: archivePath += "/" + archiveName
631: else:
632: # try to get archive-path from url
633: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
634: if (not url.startswith('http')):
635: archivePath = url.replace('index.meta', '')
636:
637: if archivePath is None:
638: # we balk without archive-path
639: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
640:
641: imageDirs = dom.xpath("//texttool/image")
642: if imageDirs and (len(imageDirs) > 0):
643: imageDir = getTextFromNode(imageDirs[0])
644:
645: else:
646: # we balk with no image tag / not necessary anymore because textmode is now standard
647: #raise IOError("No text-tool info in %s"%(url))
648: imageDir = ""
649: #xquery="//pb"
650: docinfo['imagePath'] = "" # keine Bilder
651: docinfo['imageURL'] = ""
652:
653: if imageDir and archivePath:
654: #print "image: ", imageDir, " archivepath: ", archivePath
655: imageDir = os.path.join(archivePath, imageDir)
656: imageDir = imageDir.replace("/mpiwg/online", '')
657: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
658: docinfo['imagePath'] = imageDir
659:
660: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
661:
662: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
663: if viewerUrls and (len(viewerUrls) > 0):
664: viewerUrl = getTextFromNode(viewerUrls[0])
665: docinfo['viewerURL'] = viewerUrl
666:
667: # old style text URL
668: textUrls = dom.xpath("//texttool/text")
669: if textUrls and (len(textUrls) > 0):
670: textUrl = getTextFromNode(textUrls[0])
671: if urlparse.urlparse(textUrl)[0] == "": #keine url
672: textUrl = os.path.join(archivePath, textUrl)
673: # fix URLs starting with /mpiwg/online
674: if textUrl.startswith("/mpiwg/online"):
675: textUrl = textUrl.replace("/mpiwg/online", '', 1)
676:
677: docinfo['textURL'] = textUrl
678:
679: # new style text-url-path
680: textUrls = dom.xpath("//texttool/text-url-path")
681: if textUrls and (len(textUrls) > 0):
682: textUrl = getTextFromNode(textUrls[0])
683: docinfo['textURLPath'] = textUrl
684: if not docinfo['imagePath']:
685: # text-only, no page images
686: docinfo = self.getNumTextPages(docinfo)
687:
688: presentationUrls = dom.xpath("//texttool/presentation")
689: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
690: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
691:
692:
693: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
694: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
695: # durch den relativen Pfad auf die presentation infos
696: presentationPath = getTextFromNode(presentationUrls[0])
697: if url.endswith("index.meta"):
698: presentationUrl = url.replace('index.meta', presentationPath)
699: else:
700: presentationUrl = url + "/" + presentationPath
701:
702: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
703:
704: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
705:
706: return docinfo
707:
708:
709: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
710: """gets the bibliographical information from the preseantion entry in texttools
711: """
712: dom=self.getPresentationInfoXML(url)
713: try:
714: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
715: except:
716: pass
717: try:
718: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
719: except:
720: pass
721: try:
722: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
723: except:
724: pass
725: return docinfo
726:
727: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
728: """path ist the path to the images it assumes that the index.meta file is one level higher."""
729: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
730: if docinfo is None:
731: docinfo = {}
732: path=path.replace("/mpiwg/online","")
733: docinfo['imagePath'] = path
734: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
735:
736: pathorig=path
737: for x in range(cut):
738: path=getParentDir(path)
739: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
740: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
741: docinfo['imageURL'] = imageUrl
742:
743: #path ist the path to the images it assumes that the index.meta file is one level higher.
