1: from OFS.Folder import Folder
2: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
4: from App.ImageFile import ImageFile
5: #from Products.ZSimpleFile.ZSimpleFile import ZSimpleFile
6: from AccessControl import ClassSecurityInfo
7: from AccessControl import getSecurityManager
8: from Globals import package_home
9:
10: #from Ft.Xml import EMPTY_NAMESPACE, Parse
11: #import Ft.Xml.Domlette
12:
13: import xml.etree.ElementTree as ET
14:
15: import os.path
16: import sys
17: import urllib
18: import logging
19: import math
20: import urlparse
21: import re
22: import string
23:
24: from SrvTxtUtils import getInt, getText, getHttpData
25:
26: def logger(txt,method,txt2):
27: """logging"""
28: logging.info(txt+ txt2)
29:
30:
31: def serializeNode(node, encoding="utf-8"):
32: """returns a string containing node as XML"""
33: s = ET.tostring(node)
34:
35: # 4Suite:
36: # stream = cStringIO.StringIO()
37: # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
38: # s = stream.getvalue()
39: # stream.close()
40: return s
41:
42: def browserCheck(self):
43: """check the browsers request to find out the browser type"""
44: bt = {}
45: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
46: bt['ua'] = ua
47: bt['isIE'] = False
48: bt['isN4'] = False
49: bt['versFirefox']=""
50: bt['versIE']=""
51: bt['versSafariChrome']=""
52: bt['versOpera']=""
53:
54: if string.find(ua, 'MSIE') > -1:
55: bt['isIE'] = True
56: else:
57: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
58: # Safari oder Chrome identification
59: try:
60: nav = ua[string.find(ua, '('):]
61: nav1=ua[string.find(ua,')'):]
62: nav2=nav1[string.find(nav1,'('):]
63: nav3=nav2[string.find(nav2,')'):]
64: ie = string.split(nav, "; ")[1]
65: ie1 =string.split(nav1, " ")[2]
66: ie2 =string.split(nav3, " ")[1]
67: ie3 =string.split(nav3, " ")[2]
68: if string.find(ie3, "Safari") >-1:
69: bt['versSafariChrome']=string.split(ie2, "/")[1]
70: except: pass
71: # IE identification
72: try:
73: nav = ua[string.find(ua, '('):]
74: ie = string.split(nav, "; ")[1]
75: if string.find(ie, "MSIE") > -1:
76: bt['versIE'] = string.split(ie, " ")[1]
77: except:pass
78: # Firefox identification
79: try:
80: nav = ua[string.find(ua, '('):]
81: nav1=ua[string.find(ua,')'):]
82: if string.find(ie1, "Firefox") >-1:
83: nav5= string.split(ie1, "/")[1]
84: logging.debug("FIREFOX: %s"%(nav5))
85: bt['versFirefox']=nav5[0:3]
86: except:pass
87: #Opera identification
88: try:
89: if string.find(ua,"Opera") >-1:
90: nav = ua[string.find(ua, '('):]
91: nav1=nav[string.find(nav,')'):]
92: bt['versOpera']=string.split(nav1,"/")[2]
93: except:pass
94:
95: bt['isMac'] = string.find(ua, 'Macintosh') > -1
96: bt['isWin'] = string.find(ua, 'Windows') > -1
97: bt['isIEWin'] = bt['isIE'] and bt['isWin']
98: bt['isIEMac'] = bt['isIE'] and bt['isMac']
99: bt['staticHTML'] = False
100:
101: return bt
102:
103: def getParentPath(path, cnt=1):
104: """returns pathname shortened by cnt"""
105: # make sure path doesn't end with /
106: path = path.rstrip('/')
107: # split by /, shorten, and reassemble
108: return '/'.join(path.split('/')[0:-cnt])
109:
110:
111: ##
112: ## documentViewer class
113: ##
114: class documentViewer(Folder):
115: """document viewer"""
116: meta_type="Document viewer"
117:
118: security=ClassSecurityInfo()
119: manage_options=Folder.manage_options+(
120: {'label':'main config','action':'changeDocumentViewerForm'},
121: )
122:
123: metadataService = None
124: """MetaDataFolder instance"""
125:
126: # templates and forms
127: viewer_text = PageTemplateFile('zpt/viewer_text', globals())
128: viewer_images = PageTemplateFile('zpt/viewer_images', globals())
129: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
130: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
131: toc_text = PageTemplateFile('zpt/toc_text', globals())
132: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
133: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
134: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
135: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
136: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
137: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
138: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
139: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
140: head_main = PageTemplateFile('zpt/head_main', globals())
141: info_xml = PageTemplateFile('zpt/info_xml', globals())
142: # TODO: can this be nicer?
