1: from OFS.Folder import Folder
2: from OFS.Image import File
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:
9: #from Ft.Xml import EMPTY_NAMESPACE, Parse
10: #import Ft.Xml.Domlette
11:
12: import xml.etree.ElementTree as ET
13:
14: import os.path
15: import sys
16: import urllib
17: import logging
18: import math
19: import urlparse
20: import re
21: import string
22:
23: from SrvTxtUtils import getInt, getText, getHttpData
24:
25: def logger(txt,method,txt2):
26: """logging"""
27: logging.info(txt+ txt2)
28:
29:
30: def serializeNode(node, encoding="utf-8"):
31: """returns a string containing node as XML"""
32: s = ET.tostring(node)
33:
34: # 4Suite:
35: # stream = cStringIO.StringIO()
36: # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
37: # s = stream.getvalue()
38: # stream.close()
39: return s
40:
41: def browserCheck(self):
42: """check the browsers request to find out the browser type"""
43: bt = {}
44: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
45: bt['ua'] = ua
46: bt['isIE'] = False
47: bt['isN4'] = False
48: bt['versFirefox']=""
49: bt['versIE']=""
50: bt['versSafariChrome']=""
51: bt['versOpera']=""
52:
53: if string.find(ua, 'MSIE') > -1:
54: bt['isIE'] = True
55: else:
56: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
57: # Safari oder Chrome identification
58: try:
59: nav = ua[string.find(ua, '('):]
60: nav1=ua[string.find(ua,')'):]
61: nav2=nav1[string.find(nav1,'('):]
62: nav3=nav2[string.find(nav2,')'):]
63: ie = string.split(nav, "; ")[1]
64: ie1 =string.split(nav1, " ")[2]
65: ie2 =string.split(nav3, " ")[1]
66: ie3 =string.split(nav3, " ")[2]
67: if string.find(ie3, "Safari") >-1:
68: bt['versSafariChrome']=string.split(ie2, "/")[1]
69: except: pass
70: # IE identification
71: try:
72: nav = ua[string.find(ua, '('):]
73: ie = string.split(nav, "; ")[1]
74: if string.find(ie, "MSIE") > -1:
75: bt['versIE'] = string.split(ie, " ")[1]
76: except:pass
77: # Firefox identification
78: try:
79: nav = ua[string.find(ua, '('):]
80: nav1=ua[string.find(ua,')'):]
81: if string.find(ie1, "Firefox") >-1:
82: nav5= string.split(ie1, "/")[1]
83: logging.debug("FIREFOX: %s"%(nav5))
84: bt['versFirefox']=nav5[0:3]
85: except:pass
86: #Opera identification
87: try:
88: if string.find(ua,"Opera") >-1:
89: nav = ua[string.find(ua, '('):]
90: nav1=nav[string.find(nav,')'):]
91: bt['versOpera']=string.split(nav1,"/")[2]
92: except:pass
93:
94: bt['isMac'] = string.find(ua, 'Macintosh') > -1
95: bt['isWin'] = string.find(ua, 'Windows') > -1
96: bt['isIEWin'] = bt['isIE'] and bt['isWin']
97: bt['isIEMac'] = bt['isIE'] and bt['isMac']
98: bt['staticHTML'] = False
99:
100: return bt
101:
102: def getParentPath(path, cnt=1):
103: """returns pathname shortened by cnt"""
104: # make sure path doesn't end with /
105: path = path.rstrip('/')
106: # split by /, shorten, and reassemble
107: return '/'.join(path.split('/')[0:-cnt])
108:
109:
110: ##
111: ## documentViewer class
112: ##
113: class documentViewer(Folder):
114: """document viewer"""
115: meta_type="Document viewer"
116:
117: security=ClassSecurityInfo()
118: manage_options=Folder.manage_options+(
119: {'label':'main config','action':'changeDocumentViewerForm'},
120: )
121:
122: metadataService = None
123: """MetaDataFolder instance"""
124:
125: # templates and forms
126: viewer_text = PageTemplateFile('zpt/viewer_text', globals())
127: viewer_images = PageTemplateFile('zpt/viewer_images', globals())
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_double = PageTemplateFile('zpt/page_main_double', globals())
134: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
135: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
136: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
137: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
138: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
139: head_main = PageTemplateFile('zpt/head_main', globals())
140: info_xml = PageTemplateFile('zpt/info_xml', globals())
141: # TODO: can this be nicer?