744: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
745: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
746: return docinfo
747:
748:
749: def getDocinfo(self, mode, url):
750: """returns docinfo depending on mode"""
751: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
752: # look for cached docinfo in session
753: if self.REQUEST.SESSION.has_key('docinfo'):
754: docinfo = self.REQUEST.SESSION['docinfo']
755: # check if its still current
756: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
757: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
758: return docinfo
759: # new docinfo
760: docinfo = {'mode': mode, 'url': url}
761: if mode=="texttool": #index.meta with texttool information
762: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
763: elif mode=="imagepath":
764: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
765: elif mode=="filepath":
766: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
767: else:
768: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
769: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
770:
771: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
772: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
773: self.REQUEST.SESSION['docinfo'] = docinfo
774: return docinfo
775:
776: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
777: """returns pageinfo with the given parameters"""
778: pageinfo = {}
779: current = getInt(current)
780:
781: pageinfo['current'] = current
782: rows = int(rows or self.thumbrows)
783: pageinfo['rows'] = rows
784: cols = int(cols or self.thumbcols)
785: pageinfo['cols'] = cols
786: grpsize = cols * rows
787: pageinfo['groupsize'] = grpsize
788: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
789: # int(current / grpsize) * grpsize +1))
790: pageinfo['start'] = start
791: pageinfo['end'] = start + grpsize
792: if (docinfo is not None) and ('numPages' in docinfo):
793: np = int(docinfo['numPages'])
794: pageinfo['end'] = min(pageinfo['end'], np)
795: pageinfo['numgroups'] = int(np / grpsize)
796: if np % grpsize > 0:
797: pageinfo['numgroups'] += 1
798: pageinfo['viewMode'] = viewMode
799: pageinfo['tocMode'] = tocMode
800: #pageinfo ['originalPage'] = self.getOrigPages(docinfo=None, pageinfo=None)
801: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','')
802: pageinfo['query'] = self.REQUEST.get('query','')
803: pageinfo['queryType'] = self.REQUEST.get('queryType','')
804: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
805: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
806: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
807: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
808: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
809: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
810: toc = int (pageinfo['tocPN'])
811: pageinfo['textPages'] =int (toc)
812:
813:
814:
815: if 'tocSize_%s'%tocMode in docinfo:
816: tocSize = int(docinfo['tocSize_%s'%tocMode])
817: tocPageSize = int(pageinfo['tocPageSize'])
818: # cached toc
819: if tocSize%tocPageSize>0:
820: tocPages=tocSize/tocPageSize+1
821: else:
822: tocPages=tocSize/tocPageSize
823: pageinfo['tocPN'] = min (tocPages,toc)
824: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
825: pageinfo['sn'] =self.REQUEST.get('sn','')
826: return pageinfo
827:
828: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
829: """init document viewer"""
830: self.title=title
831: self.digilibBaseUrl = digilibBaseUrl
832: self.thumbrows = thumbrows
833: self.thumbcols = thumbcols
834: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
835: if RESPONSE is not None:
836: RESPONSE.redirect('manage_main')
837:
838: def manage_AddDocumentViewerForm(self):
839: """add the viewer form"""
840: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
841: return pt()
842:
843: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
844: """add the viewer"""
845: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
846: self._setObject(id,newObj)
847:
848: if RESPONSE is not None:
849: RESPONSE.redirect('manage_main')
850:
851: ## DocumentViewerTemplate class
852: class DocumentViewerTemplate(ZopePageTemplate):
853: """Template for document viewer"""
854: meta_type="DocumentViewer Template"
855:
856:
857: def manage_addDocumentViewerTemplateForm(self):
858: """Form for adding"""
859: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
860: return pt()
861:
862: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
863: REQUEST=None, submit=None):
864: "Add a Page Template with optional file content."
865:
866: self._setObject(id, DocumentViewerTemplate(id))
867: ob = getattr(self, id)
868: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
869: logging.info("txt %s:"%txt)
870: ob.pt_edit(txt,"text/html")
871: if title:
872: ob.pt_setTitle(title)
873: try:
874: u = self.DestinationURL()
875: except AttributeError:
876: u = REQUEST['URL1']
877:
878: u = "%s/%s" % (u, urllib.quote(id))
879: REQUEST.RESPONSE.redirect(u+'/manage_main')
880: return ''
881:
882:
883:
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