143: docuviewer_css = ImageFile('css/docuviewer.css',globals())
144:
145:
146: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
147:
148:
149: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
150: """init document viewer"""
151: self.id=id
152: self.title=title
153: self.thumbcols = thumbcols
154: self.thumbrows = thumbrows
155: # authgroups is list of authorized groups (delimited by ,)
156: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
157: # create template folder so we can always use template.something
158:
159: templateFolder = Folder('template')
160: #self['template'] = templateFolder # Zope-2.12 style
161: self._setObject('template',templateFolder) # old style
162: try:
163: import MpdlXmlTextServer
164: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
165: #templateFolder['fulltextclient'] = xmlRpcClient
166: templateFolder._setObject('fulltextclient',textServer)
167: except Exception, e:
168: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
169:
170: try:
171: from Products.zogiLib.zogiLib import zogiLib
172: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
173: #templateFolder['zogilib'] = zogilib
174: templateFolder._setObject('zogilib',zogilib)
175: except Exception, e:
176: logging.error("Unable to create zogiLib for zogilib: "+str(e))
177:
178: try:
179: # assume MetaDataFolder instance is called metadata
180: self.metadataService = getattr(self, 'metadata')
181: except Exception, e:
182: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
183:
184: if digilibBaseUrl is not None:
185: self.digilibBaseUrl = digilibBaseUrl
186:
187:
188: # proxy text server methods to fulltextclient
189: def getTextPage(self, **args):
190: """get page"""
191: return self.template.fulltextclient.getTextPage(**args)
192:
193: def getOrigPages(self, **args):
194: """get page"""
195: return self.template.fulltextclient.getOrigPages(**args)
196:
197: def getOrigPagesNorm(self, **args):
198: """get page"""
199: return self.template.fulltextclient.getOrigPagesNorm(**args)
200:
201: def getQuery(self, **args):
202: """get query in search"""
203: return self.template.fulltextclient.getQuery(**args)
204:
205: def getSearch(self, **args):
206: """get search"""
207: return self.template.fulltextclient.getSearch(**args)
208:
209: def getGisPlaces(self, **args):
210: """get gis places"""
211: return self.template.fulltextclient.getGisPlaces(**args)
212:
213: def getAllGisPlaces(self, **args):
214: """get all gis places """
215: return self.template.fulltextclient.getAllGisPlaces(**args)
216:
217: def getWordInfo(self, **args):
218: """get translate"""
219: return self.template.fulltextclient.getWordInfo(**args)
220:
221: def getLemma(self, **args):
222: """get lemma"""
223: return self.template.fulltextclient.getLemma(**args)
224:
225: def getLemmaQuery(self, **args):
226: """get query"""
227: return self.template.fulltextclient.getLemmaQuery(**args)
228:
229: def getLex(self, **args):
230: """get lex"""
231: return self.template.fulltextclient.getLex(**args)
232:
233: def getToc(self, **args):
234: """get toc"""
235: return self.template.fulltextclient.getToc(**args)
236:
237: def getTocPage(self, **args):
238: """get tocpage"""
239: return self.template.fulltextclient.getTocPage(**args)
240:
241:
242: security.declareProtected('View','thumbs_rss')
243: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
244: '''
245: view it
246: @param mode: defines how to access the document behind url
247: @param url: url which contains display information
248: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
249:
250: '''
251: logging.debug("HHHHHHHHHHHHHH:load the rss")
252: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
253:
254: if not hasattr(self, 'template'):
255: # create template folder if it doesn't exist
256: self.manage_addFolder('template')
257:
258: if not self.digilibBaseUrl:
259: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
260:
261: docinfo = self.getDocinfo(mode=mode,url=url)
262: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
263: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
264: ''' ZDES '''
265: pt = getattr(self.template, 'thumbs_main_rss')
266:
267: if viewMode=="auto": # automodus gewaehlt
268: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
269: viewMode="text"
270: else:
271: viewMode="images"
272:
273: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
274:
275:
276: security.declareProtected('View','index_html')
277: def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1):
278: """
279: view page
280: @param url: url which contains display information
281: @param mode: defines how to access the document behind url
282: @param viewMode: 'images': display images, 'text': display text, default is 'auto'
283: @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text'
284: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
285: """
286:
287: logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewType=%s start=%s pn=%s"%(mode,url,viewMode,viewType,start,pn))
288:
289: if not hasattr(self, 'template'):
290: # this won't work
291: logging.error("template folder missing!")
