1:
2: from OFS.Folder import Folder
3: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
4: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
5: from AccessControl import ClassSecurityInfo
6: from AccessControl import getSecurityManager
7: from Globals import package_home
8: from Products.zogiLib.zogiLib import browserCheck
9:
10: from Ft.Xml import EMPTY_NAMESPACE, Parse
11: import Ft.Xml.Domlette
12: import os.path
13: import sys
14: import urllib
15: import urllib2
16: import logging
17: import math
18: import urlparse
19: import cStringIO
20: import re
21:
22:
23: def logger(txt,method,txt2):
24: """logging"""
25: logging.info(txt+ txt2)
26:
27:
28: def getInt(number, default=0):
29: """returns always an int (0 in case of problems)"""
30: try:
31: return int(number)
32: except:
33: return int(default)
34:
35: def getTextFromNode(nodename):
36: """get the cdata content of a node"""
37: if nodename is None:
38: return ""
39: nodelist=nodename.childNodes
40: rc = ""
41: for node in nodelist:
42: if node.nodeType == node.TEXT_NODE:
43: rc = rc + node.data
44: return rc
45:
46: def serializeNode(node, encoding='utf-8'):
47: """returns a string containing node as XML"""
48: buf = cStringIO.StringIO()
49: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
50: s = buf.getvalue()
51: buf.close()
52: return s
53:
54: def getBrowserType(self):
55: """get browser type object"""
56: if self.REQUEST.SESSION.has_key('browserType'):
57: return self.REQUEST.SESSION['browserType']
58: else:
59: bt = browserCheck(self)
60: self.REQUEST.SESSION.set('browserType', bt)
61: logging.debug("documentViewer (BROWSER TYPE) bt %s"%bt)
62: return bt
63:
64:
65: def getParentDir(path):
66: """returns pathname shortened by one"""
67: return '/'.join(path.split('/')[0:-1])
68:
69:
70: def getHttpData(url, data=None, num_tries=3, timeout=10):
71: """returns result from url+data HTTP request"""
72: # we do GET (by appending data to url)
73: if isinstance(data, str) or isinstance(data, unicode):
74: # if data is string then append
75: url = "%s?%s"%(url,data)
76: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
77: # urlencode
78: url = "%s?%s"%(url,urllib.urlencode(data))
79:
80: response = None
81: errmsg = None
82: for cnt in range(num_tries):
83: try:
84: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
85: if sys.version_info < (2, 6):
86: # set timeout on socket -- ugly :-(
87: import socket
88: socket.setdefaulttimeout(float(timeout))
89: response = urllib2.urlopen(url)
90: else:
91: response = urllib2.urlopen(url,timeout=float(timeout))
92: # check result?
93: break
94: except urllib2.HTTPError, e:
95: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
96: errmsg = str(e)
97: # stop trying
98: break
99: except urllib2.URLError, e:
100: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
101: errmsg = str(e)
102: # stop trying
103: #break
104:
105: if response is not None:
106: data = response.read()
107: response.close()
108: return data
109:
110: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
111: #return None
112:
113:
114:
115: ##
116: ## documentViewer class
117: ##
118: class documentViewer(Folder):
119: """document viewer"""
120: meta_type="Document viewer"
121:
122: security=ClassSecurityInfo()
123: manage_options=Folder.manage_options+(
124: {'label':'main config','action':'changeDocumentViewerForm'},
125: )
126:
127: # templates and forms
128: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
129: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
130: toc_text = PageTemplateFile('zpt/toc_text', globals())
131: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
132: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
133: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
134: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
135: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
136: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
137: head_main = PageTemplateFile('zpt/head_main', globals())
138: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
139: info_xml = PageTemplateFile('zpt/info_xml', globals())
140:
141:
142: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
143: security.declareProtected('View management screens','changeDocumentViewerForm')
144: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
145:
146:
147: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
148: """init document viewer"""
149: self.id=id
150: self.title=title
151: self.thumbcols = thumbcols
