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: pt = getattr(self.template, 'thumbs_main_rss')
248:
249: if viewMode=="auto": # automodus gewaehlt
250: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
251: viewMode="text"
252: else:
253: viewMode="images"
254:
255: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
256:
257: security.declareProtected('View','index_html')
258: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
259: '''
260: view it
261: @param mode: defines how to access the document behind url
262: @param url: url which contains display information
263: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
264: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
265: @param characterNormalization type of text display (reg, norm, none)
266: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
267: '''
268:
269: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
270:
271: if not hasattr(self, 'template'):
272: # this won't work
273: logging.error("template folder missing!")
274: return "ERROR: template folder missing!"
275:
276: if not getattr(self, 'digilibBaseUrl', None):
277: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
278:
279: docinfo = self.getDocinfo(mode=mode,url=url)
280:
281: if tocMode != "thumbs":
282: # get table of contents
283: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
284:
285: if viewMode=="auto": # automodus gewaehlt
286: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
287: viewMode="text_dict"
288: else:
289: viewMode="images"
290:
291: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
292:
293: pt = getattr(self.template, 'viewer_main')
294: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
295:
296: def generateMarks(self,mk):
297: ret=""
298: if mk is None:
299: return ""
300: if not isinstance(mk, list):
301: mk=[mk]
302: for m in mk:
303: ret+="mk=%s"%m
304: return ret
305:
306:
307: def findDigilibUrl(self):
308: """try to get the digilib URL from zogilib"""
309: url = self.template.zogilib.getDLBaseUrl()
310: return url
311:
312: def getDocumentViewerURL(self):
313: """returns the URL of this instance"""
314: return self.absolute_url()
315:
316: def getStyle(self, idx, selected, style=""):
317: """returns a string with the given style and append 'sel' if path == selected."""
318: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
319: if idx == selected:
320: return style + 'sel'
321: else:
322: return style
323:
324: def getLink(self,param=None,val=None):
325: """link to documentviewer with parameter param set to val"""
326: params=self.REQUEST.form.copy()
327: if param is not None:
328: if val is None:
329: if params.has_key(param):
330: del params[param]
331: else:
332: params[param] = str(val)
333:
334: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
335: params["mode"] = "imagepath"
336: params["url"] = getParentDir(params["url"])
337:
338: # quote values and assemble into query string
339: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
340: ps = urllib.urlencode(params)
341: url=self.REQUEST['URL1']+"?"+ps
342: return url
343:
344: def getLinkAmp(self,param=None,val=None):
345: """link to documentviewer with parameter param set to val"""
346: params=self.REQUEST.form.copy()
347: if param is not None:
348: if val is None:
349: if params.has_key(param):
350: del params[param]
351: else:
352: params[param] = str(val)
353:
354: # quote values and assemble into query string
355: logging.debug("XYXXXXX: %s"%repr(params.items()))
356: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
357: url=self.REQUEST['URL1']+"?"+ps
358: return url
359:
360: def getInfo_xml(self,url,mode):
361: """returns info about the document as XML"""
362:
363: if not self.digilibBaseUrl:
364: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
365:
366: docinfo = self.getDocinfo(mode=mode,url=url)
367: pt = getattr(self.template, 'info_xml')
368: return pt(docinfo=docinfo)
369:
370:
371: def isAccessible(self, docinfo):
372: """returns if access to the resource is granted"""
373: access = docinfo.get('accessType', None)
374: logging.debug("documentViewer (accessOK) access type %s"%access)
375: if access is not None and access == 'free':
376: logging.debug("documentViewer (accessOK) access is free")
377: return True
378: elif access is None or access in self.authgroups:
379: # only local access -- only logged in users
380: user = getSecurityManager().getUser()
381: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
382: if user is not None:
383: #print "user: ", user
384: return (user.getUserName() != "Anonymous User")
385: else:
386: return False
387:
388: logging.error("documentViewer (accessOK) unknown access type %s"%access)
389: return False
390:
391:
392: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
393: """gibt param von dlInfo aus"""
394: if docinfo is None:
395: docinfo = {}
396:
397: for x in range(cut):
398:
399: path=getParentDir(path)
400:
401: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
402:
403: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