292: return "ERROR: template folder missing!"
293:
294: if not getattr(self, 'digilibBaseUrl', None):
295: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
296:
297: docinfo = self.getDocinfo(mode=mode,url=url)
298:
299: if tocMode != "thumbs":
300: # get table of contents
301: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
302:
303: # auto viewMode: text if there is a text else images
304: if viewMode=="auto":
305: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
306: viewMode = "text"
307: viewType = "dict"
308: else:
309: viewMode = "images"
310:
311: elif viewMode == "text_dict":
312: # legacy fix
313: viewMode = "text"
314: viewType = "dict"
315:
316: # stringify viewType
317: if isinstance(viewType, list):
318: logging.debug("index_html: viewType is list:%s"%viewType)
319: viewType = ','.join([t for t in viewType if t])
320:
321: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode)
322:
323: # get template /template/viewer_$viewMode
324: pt = getattr(self.template, 'viewer_%s'%viewMode, None)
325: if pt is None:
326: logging.error("No template for viewMode=%s!"%viewMode)
327: # TODO: error page?
328: return "No template for viewMode=%s!"%viewMode
329:
330: # and execute with parameters
331: return pt(docinfo=docinfo, pageinfo=pageinfo)
332:
333: def generateMarks(self,mk):
334: ret=""
335: if mk is None:
336: return ""
337: if not isinstance(mk, list):
338: mk=[mk]
339: for m in mk:
340: ret+="mk=%s"%m
341: return ret
342:
343:
344: def getBrowser(self):
345: """getBrowser the version of browser """
346: bt = browserCheck(self)
347: logging.debug("BROWSER VERSION: %s"%(bt))
348: return bt
349:
350: def findDigilibUrl(self):
351: """try to get the digilib URL from zogilib"""
352: url = self.template.zogilib.getDLBaseUrl()
353: return url
354:
355: def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None):
356: """returns URL to digilib Scaler with params"""
357: url = None
358: if docinfo is not None:
359: url = docinfo.get('imageURL', None)
360:
361: if url is None:
362: url = "%s/servlet/Scaler?"%self.digilibBaseUrl
363: if fn is None and docinfo is not None:
364: fn = docinfo.get('imagePath','')
365:
366: url += "fn=%s"%fn
367:
368: if pn:
369: url += "&pn=%s"%pn
370:
371: url += "&dw=%s&dh=%s"%(dw,dh)
372: return url
373:
374: def getDocumentViewerURL(self):
375: """returns the URL of this instance"""
376: return self.absolute_url()
377:
378: def getStyle(self, idx, selected, style=""):
379: """returns a string with the given style and append 'sel' if idx == selected."""
380: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
381: if idx == selected:
382: return style + 'sel'
383: else:
384: return style
385:
386: def getParams(self, param=None, val=None, params=None, duplicates=None):
387: """returns dict with URL parameters.
388:
389: Takes URL parameters and additionally param=val or dict params.
390: Deletes key if value is None."""