152: self.thumbrows = thumbrows
153: # authgroups is list of authorized groups (delimited by ,)
154: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
155: # create template folder so we can always use template.something
156:
157: templateFolder = Folder('template')
158: #self['template'] = templateFolder # Zope-2.12 style
159: self._setObject('template',templateFolder) # old style
160: try:
161: import MpdlXmlTextServer
162: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
163: #templateFolder['fulltextclient'] = xmlRpcClient
164: templateFolder._setObject('fulltextclient',textServer)
165: except Exception, e:
166: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
167: try:
168: from Products.zogiLib.zogiLib import zogiLib
169: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
170: #templateFolder['zogilib'] = zogilib
171: templateFolder._setObject('zogilib',zogilib)
172: except Exception, e:
173: logging.error("Unable to create zogiLib for zogilib: "+str(e))
174:
175:
176: # proxy text server methods to fulltextclient
177: def getTextPage(self, **args):
178: """get page"""
179: return self.template.fulltextclient.getTextPage(**args)
180:
181: def getQuery(self, **args):
182: """get query"""
183: return self.template.fulltextclient.getQuery(**args)
184:
185: def getSearch(self, **args):
186: """get search"""
187: return self.template.fulltextclient.getSearch(**args)
188:
189: def getGisPlaces(self, **args):
190: """get gis places"""
191: return self.template.fulltextclient.getGisPlaces(**args)
192:
193: def getAllGisPlaces(self, **args):
194: """get all gis places """
195: return self.template.fulltextclient.getAllGisPlaces(**args)
196:
197: def getOrigPages(self, **args):
198: """get original page number """
199: return self.template.fulltextclient.getOrigPages(**args)
200:
201: def getNumPages(self, docinfo):
202: """get numpages"""
203: return self.template.fulltextclient.getNumPages(docinfo)
204:
205: def getNumTextPages(self, docinfo):
206: """get numpages text"""
207: return self.template.fulltextclient.getNumTextPages(docinfo)
208:
209: def getTranslate(self, **args):
210: """get translate"""
211: return self.template.fulltextclient.getTranslate(**args)
212:
213: def getLemma(self, **args):
214: """get lemma"""
215: return self.template.fulltextclient.getLemma(**args)
216:
217: def getToc(self, **args):
218: """get toc"""
219: return self.template.fulltextclient.getToc(**args)
220:
221: def getTocPage(self, **args):
222: """get tocpage"""
223: return self.template.fulltextclient.getTocPage(**args)
224:
225:
226: security.declareProtected('View','thumbs_rss')
227: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
228: '''
229: view it
230: @param mode: defines how to access the document behind url
231: @param url: url which contains display information
232: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
233:
234: '''
235: logging.debug("HHHHHHHHHHHHHH:load the rss")
236: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
237:
238: if not hasattr(self, 'template'):
239: # create template folder if it doesn't exist
240: self.manage_addFolder('template')
241:
242: if not self.digilibBaseUrl:
243: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
244:
245: docinfo = self.getDocinfo(mode=mode,url=url)
246: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
247: #pageinfo = self.getPageinfo(start=start,current=pn, originalPage=originalPage, docinfo=docinfo)
248: ''' ZDES '''
249: pt = getattr(self.template, 'thumbs_main_rss')
250:
251: if viewMode=="auto": # automodus gewaehlt
252: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
253: viewMode="text"
254: else:
255: viewMode="images"
256:
257: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
258:
259: security.declareProtected('View','index_html')
260: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
261: '''
262: view it
263: @param mode: defines how to access the document behind url
264: @param url: url which contains display information
265: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
266: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
267: @param characterNormalization type of text display (reg, norm, none)
268: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
269: '''
270:
271: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
272:
273: if not hasattr(self, 'template'):
274: # this won't work
275: logging.error("template folder missing!")
276: return "ERROR: template folder missing!"