404:
405: txt = getHttpData(infoUrl)
406: if txt is None:
407: raise IOError("Unable to get dir-info from %s"%(infoUrl))
408:
409: dom = Parse(txt)
410: sizes=dom.xpath("//dir/size")
411: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
412:
413: if sizes:
414: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
415: else:
416: docinfo['numPages'] = 0
417:
418: # TODO: produce and keep list of image names and numbers
419:
420: return docinfo
421:
422: def getIndexMetaPath(self,url):
423: """gib nur den Pfad zurueck"""
424: regexp = re.compile(r".*(experimental|permanent)/(.*)")
425: regpath = regexp.match(url)
426: if (regpath==None):
427: return ""
428: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
429: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
430:
431:
432:
433: def getIndexMetaUrl(self,url):
434: """returns utr of index.meta document at url"""
435:
436: metaUrl = None
437: if url.startswith("http://"):
438: # real URL
439: metaUrl = url
440: else:
441: # online path
442: server=self.digilibBaseUrl+"/servlet/Texter?fn="
443: metaUrl=server+url.replace("/mpiwg/online","")
444: if not metaUrl.endswith("index.meta"):
445: metaUrl += "/index.meta"
446:
447: return metaUrl
448:
449: def getDomFromIndexMeta(self, url):
450: """get dom from index meta"""
451: dom = None
452: metaUrl = self.getIndexMetaUrl(url)
453:
454: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
455: txt=getHttpData(metaUrl)
456: if txt is None:
457: raise IOError("Unable to read index meta from %s"%(url))
458:
459: dom = Parse(txt)
460: return dom
461:
462: def getPresentationInfoXML(self, url):
463: """returns dom of info.xml document at url"""
464: dom = None
465: metaUrl = None
466: if url.startswith("http://"):
467: # real URL
468: metaUrl = url
469: else:
470: # online path
471: server=self.digilibBaseUrl+"/servlet/Texter?fn="
472: metaUrl=server+url.replace("/mpiwg/online","")
473:
474: txt=getHttpData(metaUrl)
475: if txt is None:
476: raise IOError("Unable to read infoXMLfrom %s"%(url))
477:
478: dom = Parse(txt)
479: return dom
480:
481:
482: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
483: """gets authorization info from the index.meta file at path or given by dom"""
484: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
485:
486: access = None
487:
488: if docinfo is None:
489: docinfo = {}
490:
491: if dom is None:
492: for x in range(cut):
493: path=getParentDir(path)
494: dom = self.getDomFromIndexMeta(path)
495:
496: acctype = dom.xpath("//access-conditions/access/@type")
497: if acctype and (len(acctype)>0):
498: access=acctype[0].value
499: if access in ['group', 'institution']:
500: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
501:
502: docinfo['accessType'] = access
503: return docinfo
504:
505:
506: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
507: """gets bibliographical info from the index.meta file at path or given by dom"""
508: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
509:
510: if docinfo is None:
511: docinfo = {}
512:
513: if dom is None:
514: for x in range(cut):
515: path=getParentDir(path)
516: dom = self.getDomFromIndexMeta(path)
517:
518: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
519:
520: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
521: # put in all raw bib fields as dict "bib"
522: bib = dom.xpath("//bib/*")
523: if bib and len(bib)>0:
524: bibinfo = {}
525: for e in bib:
526: bibinfo[e.localName] = getTextFromNode(e)
527: docinfo['bib'] = bibinfo
528:
529: # extract some fields (author, title, year) according to their mapping
530: metaData=self.metadata.main.meta.bib
531: bibtype=dom.xpath("//bib/@type")
532: if bibtype and (len(bibtype)>0):
533: bibtype=bibtype[0].value
534: else:
535: bibtype="generic"
536:
537: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
538: docinfo['bib_type'] = bibtype
539: bibmap=metaData.generateMappingForType(bibtype)
540: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
541: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
542: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
543: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
544: try:
545: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
546: except: pass
547: try:
548: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
549: except: pass
550: try:
551: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
552: except: pass
553: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
554: try:
555: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
556: except:
557: docinfo['lang']=''
558:
559: return docinfo
560:
561:
562: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
563: """gets name info from the index.meta file at path or given by dom"""
564: if docinfo is None:
565: docinfo = {}
566:
567: if dom is None:
568: for x in range(cut):
569: path=getParentDir(path)
570: dom = self.getDomFromIndexMeta(path)
571:
572: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
573: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
574: return docinfo
575:
576: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
577: """parse texttool tag in index meta"""
578: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
579: if docinfo is None:
580: docinfo = {}
581: if docinfo.get('lang', None) is None:
582: docinfo['lang'] = '' # default keine Sprache gesetzt
583: if dom is None:
584: dom = self.getDomFromIndexMeta(url)
585:
586: archivePath = None
587: archiveName = None
588:
589: archiveNames = dom.xpath("//resource/name")
590: if archiveNames and (len(archiveNames) > 0):
591: archiveName = getTextFromNode(archiveNames[0])
592: else:
593: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
594:
595: archivePaths = dom.xpath("//resource/archive-path")
596: if archivePaths and (len(archivePaths) > 0):
597: archivePath = getTextFromNode(archivePaths[0])
598: # clean up archive path
599: if archivePath[0] != '/':
600: archivePath = '/' + archivePath
601: if archiveName and (not archivePath.endswith(archiveName)):
602: archivePath += "/" + archiveName
603: else:
604: # try to get archive-path from url
605: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
606: if (not url.startswith('http')):
607: archivePath = url.replace('index.meta', '')
608:
609: if archivePath is None:
610: # we balk without archive-path
611: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
612:
613: imageDirs = dom.xpath("//texttool/image")
614: if imageDirs and (len(imageDirs) > 0):
615: imageDir = getTextFromNode(imageDirs[0])
616:
617: else:
618: # we balk with no image tag / not necessary anymore because textmode is now standard
619: #raise IOError("No text-tool info in %s"%(url))
620: imageDir = ""
621: #xquery="//pb"
622: docinfo['imagePath'] = "" # keine Bilder
623: docinfo['imageURL'] = ""
624:
625: if imageDir and archivePath:
626: #print "image: ", imageDir, " archivepath: ", archivePath
627: imageDir = os.path.join(archivePath, imageDir)
628: imageDir = imageDir.replace("/mpiwg/online", '')
629: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
630: docinfo['imagePath'] = imageDir
631:
632: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
633:
634: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
635: if viewerUrls and (len(viewerUrls) > 0):
636: viewerUrl = getTextFromNode(viewerUrls[0])
637: docinfo['viewerURL'] = viewerUrl
638:
639: # old style text URL
640: textUrls = dom.xpath("//texttool/text")
641: if textUrls and (len(textUrls) > 0):
642: textUrl = getTextFromNode(textUrls[0])
643: if urlparse.urlparse(textUrl)[0] == "": #keine url
644: textUrl = os.path.join(archivePath, textUrl)
645: # fix URLs starting with /mpiwg/online
646: if textUrl.startswith("/mpiwg/online"):
647: textUrl = textUrl.replace("/mpiwg/online", '', 1)
648:
649: docinfo['textURL'] = textUrl
650:
651: # new style text-url-path
652: textUrls = dom.xpath("//texttool/text-url-path")
653: if textUrls and (len(textUrls) > 0):
654: textUrl = getTextFromNode(textUrls[0])
655: docinfo['textURLPath'] = textUrl
656: if not docinfo['imagePath']:
657: # text-only, no page images
658: docinfo = self.getNumTextPages(docinfo)
659:
660: presentationUrls = dom.xpath("//texttool/presentation")
661: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
662: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
663:
664: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
665: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
666: # durch den relativen Pfad auf die presentation infos
667: presentationPath = getTextFromNode(presentationUrls[0])
668: if url.endswith("index.meta"):
669: presentationUrl = url.replace('index.meta', presentationPath)
670: else:
671: presentationUrl = url + "/" + presentationPath
672:
673: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
674:
675: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
676:
677: return docinfo
678:
679:
680: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
681: """gets the bibliographical information from the preseantion entry in texttools
682: """
683: dom=self.getPresentationInfoXML(url)
684: try:
685: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
686: except:
687: pass
688: try:
689: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
690: except:
691: pass
692: try:
693: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
694: except:
695: pass
696: return docinfo
697:
698: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
699: """path ist the path to the images it assumes that the index.meta file is one level higher."""
700: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
701: if docinfo is None:
702: docinfo = {}
703: path=path.replace("/mpiwg/online","")
704: docinfo['imagePath'] = path
705: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
706:
707: pathorig=path
708: for x in range(cut):
709: path=getParentDir(path)
710: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
711: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
712: docinfo['imageURL'] = imageUrl
713:
714: #path ist the path to the images it assumes that the index.meta file is one level higher.