142: docuviewer_css = File('docuviewer_css','',open(os.path.join(package_home(globals()),'css/docuviewer.css')), content_type='text/css')
143:
144:
145: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
146:
147:
148: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
149: """init document viewer"""
150: self.id=id
151: self.title=title
152: self.thumbcols = thumbcols
153: self.thumbrows = thumbrows
154: # authgroups is list of authorized groups (delimited by ,)
155: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
156: # create template folder so we can always use template.something
157:
158: templateFolder = Folder('template')
159: #self['template'] = templateFolder # Zope-2.12 style
160: self._setObject('template',templateFolder) # old style
161: try:
162: import MpdlXmlTextServer
163: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
164: #templateFolder['fulltextclient'] = xmlRpcClient
165: templateFolder._setObject('fulltextclient',textServer)
166: except Exception, e:
167: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
168:
169: try:
170: from Products.zogiLib.zogiLib import zogiLib
171: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
172: #templateFolder['zogilib'] = zogilib
173: templateFolder._setObject('zogilib',zogilib)
174: except Exception, e:
175: logging.error("Unable to create zogiLib for zogilib: "+str(e))
176:
177: try:
178: # assume MetaDataFolder instance is called metadata
179: self.metadataService = getattr(self, 'metadata')
180: except Exception, e:
181: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
182:
183: if digilibBaseUrl is not None:
184: self.digilibBaseUrl = digilibBaseUrl
185:
186:
187: # proxy text server methods to fulltextclient
188: def getTextPage(self, **args):
189: """get page"""
190: return self.template.fulltextclient.getTextPage(**args)
191:
192: def getOrigPages(self, **args):
193: """get page"""
194: return self.template.fulltextclient.getOrigPages(**args)
195:
196: def getOrigPagesNorm(self, **args):
197: """get page"""
198: return self.template.fulltextclient.getOrigPagesNorm(**args)
199:
200: def getQuery(self, **args):
201: """get query in search"""
202: return self.template.fulltextclient.getQuery(**args)
203:
204: def getSearch(self, **args):
205: """get search"""
206: return self.template.fulltextclient.getSearch(**args)
207:
208: def getGisPlaces(self, **args):
209: """get gis places"""
210: return self.template.fulltextclient.getGisPlaces(**args)
211:
212: def getAllGisPlaces(self, **args):
213: """get all gis places """
214: return self.template.fulltextclient.getAllGisPlaces(**args)
215:
216: def getWordInfo(self, **args):
217: """get translate"""
218: return self.template.fulltextclient.getWordInfo(**args)
219:
220: def getLemma(self, **args):
221: """get lemma"""
222: return self.template.fulltextclient.getLemma(**args)
223:
224: def getLemmaQuery(self, **args):
225: """get query"""
226: return self.template.fulltextclient.getLemmaQuery(**args)
227:
228: def getLex(self, **args):
229: """get lex"""
230: return self.template.fulltextclient.getLex(**args)
231:
232: def getToc(self, **args):
233: """get toc"""
234: return self.template.fulltextclient.getToc(**args)
235:
236: def getTocPage(self, **args):
237: """get tocpage"""
238: return self.template.fulltextclient.getTocPage(**args)
239:
240:
241: security.declareProtected('View','thumbs_rss')
242: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
243: '''
244: view it
245: @param mode: defines how to access the document behind url
246: @param url: url which contains display information
247: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
248:
249: '''
250: logging.debug("HHHHHHHHHHHHHH:load the rss")
251: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
252:
253: if not hasattr(self, 'template'):
254: # create template folder if it doesn't exist
255: self.manage_addFolder('template')
256:
257: if not self.digilibBaseUrl:
258: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
259:
260: docinfo = self.getDocinfo(mode=mode,url=url)
261: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
262: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
263: ''' ZDES '''
264: pt = getattr(self.template, 'thumbs_main_rss')
265:
266: if viewMode=="auto": # automodus gewaehlt
267: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
268: viewMode="text"
269: else:
270: viewMode="images"
271:
272: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
273:
274:
275: security.declareProtected('View','index_html')
276: def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1):
277: """
278: view page
279: @param url: url which contains display information
280: @param mode: defines how to access the document behind url
281: @param viewMode: 'images': display images, 'text': display text, default is 'auto'
282: @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text'
283: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
284: """
285:
286: logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewType=%s start=%s pn=%s"%(mode,url,viewMode,viewType,start,pn))
287:
288: if not hasattr(self, 'template'):
289: # this won't work
290: logging.error("template folder missing!")
