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