715: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
716: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
717: return docinfo
718:
719:
720: def getDocinfo(self, mode, url):
721: """returns docinfo depending on mode"""
722: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
723: # look for cached docinfo in session
724: if self.REQUEST.SESSION.has_key('docinfo'):
725: docinfo = self.REQUEST.SESSION['docinfo']
726: # check if its still current
727: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
728: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
729: return docinfo
730: # new docinfo
731: docinfo = {'mode': mode, 'url': url}
732: if mode=="texttool": #index.meta with texttool information
733: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
734: elif mode=="imagepath":
735: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
736: elif mode=="filepath":
737: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
738: else:
739: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
740: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
741:
742: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
743: self.REQUEST.SESSION['docinfo'] = docinfo
744: return docinfo
745:
746: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
747: """returns pageinfo with the given parameters"""
748: pageinfo = {}
749: current = getInt(current)
750: #pageinfo ['originalPage'] = originalPage
751: pageinfo['current'] = current
752: rows = int(rows or self.thumbrows)
753: pageinfo['rows'] = rows
754: cols = int(cols or self.thumbcols)
755: pageinfo['cols'] = cols
756: grpsize = cols * rows
757: pageinfo['groupsize'] = grpsize
758: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
759: # int(current / grpsize) * grpsize +1))
760: pageinfo['start'] = start
761: pageinfo['end'] = start + grpsize
762: if (docinfo is not None) and ('numPages' in docinfo):
763: np = int(docinfo['numPages'])
764: pageinfo['end'] = min(pageinfo['end'], np)
765: pageinfo['numgroups'] = int(np / grpsize)
766: if np % grpsize > 0:
767: pageinfo['numgroups'] += 1
768: pageinfo['viewMode'] = viewMode
769: pageinfo['tocMode'] = tocMode
770: #pageinfo['characterNormalization'] =characterNormalization
771: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
772: pageinfo['query'] = self.REQUEST.get('query',' ')
773: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
774: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
775: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
776: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
777: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
778: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
779: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
780: toc = int (pageinfo['tocPN'])
781: pageinfo['textPages'] =int (toc)
782:
783:
784:
785: if 'tocSize_%s'%tocMode in docinfo:
786: tocSize = int(docinfo['tocSize_%s'%tocMode])
787: tocPageSize = int(pageinfo['tocPageSize'])
788: # cached toc
789: if tocSize%tocPageSize>0:
790: tocPages=tocSize/tocPageSize+1
791: else:
792: tocPages=tocSize/tocPageSize
793: pageinfo['tocPN'] = min (tocPages,toc)
794: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
795: pageinfo['sn'] =self.REQUEST.get('sn','')
796: return pageinfo
797:
798: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
799: """init document viewer"""
800: self.title=title
801: self.digilibBaseUrl = digilibBaseUrl
802: self.thumbrows = thumbrows
803: self.thumbcols = thumbcols
804: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
805: if RESPONSE is not None:
806: RESPONSE.redirect('manage_main')
807:
808: def manage_AddDocumentViewerForm(self):
809: """add the viewer form"""
810: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
811: return pt()
812:
813: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
814: """add the viewer"""
815: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
816: self._setObject(id,newObj)
817:
818: if RESPONSE is not None:
819: RESPONSE.redirect('manage_main')
820:
821: ## DocumentViewerTemplate class
822: class DocumentViewerTemplate(ZopePageTemplate):
823: """Template for document viewer"""
824: meta_type="DocumentViewer Template"
825:
826:
827: def manage_addDocumentViewerTemplateForm(self):
828: """Form for adding"""
829: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
830: return pt()
831:
832: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
833: REQUEST=None, submit=None):
834: "Add a Page Template with optional file content."
835:
836: self._setObject(id, DocumentViewerTemplate(id))
837: ob = getattr(self, id)
838: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
839: logging.info("txt %s:"%txt)
840: ob.pt_edit(txt,"text/html")
841: if title:
842: ob.pt_setTitle(title)
843: try:
844: u = self.DestinationURL()
845: except AttributeError:
846: u = REQUEST['URL1']
847:
848: u = "%s/%s" % (u, urllib.quote(id))
849: REQUEST.RESPONSE.redirect(u+'/manage_main')
850: return ''
851:
852:
853:
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