291: return "ERROR: template folder missing!"
292:
293: if not getattr(self, 'digilibBaseUrl', None):
294: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
295:
296: docinfo = self.getDocinfo(mode=mode,url=url)
297:
298: if tocMode != "thumbs":
299: # get table of contents
300: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
301:
302: # auto viewMode: text if there is a text else images
303: if viewMode=="auto":
304: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
305: viewMode = "text"
306: viewType = "dict"
307: else:
308: viewMode = "images"
309:
310: elif viewMode == "text_dict":
311: # legacy fix
312: viewMode = "text"
313: viewType = "dict"
314:
315: # stringify viewType
316: if isinstance(viewType, list):
317: logging.debug("index_html: viewType is list:%s"%viewType)
318: viewType = ','.join([t for t in viewType if t])
319:
320: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode)
321:
322: # get template /template/viewer_$viewMode
323: pt = getattr(self.template, 'viewer_%s'%viewMode, None)
324: if pt is None:
325: logging.error("No template for viewMode=%s!"%viewMode)
326: # TODO: error page?
327: return "No template for viewMode=%s!"%viewMode
328:
329: # and execute with parameters
330: return pt(docinfo=docinfo, pageinfo=pageinfo)
331:
332: def generateMarks(self,mk):
333: ret=""
334: if mk is None:
335: return ""
336: if not isinstance(mk, list):
337: mk=[mk]
338: for m in mk:
339: ret+="mk=%s"%m
340: return ret
341:
342:
343: def getBrowser(self):
344: """getBrowser the version of browser """
345: bt = browserCheck(self)
346: logging.debug("BROWSER VERSION: %s"%(bt))
347: return bt
348:
349: def findDigilibUrl(self):
350: """try to get the digilib URL from zogilib"""
351: url = self.template.zogilib.getDLBaseUrl()
352: return url
353:
354: def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None):
355: """returns URL to digilib Scaler with params"""
356: url = None
357: if docinfo is not None:
358: url = docinfo.get('imageURL', None)
359:
360: if url is None:
361: url = "%s/servlet/Scaler?"%self.digilibBaseUrl
362: if fn is None and docinfo is not None:
363: fn = docinfo.get('imagePath','')
364:
365: url += "fn=%s"%fn
366:
367: if pn:
368: url += "&pn=%s"%pn
369:
370: url += "&dw=%s&dh=%s"%(dw,dh)
371: return url
372:
373: def getDocumentViewerURL(self):
374: """returns the URL of this instance"""
375: return self.absolute_url()
376:
377: def getStyle(self, idx, selected, style=""):
378: """returns a string with the given style and append 'sel' if idx == selected."""
379: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
380: if idx == selected:
381: return style + 'sel'
382: else:
383: return style
384:
385: def getParams(self, param=None, val=None, params=None, duplicates=None):
386: """returns dict with URL parameters.
387:
388: Takes URL parameters and additionally param=val or dict params.
389: Deletes key if value is None."""