277:
278: if not getattr(self, 'digilibBaseUrl', None):
279: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
280:
281: docinfo = self.getDocinfo(mode=mode,url=url)
282:
283: if tocMode != "thumbs":
284: # get table of contents
285: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
286:
287: if viewMode=="auto": # automodus gewaehlt
288: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
289: viewMode="text_dict"
290: else:
291: viewMode="images"
292:
293: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
294:
295: pt = getattr(self.template, 'viewer_main')
296: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
297:
298: def generateMarks(self,mk):
299: ret=""
300: if mk is None:
301: return ""
302: if not isinstance(mk, list):
303: mk=[mk]
304: for m in mk:
305: ret+="mk=%s"%m
306: return ret
307:
308:
309: def findDigilibUrl(self):
310: """try to get the digilib URL from zogilib"""
311: url = self.template.zogilib.getDLBaseUrl()
312: return url
313:
314: def getDocumentViewerURL(self):
315: """returns the URL of this instance"""
316: return self.absolute_url()
317:
318: def getStyle(self, idx, selected, style=""):
319: """returns a string with the given style and append 'sel' if path == selected."""
320: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
321: if idx == selected:
322: return style + 'sel'
323: else:
324: return style
325:
326: def getLink(self,param=None,val=None):
327: """link to documentviewer with parameter param set to val"""
328: params=self.REQUEST.form.copy()
329: if param is not None:
330: if val is None:
331: if params.has_key(param):
332: del params[param]
333: else:
334: params[param] = str(val)
335:
336: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
337: params["mode"] = "imagepath"
338: params["url"] = getParentDir(params["url"])
339:
340: # quote values and assemble into query string
341: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
342: ps = urllib.urlencode(params)
343: url=self.REQUEST['URL1']+"?"+ps
344: return url
345:
346: def getLinkAmp(self,param=None,val=None):
347: """link to documentviewer with parameter param set to val"""
348: params=self.REQUEST.form.copy()
349: if param is not None:
350: if val is None:
351: if params.has_key(param):
352: del params[param]
353: else:
354: params[param] = str(val)
355:
356: # quote values and assemble into query string
357: logging.debug("XYXXXXX: %s"%repr(params.items()))
358: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
359: url=self.REQUEST['URL1']+"?"+ps
360: return url
361:
362: def getInfo_xml(self,url,mode):
363: """returns info about the document as XML"""
364:
365: if not self.digilibBaseUrl:
366: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
367:
368: docinfo = self.getDocinfo(mode=mode,url=url)
369: pt = getattr(self.template, 'info_xml')
370: return pt(docinfo=docinfo)
371:
372:
373: def isAccessible(self, docinfo):
374: """returns if access to the resource is granted"""
375: access = docinfo.get('accessType', None)
376: logging.debug("documentViewer (accessOK) access type %s"%access)
377: if access is not None and access == 'free':
378: logging.debug("documentViewer (accessOK) access is free")
379: return True
380: elif access is None or access in self.authgroups:
381: # only local access -- only logged in users
382: user = getSecurityManager().getUser()
383: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
384: if user is not None:
385: #print "user: ", user
386: return (user.getUserName() != "Anonymous User")
387: else:
388: return False
389:
390: logging.error("documentViewer (accessOK) unknown access type %s"%access)
391: return False
392:
393:
394: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
395: """gibt param von dlInfo aus"""
396: if docinfo is None:
397: docinfo = {}
398:
399: for x in range(cut):
400:
401: path=getParentDir(path)
402:
403: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
404:
405: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
406:
407: txt = getHttpData(infoUrl)
408: if txt is None:
409: raise IOError("Unable to get dir-info from %s"%(infoUrl))
410:
411: dom = Parse(txt)
412: sizes=dom.xpath("//dir/size")
413: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
414:
415: if sizes:
416: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
417: else:
418: docinfo['numPages'] = 0
419:
420: # TODO: produce and keep list of image names and numbers
421:
422: return docinfo
423:
424: def getIndexMetaPath(self,url):
425: """gib nur den Pfad zurueck"""
426: regexp = re.compile(r".*(experimental|permanent)/(.*)")
427: regpath = regexp.match(url)
428: if (regpath==None):
429: return ""
430: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