391: # copy existing request params
392: newParams=self.REQUEST.form.copy()
393: # change single param
394: if param is not None:
395: if val is None:
396: if newParams.has_key(param):
397: del newParams[param]
398: else:
399: newParams[param] = str(val)
400:
401: # change more params
402: if params is not None:
403: for (k, v) in params.items():
404: if v is None:
405: # val=None removes param
406: if newParams.has_key(k):
407: del newParams[k]
408:
409: else:
410: newParams[k] = v
411:
412: if duplicates:
413: # eliminate lists (coming from duplicate keys)
414: for (k,v) in newParams.items():
415: if isinstance(v, list):
416: if duplicates == 'comma':
417: # make comma-separated list of non-empty entries
418: newParams[k] = ','.join([t for t in v if t])
419: elif duplicates == 'first':
420: # take first non-empty entry
421: newParams[k] = [t for t in v if t][0]
422:
423: return newParams
424:
425: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'):
426: """returns URL to documentviewer with parameter param set to val or from dict params"""
427: urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates)
428: # quote values and assemble into query string (not escaping '/')
429: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()])
430: if baseUrl is None:
431: baseUrl = self.getDocumentViewerURL()
432:
433: url = "%s?%s"%(baseUrl, ps)
434: return url
435:
436: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'):
437: """link to documentviewer with parameter param set to val"""
438: return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&', duplicates=duplicates)
439:
440:
441: def getInfo_xml(self,url,mode):
442: """returns info about the document as XML"""
443: if not self.digilibBaseUrl:
444: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
445:
446: docinfo = self.getDocinfo(mode=mode,url=url)
447: pt = getattr(self.template, 'info_xml')
448: return pt(docinfo=docinfo)
449:
450: def isAccessible(self, docinfo):
451: """returns if access to the resource is granted"""
452: access = docinfo.get('accessType', None)
453: logging.debug("documentViewer (accessOK) access type %s"%access)
454: if access == 'free':
455: logging.debug("documentViewer (accessOK) access is free")
456: return True
457:
458: elif access is None or access in self.authgroups:
459: # only local access -- only logged in users
460: user = getSecurityManager().getUser()
461: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
462: if user is not None:
463: #print "user: ", user
464: return (user.getUserName() != "Anonymous User")
465: else:
466: return False
467:
468: logging.error("documentViewer (accessOK) unknown access type %s"%access)
469: return False
470:
471:
472:
473: def getDocinfo(self, mode, url):
474: """returns docinfo depending on mode"""
475: logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
476: # look for cached docinfo in session
477: if self.REQUEST.SESSION.has_key('docinfo'):
478: docinfo = self.REQUEST.SESSION['docinfo']
479: # check if its still current
480: if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
481: logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
482: return docinfo
483:
484: # new docinfo
485: docinfo = {'mode': mode, 'url': url}
486: # add self url
487: docinfo['viewerUrl'] = self.getDocumentViewerURL()
488: docinfo['digilibBaseUrl'] = self.digilibBaseUrl
489: # get index.meta DOM
490: docUrl = None
491: metaDom = None
492: if mode=="texttool":
493: # url points to document dir or index.meta
494: metaDom = self.metadataService.getDomFromPathOrUrl(url)
495: docUrl = url.replace('/index.meta', '')
496: if metaDom is None:
497: raise IOError("Unable to find index.meta for mode=texttool!")