390: # copy existing request params
391: newParams=self.REQUEST.form.copy()
392: # change single param
393: if param is not None:
394: if val is None:
395: if newParams.has_key(param):
396: del newParams[param]
397: else:
398: newParams[param] = str(val)
399:
400: # change more params
401: if params is not None:
402: for (k, v) in params.items():
403: if v is None:
404: # val=None removes param
405: if newParams.has_key(k):
406: del newParams[k]
407:
408: else:
409: newParams[k] = v
410:
411: if duplicates:
412: # eliminate lists (coming from duplicate keys)
413: for (k,v) in newParams.items():
414: if isinstance(v, list):
415: if duplicates == 'comma':
416: # make comma-separated list of non-empty entries
417: newParams[k] = ','.join([t for t in v if t])
418: elif duplicates == 'first':
419: # take first non-empty entry
420: newParams[k] = [t for t in v if t][0]
421:
422: return newParams
423:
424: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'):
425: """returns URL to documentviewer with parameter param set to val or from dict params"""
426: urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates)
427: # quote values and assemble into query string (not escaping '/')
428: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()])
429: if baseUrl is None:
430: baseUrl = self.getDocumentViewerURL()
431:
432: url = "%s?%s"%(baseUrl, ps)
433: return url
434:
435: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'):
436: """link to documentviewer with parameter param set to val"""
437: return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&', duplicates=duplicates)
438:
439:
440: def getInfo_xml(self,url,mode):
441: """returns info about the document as XML"""
442: if not self.digilibBaseUrl:
443: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
444:
445: docinfo = self.getDocinfo(mode=mode,url=url)
446: pt = getattr(self.template, 'info_xml')
447: return pt(docinfo=docinfo)
448:
449: def isAccessible(self, docinfo):
450: """returns if access to the resource is granted"""
451: access = docinfo.get('accessType', None)
452: logging.debug("documentViewer (accessOK) access type %s"%access)
453: if access == 'free':
454: logging.debug("documentViewer (accessOK) access is free")
455: return True
456:
457: elif access is None or access in self.authgroups:
458: # only local access -- only logged in users
459: user = getSecurityManager().getUser()
460: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
461: if user is not None:
462: #print "user: ", user
463: return (user.getUserName() != "Anonymous User")
464: else:
465: return False
466:
467: logging.error("documentViewer (accessOK) unknown access type %s"%access)
468: return False
469:
470:
471:
472: def getDocinfo(self, mode, url):
473: """returns docinfo depending on mode"""
474: logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
475: # look for cached docinfo in session
476: if self.REQUEST.SESSION.has_key('docinfo'):
477: docinfo = self.REQUEST.SESSION['docinfo']
478: # check if its still current
479: if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
480: logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
481: return docinfo
482:
483: # new docinfo
484: docinfo = {'mode': mode, 'url': url}
485: # add self url
486: docinfo['viewerUrl'] = self.getDocumentViewerURL()
487: docinfo['digilibBaseUrl'] = self.digilibBaseUrl
488: # get index.meta DOM
489: docUrl = None
490: metaDom = None
491: if mode=="texttool":
492: # url points to document dir or index.meta
493: metaDom = self.metadataService.getDomFromPathOrUrl(url)
494: docUrl = url.replace('/index.meta', '')
495: if metaDom is None:
496: raise IOError("Unable to find index.meta for mode=texttool!")