431: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
432:
433:
434:
435: def getIndexMetaUrl(self,url):
436: """returns utr of index.meta document at url"""
437:
438: metaUrl = None
439: if url.startswith("http://"):
440: # real URL
441: metaUrl = url
442: else:
443: # online path
444: server=self.digilibBaseUrl+"/servlet/Texter?fn="
445: metaUrl=server+url.replace("/mpiwg/online","")
446: if not metaUrl.endswith("index.meta"):
447: metaUrl += "/index.meta"
448:
449: return metaUrl
450:
451: def getDomFromIndexMeta(self, url):
452: """get dom from index meta"""
453: dom = None
454: metaUrl = self.getIndexMetaUrl(url)
455:
456: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
457: txt=getHttpData(metaUrl)
458: if txt is None:
459: raise IOError("Unable to read index meta from %s"%(url))
460:
461: dom = Parse(txt)
462: return dom
463:
464: def getPresentationInfoXML(self, url):
465: """returns dom of info.xml document at url"""
466: dom = None
467: metaUrl = None
468: if url.startswith("http://"):
469: # real URL
470: metaUrl = url
471: else:
472: # online path
473: server=self.digilibBaseUrl+"/servlet/Texter?fn="
474: metaUrl=server+url.replace("/mpiwg/online","")
475:
476: txt=getHttpData(metaUrl)
477: if txt is None:
478: raise IOError("Unable to read infoXMLfrom %s"%(url))
479:
480: dom = Parse(txt)
481: return dom
482:
483:
484: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
485: """gets authorization info from the index.meta file at path or given by dom"""
486: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
487:
488: access = None
489:
490: if docinfo is None:
491: docinfo = {}
492:
493: if dom is None:
494: for x in range(cut):
495: path=getParentDir(path)
496: dom = self.getDomFromIndexMeta(path)
497:
498: acctype = dom.xpath("//access-conditions/access/@type")
499: if acctype and (len(acctype)>0):
500: access=acctype[0].value
501: if access in ['group', 'institution']:
502: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
503:
504: docinfo['accessType'] = access
505: return docinfo
506:
507:
508: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
509: """gets bibliographical info from the index.meta file at path or given by dom"""
510: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
511:
512: if docinfo is None:
513: docinfo = {}
514:
515: if dom is None:
516: for x in range(cut):
517: path=getParentDir(path)
518: dom = self.getDomFromIndexMeta(path)
519:
520: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
521:
522: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
523: # put in all raw bib fields as dict "bib"
524: bib = dom.xpath("//bib/*")
525: if bib and len(bib)>0:
526: bibinfo = {}
527: for e in bib:
528: bibinfo[e.localName] = getTextFromNode(e)
529: docinfo['bib'] = bibinfo
530:
531: # extract some fields (author, title, year) according to their mapping
532: metaData=self.metadata.main.meta.bib
533: bibtype=dom.xpath("//bib/@type")
534: if bibtype and (len(bibtype)>0):
535: bibtype=bibtype[0].value
536: else:
537: bibtype="generic"
538:
539: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
540: docinfo['bib_type'] = bibtype
541: bibmap=metaData.generateMappingForType(bibtype)
542: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
543: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
544: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
545: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
546: try:
547: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
548: except: pass
549: try:
550: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
551: except: pass
552: try:
553: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
554: except: pass
555: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
556: try:
557: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
558: except:
559: docinfo['lang']=''
560:
561: return docinfo
562:
563:
564: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
565: """gets name info from the index.meta file at path or given by dom"""
566: if docinfo is None:
567: docinfo = {}
568:
569: if dom is None:
570: for x in range(cut):
571: path=getParentDir(path)
572: dom = self.getDomFromIndexMeta(path)
573:
574: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
575: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
576: return docinfo
577:
578: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
579: """parse texttool tag in index meta"""
580: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
581: if docinfo is None:
582: docinfo = {}
583: if docinfo.get('lang', None) is None:
584: docinfo['lang'] = '' # default keine Sprache gesetzt
585: if dom is None:
586: dom = self.getDomFromIndexMeta(url)
587:
588: archivePath = None