498:
499: elif mode=="imagepath":
500: # url points to folder with images, index.meta optional
501: # asssume index.meta in parent dir
502: docUrl = getParentPath(url)
503: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
504:
505: elif mode=="filepath":
506: # url points to image file, index.meta optional
507: # asssume index.meta is two path segments up
508: docUrl = getParentPath(url, 2)
509: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
510:
511: else:
512: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
513: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
514:
515: docinfo['documentUrl'] = docUrl
516: # process index.meta contents
517: if metaDom is not None and metaDom.tag == 'resource':
518: # document directory name and path
519: resource = self.metadataService.getResourceData(dom=metaDom)
520: if resource:
521: docinfo = self.getDocinfoFromResource(docinfo, resource)
522:
523: # texttool info
524: texttool = self.metadataService.getTexttoolData(dom=metaDom)
525: if texttool:
526: docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
527:
528: # bib info
529: bib = self.metadataService.getBibData(dom=metaDom)
530: if bib:
531: docinfo = self.getDocinfoFromBib(docinfo, bib)
532: else:
533: # no bib - try info.xml
534: docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)
535:
536: # auth info
537: access = self.metadataService.getAccessData(dom=metaDom)
538: if access:
539: docinfo = self.getDocinfoFromAccess(docinfo, access)
540:
541: # attribution info
542: attribution = self.metadataService.getAttributionData(dom=metaDom)
543: if attribution:
544: logging.debug("getDocinfo: attribution=%s"%repr(attribution))
545: docinfo['attribution'] = attribution
546: #docinfo = self.getDocinfoFromAccess(docinfo, access)
547:
548: # copyright info
549: copyright = self.metadataService.getCopyrightData(dom=metaDom)
550: if copyright:
551: logging.debug("getDocinfo: copyright=%s"%repr(copyright))
552: docinfo['copyright'] = copyright
553: #docinfo = self.getDocinfoFromAccess(docinfo, access)
554:
555: # image path
556: if mode != 'texttool':
557: # override image path from texttool with url
558: docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)
559:
560: # number of images from digilib
561: if docinfo.get('imagePath', None):
562: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
563: docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
564:
565: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
566: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
567: # store in session
568: self.REQUEST.SESSION['docinfo'] = docinfo
569: return docinfo
570:
571: def getDocinfoFromResource(self, docinfo, resource):
572: """reads contents of resource element into docinfo"""
573: docName = resource.get('name', None)
574: docinfo['documentName'] = docName
575: docPath = resource.get('archive-path', None)
576: if docPath:
577: # clean up document path
578: if docPath[0] != '/':
579: docPath = '/' + docPath
580:
581: if docName and (not docPath.endswith(docName)):
582: docPath += "/" + docName
583:
584: else:
585: # use docUrl as docPath
586: docUrl = docinfo['documentURL']
587: if not docUrl.startswith('http:'):
588: docPath = docUrl
589: if docPath:
590: # fix URLs starting with /mpiwg/online
591: docPath = docPath.replace('/mpiwg/online', '', 1)
592:
593: docinfo['documentPath'] = docPath
594: return docinfo
595:
596: def getDocinfoFromTexttool(self, docinfo, texttool):
597: """reads contents of texttool element into docinfo"""
598: # image dir
599: imageDir = texttool.get('image', None)
600: docPath = docinfo.get('documentPath', None)
601: if imageDir and docPath:
602: #print "image: ", imageDir, " archivepath: ", archivePath
603: imageDir = os.path.join(docPath, imageDir)
604: imageDir = imageDir.replace('/mpiwg/online', '', 1)
605: docinfo['imagePath'] = imageDir
606:
607: # old style text URL
608: textUrl = texttool.get('text', None)
609: if textUrl and docPath:
610: if urlparse.urlparse(textUrl)[0] == "": #keine url
611: textUrl = os.path.join(docPath, textUrl)
612:
613: docinfo['textURL'] = textUrl
614:
615: # new style text-url-path
616: textUrl = texttool.get('text-url-path', None)
617: if textUrl:
618: docinfo['textURLPath'] = textUrl
619:
620: # page flow
621: docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')
622:
623: # odd pages are left
624: docinfo['oddPage'] = texttool.get('odd-scan-position', 'left')
625:
626: # number of title page (0: not defined)
627: docinfo['titlePage'] = texttool.get('title-scan-no', 0)