497:
498: elif mode=="imagepath":
499: # url points to folder with images, index.meta optional
500: # asssume index.meta in parent dir
501: docUrl = getParentPath(url)
502: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
503:
504: elif mode=="filepath":
505: # url points to image file, index.meta optional
506: # asssume index.meta is two path segments up
507: docUrl = getParentPath(url, 2)
508: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
509:
510: else:
511: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
512: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
513:
514: docinfo['documentUrl'] = docUrl
515: # process index.meta contents
516: if metaDom is not None and metaDom.tag == 'resource':
517: # document directory name and path
518: resource = self.metadataService.getResourceData(dom=metaDom)
519: if resource:
520: docinfo = self.getDocinfoFromResource(docinfo, resource)
521:
522: # texttool info
523: texttool = self.metadataService.getTexttoolData(dom=metaDom)
524: if texttool:
525: docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
526:
527: # bib info
528: bib = self.metadataService.getBibData(dom=metaDom)
529: if bib:
530: docinfo = self.getDocinfoFromBib(docinfo, bib)
531: else:
532: # no bib - try info.xml
533: docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)
534:
535: # auth info
536: access = self.metadataService.getAccessData(dom=metaDom)
537: if access:
538: docinfo = self.getDocinfoFromAccess(docinfo, access)
539:
540: # attribution info
541: attribution = self.metadataService.getAttributionData(dom=metaDom)
542: if attribution:
543: logging.debug("getDocinfo: attribution=%s"%repr(attribution))
544: docinfo['attribution'] = attribution
545: #docinfo = self.getDocinfoFromAccess(docinfo, access)
546:
547: # copyright info
548: copyright = self.metadataService.getCopyrightData(dom=metaDom)
549: if copyright:
550: logging.debug("getDocinfo: copyright=%s"%repr(copyright))
551: docinfo['copyright'] = copyright
552: #docinfo = self.getDocinfoFromAccess(docinfo, access)
553:
554: # image path
555: if mode != 'texttool':
556: # override image path from texttool with url
557: docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)
558:
559: # number of images from digilib
560: if docinfo.get('imagePath', None):
561: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
562: docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
563:
564: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
565: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
566: # store in session
567: self.REQUEST.SESSION['docinfo'] = docinfo
568: return docinfo
569:
570: def getDocinfoFromResource(self, docinfo, resource):
571: """reads contents of resource element into docinfo"""
572: docName = resource.get('name', None)
573: docinfo['documentName'] = docName
574: docPath = resource.get('archive-path', None)
575: if docPath:
576: # clean up document path
577: if docPath[0] != '/':
578: docPath = '/' + docPath
579:
580: if docName and (not docPath.endswith(docName)):
581: docPath += "/" + docName
582:
583: else:
584: # use docUrl as docPath
585: docUrl = docinfo['documentURL']
586: if not docUrl.startswith('http:'):
587: docPath = docUrl
588: if docPath:
589: # fix URLs starting with /mpiwg/online
590: docPath = docPath.replace('/mpiwg/online', '', 1)
591:
592: docinfo['documentPath'] = docPath
593: return docinfo
594:
595: def getDocinfoFromTexttool(self, docinfo, texttool):
596: """reads contents of texttool element into docinfo"""
597: # image dir
598: imageDir = texttool.get('image', None)
599: docPath = docinfo.get('documentPath', None)
600: if imageDir and docPath:
601: #print "image: ", imageDir, " archivepath: ", archivePath
602: imageDir = os.path.join(docPath, imageDir)
603: imageDir = imageDir.replace('/mpiwg/online', '', 1)
604: docinfo['imagePath'] = imageDir
605:
606: # old style text URL
607: textUrl = texttool.get('text', None)
608: if textUrl and docPath:
609: if urlparse.urlparse(textUrl)[0] == "": #keine url
610: textUrl = os.path.join(docPath, textUrl)
611:
612: docinfo['textURL'] = textUrl
613:
614: # new style text-url-path
615: textUrl = texttool.get('text-url-path', None)
616: if textUrl:
617: docinfo['textURLPath'] = textUrl
618:
619: # page flow
620: docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')
621:
622: # odd pages are left
623: docinfo['oddPage'] = texttool.get('odd-scan-position', 'left')
624:
625: # number of title page (0: not defined)
626: docinfo['titlePage'] = texttool.get('title-scan-no', 0)
