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