628:
629: # old presentation stuff
630: presentation = texttool.get('presentation', None)
631: if presentation and docPath:
632: if presentation.startswith('http:'):
633: docinfo['presentationUrl'] = presentation
634: else:
635: docinfo['presentationUrl'] = os.path.join(docPath, presentation)
636:
637:
638: return docinfo
639:
640: def getDocinfoFromBib(self, docinfo, bib):
641: """reads contents of bib element into docinfo"""
642: logging.debug("getDocinfoFromBib bib=%s"%repr(bib))
643: # put all raw bib fields in dict "bib"
644: docinfo['bib'] = bib
645: bibtype = bib.get('@type', None)
646: docinfo['bibType'] = bibtype
647: # also store DC metadata for convenience
648: dc = self.metadataService.getDCMappedData(bib)
649: docinfo['creator'] = dc.get('creator',None)
650: docinfo['title'] = dc.get('title',None)
651: docinfo['date'] = dc.get('date',None)
652: return docinfo
653:
654: def getDocinfoFromAccess(self, docinfo, acc):
655: """reads contents of access element into docinfo"""
656: #TODO: also read resource type
657: logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))
658: try:
659: acctype = acc['@attr']['type']
660: if acctype:
661: access=acctype
662: if access in ['group', 'institution']:
663: access = acc['name'].lower()
664:
665: docinfo['accessType'] = access
666:
667: except:
668: pass
669:
670: return docinfo
671:
672: def getDocinfoFromDigilib(self, docinfo, path):
673: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
674: # fetch data
675: txt = getHttpData(infoUrl)
676: if not txt:
677: logging.error("Unable to get dir-info from %s"%(infoUrl))
678: return docinfo
679:
680: dom = ET.fromstring(txt)
681: size = getText(dom.find("size"))
682: logging.debug("getDocinfoFromDigilib: size=%s"%size)
683: if size:
684: docinfo['numPages'] = int(size)
685: else:
686: docinfo['numPages'] = 0
687:
688: # TODO: produce and keep list of image names and numbers
689: return docinfo
690:
691:
692: def getDocinfoFromPresentationInfoXml(self,docinfo):
693: """gets DC-like bibliographical information from the presentation entry in texttools"""
694: url = docinfo.get('presentationUrl', None)
695: if not url:
696: logging.error("getDocinfoFromPresentation: no URL!")
697: return docinfo
698:
699: dom = None
700: metaUrl = None
701: if url.startswith("http://"):
702: # real URL
703: metaUrl = url
704: else:
705: # online path
706:
707: server=self.digilibBaseUrl+"/servlet/Texter?fn="
708: metaUrl=server+url
709:
710: txt=getHttpData(metaUrl)
711: if txt is None:
712: logging.error("Unable to read info.xml from %s"%(url))
713: return docinfo
714:
715: dom = ET.fromstring(txt)
716: docinfo['creator']=getText(dom.find(".//author"))
717: docinfo['title']=getText(dom.find(".//title"))
718: docinfo['date']=getText(dom.find(".//date"))
719: return docinfo
720:
721:
722: def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None):
723: """returns pageinfo with the given parameters"""
724: logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewType=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewType,tocMode))
725: pageinfo = {}
726: pageinfo['viewMode'] = viewMode
727: pageinfo['viewType'] = viewType
728: pageinfo['tocMode'] = tocMode
729:
730: current = getInt(current)
731: pageinfo['current'] = current
732: pageinfo['pn'] = current
733: rows = int(rows or self.thumbrows)
734: pageinfo['rows'] = rows
735: cols = int(cols or self.thumbcols)
736: pageinfo['cols'] = cols
737: grpsize = cols * rows
738: pageinfo['groupsize'] = grpsize
739: # is start is empty use one around current
740: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
741: # int(current / grpsize) * grpsize +1))
742: pageinfo['start'] = start
743:
744: np = int(docinfo.get('numPages', 0))
745: if np == 0:
746: # numPages unknown - maybe we can get it from text page
747: if docinfo.get('textURLPath', None):
748: # cache text page as well
749: pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=current, docinfo=docinfo, pageinfo=pageinfo)
750: np = int(docinfo.get('numPages', 0))
751:
752: pageinfo['numgroups'] = int(np / grpsize)
753: if np % grpsize > 0:
754: pageinfo['numgroups'] += 1
755:
756: pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl'
757: oddScanLeft = docinfo.get('oddPage', 'left') != 'right'
758: # add zeroth page for two columns
759: pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft))
760: pageinfo['pageZero'] = pageZero
761: pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np)
762:
763: # TODO: do we need this here?