627:
628: # old presentation stuff
629: presentation = texttool.get('presentation', None)
630: if presentation and docPath:
631: if presentation.startswith('http:'):
632: docinfo['presentationUrl'] = presentation
633: else:
634: docinfo['presentationUrl'] = os.path.join(docPath, presentation)
635:
636:
637: return docinfo
638:
639: def getDocinfoFromBib(self, docinfo, bib):
640: """reads contents of bib element into docinfo"""
641: logging.debug("getDocinfoFromBib bib=%s"%repr(bib))
642: # put all raw bib fields in dict "bib"
643: docinfo['bib'] = bib
644: bibtype = bib.get('@type', None)
645: docinfo['bibType'] = bibtype
646: # also store DC metadata for convenience
647: dc = self.metadataService.getDCMappedData(bib)
648: docinfo['creator'] = dc.get('creator',None)
649: docinfo['title'] = dc.get('title',None)
650: docinfo['date'] = dc.get('date',None)
651: return docinfo
652:
653: def getDocinfoFromAccess(self, docinfo, acc):
654: """reads contents of access element into docinfo"""
655: #TODO: also read resource type
656: logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))
657: try:
658: acctype = acc['@attr']['type']
659: if acctype:
660: access=acctype
661: if access in ['group', 'institution']:
662: access = acc['name'].lower()
663:
664: docinfo['accessType'] = access
665:
666: except:
667: pass
668:
669: return docinfo
670:
671: def getDocinfoFromDigilib(self, docinfo, path):
672: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
673: # fetch data
674: txt = getHttpData(infoUrl)
675: if not txt:
676: logging.error("Unable to get dir-info from %s"%(infoUrl))
677: return docinfo
678:
679: dom = ET.fromstring(txt)
680: size = getText(dom.find("size"))
681: logging.debug("getDocinfoFromDigilib: size=%s"%size)
682: if size:
683: docinfo['numPages'] = int(size)
684: else:
685: docinfo['numPages'] = 0
686:
687: # TODO: produce and keep list of image names and numbers
688: return docinfo
689:
690:
691: def getDocinfoFromPresentationInfoXml(self,docinfo):
692: """gets DC-like bibliographical information from the presentation entry in texttools"""
693: url = docinfo.get('presentationUrl', None)
694: if not url:
695: logging.error("getDocinfoFromPresentation: no URL!")
696: return docinfo
697:
698: dom = None
699: metaUrl = None
700: if url.startswith("http://"):
701: # real URL
702: metaUrl = url
703: else:
704: # online path
705:
706: server=self.digilibBaseUrl+"/servlet/Texter?fn="
707: metaUrl=server+url
708:
709: txt=getHttpData(metaUrl)
710: if txt is None:
711: logging.error("Unable to read info.xml from %s"%(url))
712: return docinfo
713:
714: dom = ET.fromstring(txt)
715: docinfo['creator']=getText(dom.find(".//author"))
716: docinfo['title']=getText(dom.find(".//title"))
717: docinfo['date']=getText(dom.find(".//date"))
718: return docinfo
719:
720:
721: def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None):
722: """returns pageinfo with the given parameters"""
723: logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewType=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewType,tocMode))
724: pageinfo = {}
725: pageinfo['viewMode'] = viewMode
726: pageinfo['viewType'] = viewType
727: pageinfo['tocMode'] = tocMode
728:
729: current = getInt(current)
730: pageinfo['current'] = current
731: pageinfo['pn'] = current
732: rows = int(rows or self.thumbrows)
733: pageinfo['rows'] = rows
734: cols = int(cols or self.thumbcols)
735: pageinfo['cols'] = cols
736: grpsize = cols * rows
737: pageinfo['groupsize'] = grpsize
738: # is start is empty use one around current
739: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
740: # int(current / grpsize) * grpsize +1))
741: pageinfo['start'] = start
742:
743: np = int(docinfo.get('numPages', 0))
744: if np == 0:
745: # numPages unknown - maybe we can get it from text page
746: if docinfo.get('textURLPath', None):
747: # cache text page as well
748: pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=current, docinfo=docinfo, pageinfo=pageinfo)
749: np = int(docinfo.get('numPages', 0))
750:
751: pageinfo['numgroups'] = int(np / grpsize)
752: if np % grpsize > 0:
753: pageinfo['numgroups'] += 1
754:
755: pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl'
756: oddScanLeft = docinfo.get('oddPage', 'left') != 'right'
757: # add zeroth page for two columns
758: pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft))
759: pageinfo['pageZero'] = pageZero
760: pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np)
761:
762: # TODO: do we need this here?