589: archiveName = None
590:
591: archiveNames = dom.xpath("//resource/name")
592: if archiveNames and (len(archiveNames) > 0):
593: archiveName = getTextFromNode(archiveNames[0])
594: else:
595: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
596:
597: archivePaths = dom.xpath("//resource/archive-path")
598: if archivePaths and (len(archivePaths) > 0):
599: archivePath = getTextFromNode(archivePaths[0])
600: # clean up archive path
601: if archivePath[0] != '/':
602: archivePath = '/' + archivePath
603: if archiveName and (not archivePath.endswith(archiveName)):
604: archivePath += "/" + archiveName
605: else:
606: # try to get archive-path from url
607: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
608: if (not url.startswith('http')):
609: archivePath = url.replace('index.meta', '')
610:
611: if archivePath is None:
612: # we balk without archive-path
613: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
614:
615: imageDirs = dom.xpath("//texttool/image")
616: if imageDirs and (len(imageDirs) > 0):
617: imageDir = getTextFromNode(imageDirs[0])
618:
619: else:
620: # we balk with no image tag / not necessary anymore because textmode is now standard
621: #raise IOError("No text-tool info in %s"%(url))
622: imageDir = ""
623: #xquery="//pb"
624: docinfo['imagePath'] = "" # keine Bilder
625: docinfo['imageURL'] = ""
626:
627: if imageDir and archivePath:
628: #print "image: ", imageDir, " archivepath: ", archivePath
629: imageDir = os.path.join(archivePath, imageDir)
630: imageDir = imageDir.replace("/mpiwg/online", '')
631: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
632: docinfo['imagePath'] = imageDir
633:
634: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
635:
636: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
637: if viewerUrls and (len(viewerUrls) > 0):
638: viewerUrl = getTextFromNode(viewerUrls[0])
639: docinfo['viewerURL'] = viewerUrl
640:
641: # old style text URL
642: textUrls = dom.xpath("//texttool/text")
643: if textUrls and (len(textUrls) > 0):
644: textUrl = getTextFromNode(textUrls[0])
645: if urlparse.urlparse(textUrl)[0] == "": #keine url
646: textUrl = os.path.join(archivePath, textUrl)
647: # fix URLs starting with /mpiwg/online
648: if textUrl.startswith("/mpiwg/online"):
649: textUrl = textUrl.replace("/mpiwg/online", '', 1)
650:
651: docinfo['textURL'] = textUrl
652:
653: # new style text-url-path
654: textUrls = dom.xpath("//texttool/text-url-path")
655: if textUrls and (len(textUrls) > 0):
656: textUrl = getTextFromNode(textUrls[0])
657: docinfo['textURLPath'] = textUrl
658: if not docinfo['imagePath']:
659: # text-only, no page images
660: docinfo = self.getNumTextPages(docinfo)
661:
662: presentationUrls = dom.xpath("//texttool/presentation")
663: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
664: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
665: docinfo =self.getOrigPages(docinfo=docinfo)
666:
667: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
668: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
669: # durch den relativen Pfad auf die presentation infos
670: presentationPath = getTextFromNode(presentationUrls[0])
671: if url.endswith("index.meta"):
672: presentationUrl = url.replace('index.meta', presentationPath)
673: else:
674: presentationUrl = url + "/" + presentationPath
675:
676: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
677:
678: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
679:
680: return docinfo
681:
682:
683: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
684: """gets the bibliographical information from the preseantion entry in texttools
685: """
686: dom=self.getPresentationInfoXML(url)
687: try:
688: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
689: except:
690: pass
691: try:
692: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
693: except:
694: pass
695: try:
696: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
697: except:
698: pass
699: return docinfo
700:
701: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
702: """path ist the path to the images it assumes that the index.meta file is one level higher."""
703: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
704: if docinfo is None:
705: docinfo = {}
706: path=path.replace("/mpiwg/online","")
707: docinfo['imagePath'] = path
708: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
709:
710: pathorig=path
711: for x in range(cut):
712: path=getParentDir(path)
713: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
714: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
715: docinfo['imageURL'] = imageUrl
716:
717: #path ist the path to the images it assumes that the index.meta file is one level higher.