764: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
765: pageinfo['query'] = self.REQUEST.get('query','')
766: pageinfo['queryType'] = self.REQUEST.get('queryType','')
767: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
768: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
769: pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30))
770: pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10))
771: pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1'))
772: pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1'))
773:
774: # limit tocPN
775: if 'tocSize_%s'%tocMode in docinfo:
776: tocSize = docinfo['tocSize_%s'%tocMode]
777: tocPageSize = pageinfo['tocPageSize']
778: # cached toc
779: if tocSize%tocPageSize>0:
780: tocPages=tocSize/tocPageSize+1
781: else:
782: tocPages=tocSize/tocPageSize
783:
784: pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN'])
785:
786: return pageinfo
787:
788:
789: def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0):
790: """returns dict with array of page informations for one screenfull of thumbnails"""
791: batch = {}
792: grpsize = rows * cols
793: if maxIdx == 0:
794: maxIdx = start + grpsize
795:
796: nb = int(math.ceil(maxIdx / float(grpsize)))
797: # list of all batch start and end points
798: batches = []
799: if pageZero:
800: ofs = 0
801: else:
802: ofs = 1
803:
804: for i in range(nb):
805: s = i * grpsize + ofs
806: e = min((i + 1) * grpsize + ofs - 1, maxIdx)
807: batches.append({'start':s, 'end':e})
808:
809: batch['batches'] = batches
810:
811: pages = []
812: if pageZero and start == 1:
813: # correct beginning
814: idx = 0
815: else:
816: idx = start
817:
818: for r in range(rows):
819: row = []
820: for c in range(cols):
821: if idx < minIdx or idx > maxIdx:
822: page = {'idx':None}
823: else:
824: page = {'idx':idx}
825:
826: idx += 1
827: if pageFlowLtr:
828: row.append(page)
829: else:
830: row.insert(0, page)
831:
832: pages.append(row)
833:
834: if start > 1:
835: batch['prevStart'] = max(start - grpsize, 1)
836: else:
837: batch['prevStart'] = None
838:
839: if start + grpsize < maxIdx:
840: batch['nextStart'] = start + grpsize
841: else:
842: batch['nextStart'] = None
843:
844: batch['pages'] = pages
845: return batch
846:
847: def getBatch(self, start=1, size=10, end=0, data=None, fullData=True):
848: """returns dict with information for one screenfull of data."""
849: batch = {}
850: if end == 0:
851: end = start + size
852:
853: nb = int(math.ceil(end / float(size)))
854: # list of all batch start and end points
855: batches = []
856: for i in range(nb):
857: s = i * size + 1
858: e = min((i + 1) * size, end)
859: batches.append({'start':s, 'end':e})
860:
861: batch['batches'] = batches
862: # list of elements in this batch
863: this = []
864: j = 0
865: for i in range(start, min(start+size, end)):
866: if data:
867: if fullData:
868: d = data[i]
869: else:
870: d = data[j]
871: j += 1
872:
873: else:
874: d = i+1
875:
876: this.append(d)
877:
878: batch['this'] = this
879: if start > 1:
880: batch['prevStart'] = max(start - size, 1)
881: else:
882: batch['prevStart'] = None
883:
884: if start + size < end:
885: batch['nextStart'] = start + size
886: else:
887: batch['nextStart'] = None
888:
889: return batch
890:
891:
892: security.declareProtected('View management screens','changeDocumentViewerForm')
893: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
894:
895: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
896: """init document viewer"""
897: self.title=title
898: self.digilibBaseUrl = digilibBaseUrl
899: self.thumbrows = thumbrows
900: self.thumbcols = thumbcols
901: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
902: try:
903: # assume MetaDataFolder instance is called metadata
904: self.metadataService = getattr(self, 'metadata')
905: except Exception, e:
906: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
907:
908: if RESPONSE is not None:
909: RESPONSE.redirect('manage_main')
910:
911: def manage_AddDocumentViewerForm(self):
912: """add the viewer form"""
913: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
914: return pt()
915:
916: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
917: """add the viewer"""
918: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
919: self._setObject(id,newObj)
920:
921: if RESPONSE is not None:
922: RESPONSE.redirect('manage_main')
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>