718: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
719: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
720: return docinfo
721:
722:
723: def getDocinfo(self, mode, url):
724: """returns docinfo depending on mode"""
725: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
726: # look for cached docinfo in session
727: if self.REQUEST.SESSION.has_key('docinfo'):
728: docinfo = self.REQUEST.SESSION['docinfo']
729: # check if its still current
730: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
731: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
732: return docinfo
733: # new docinfo
734: docinfo = {'mode': mode, 'url': url}
735: if mode=="texttool": #index.meta with texttool information
736: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
737: elif mode=="imagepath":
738: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
739: elif mode=="filepath":
740: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
741: else:
742: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
743: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
744:
745: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
746: self.REQUEST.SESSION['docinfo'] = docinfo
747: return docinfo
748:
749: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
750: """returns pageinfo with the given parameters"""
751: pageinfo = {}
752: current = getInt(current)
753: #pageinfo ['originalPage'] = originalPage
754: pageinfo['current'] = current
755: rows = int(rows or self.thumbrows)
756: pageinfo['rows'] = rows
757: cols = int(cols or self.thumbcols)
758: pageinfo['cols'] = cols
759: grpsize = cols * rows
760: pageinfo['groupsize'] = grpsize
761: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
762: # int(current / grpsize) * grpsize +1))
763: pageinfo['start'] = start
764: pageinfo['end'] = start + grpsize
765: if (docinfo is not None) and ('numPages' in docinfo):
766: np = int(docinfo['numPages'])
767: pageinfo['end'] = min(pageinfo['end'], np)
768: pageinfo['numgroups'] = int(np / grpsize)
769: if np % grpsize > 0:
770: pageinfo['numgroups'] += 1
771: pageinfo['viewMode'] = viewMode
772: pageinfo['tocMode'] = tocMode
773: #pageinfo['characterNormalization'] =characterNormalization
774: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
775: pageinfo['query'] = self.REQUEST.get('query',' ')
776: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
777: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
778: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
779: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
780: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
781: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
782: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
783: toc = int (pageinfo['tocPN'])
784: pageinfo['textPages'] =int (toc)
785:
786:
787:
788: if 'tocSize_%s'%tocMode in docinfo:
789: tocSize = int(docinfo['tocSize_%s'%tocMode])
790: tocPageSize = int(pageinfo['tocPageSize'])
791: # cached toc
792: if tocSize%tocPageSize>0:
793: tocPages=tocSize/tocPageSize+1
794: else:
795: tocPages=tocSize/tocPageSize
796: pageinfo['tocPN'] = min (tocPages,toc)
797: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
798: pageinfo['sn'] =self.REQUEST.get('sn','')
799: return pageinfo
800:
801: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
802: """init document viewer"""
803: self.title=title
804: self.digilibBaseUrl = digilibBaseUrl
805: self.thumbrows = thumbrows
806: self.thumbcols = thumbcols
807: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
808: if RESPONSE is not None:
809: RESPONSE.redirect('manage_main')
810:
811: def manage_AddDocumentViewerForm(self):
812: """add the viewer form"""
813: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
814: return pt()
815:
816: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
817: """add the viewer"""
818: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
819: self._setObject(id,newObj)
820:
821: if RESPONSE is not None:
822: RESPONSE.redirect('manage_main')
823:
824: ## DocumentViewerTemplate class
825: class DocumentViewerTemplate(ZopePageTemplate):
826: """Template for document viewer"""
827: meta_type="DocumentViewer Template"
828:
829:
830: def manage_addDocumentViewerTemplateForm(self):
831: """Form for adding"""
832: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
833: return pt()
834:
835: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
836: REQUEST=None, submit=None):
837: "Add a Page Template with optional file content."
838:
839: self._setObject(id, DocumentViewerTemplate(id))
840: ob = getattr(self, id)
841: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
842: logging.info("txt %s:"%txt)
843: ob.pt_edit(txt,"text/html")
844: if title:
845: ob.pt_setTitle(title)
846: try:
847: u = self.DestinationURL()
848: except AttributeError:
849: u = REQUEST['URL1']
850:
851: u = "%s/%s" % (u, urllib.quote(id))
852: REQUEST.RESPONSE.redirect(u+'/manage_main')
853: return ''
854:
855:
856:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>