763: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
764: pageinfo['query'] = self.REQUEST.get('query','')
765: pageinfo['queryType'] = self.REQUEST.get('queryType','')
766: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
767: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
768: pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30))
769: pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10))
770: pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1'))
771: pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1'))
772:
773: # limit tocPN
774: if 'tocSize_%s'%tocMode in docinfo:
775: tocSize = docinfo['tocSize_%s'%tocMode]
776: tocPageSize = pageinfo['tocPageSize']
777: # cached toc
778: if tocSize%tocPageSize>0:
779: tocPages=tocSize/tocPageSize+1
780: else:
781: tocPages=tocSize/tocPageSize
782:
783: pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN'])
784:
785: return pageinfo
786:
787:
788: def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0):
789: """returns dict with array of page informations for one screenfull of thumbnails"""
790: batch = {}
791: grpsize = rows * cols
792: if maxIdx == 0:
793: maxIdx = start + grpsize
794:
795: nb = int(math.ceil(maxIdx / float(grpsize)))
796: # list of all batch start and end points
797: batches = []
798: if pageZero:
799: ofs = 0
800: else:
801: ofs = 1
802:
803: for i in range(nb):
804: s = i * grpsize + ofs
805: e = min((i + 1) * grpsize + ofs - 1, maxIdx)
806: batches.append({'start':s, 'end':e})
807:
808: batch['batches'] = batches
809:
810: pages = []
811: if pageZero and start == 1:
812: # correct beginning
813: idx = 0
814: else:
815: idx = start
816:
817: for r in range(rows):
818: row = []
819: for c in range(cols):
820: if idx < minIdx or idx > maxIdx:
821: page = {'idx':None}
822: else:
823: page = {'idx':idx}
824:
825: idx += 1
826: if pageFlowLtr:
827: row.append(page)
828: else:
829: row.insert(0, page)
830:
831: pages.append(row)
832:
833: if start > 1:
834: batch['prevStart'] = max(start - grpsize, 1)
835: else:
836: batch['prevStart'] = None
837:
838: if start + grpsize < maxIdx:
839: batch['nextStart'] = start + grpsize
840: else:
841: batch['nextStart'] = None
842:
843: batch['pages'] = pages
844: return batch
845:
846: def getBatch(self, start=1, size=10, end=0, data=None, fullData=True):
847: """returns dict with information for one screenfull of data."""
848: batch = {}
849: if end == 0:
850: end = start + size
851:
852: nb = int(math.ceil(end / float(size)))
853: # list of all batch start and end points
854: batches = []
855: for i in range(nb):
856: s = i * size + 1
857: e = min((i + 1) * size, end)
858: batches.append({'start':s, 'end':e})
859:
860: batch['batches'] = batches
861: # list of elements in this batch
862: this = []
863: j = 0
864: for i in range(start, min(start+size, end)):
865: if data:
866: if fullData:
867: d = data[i]
868: else:
869: d = data[j]
870: j += 1
871:
872: else:
873: d = i+1
874:
875: this.append(d)
876:
877: batch['this'] = this
878: if start > 1:
879: batch['prevStart'] = max(start - size, 1)
880: else:
881: batch['prevStart'] = None
882:
883: if start + size < end:
884: batch['nextStart'] = start + size
885: else:
886: batch['nextStart'] = None
887:
888: return batch
889:
890:
891: security.declareProtected('View management screens','changeDocumentViewerForm')
892: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
893:
894: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
895: """init document viewer"""
896: self.title=title
897: self.digilibBaseUrl = digilibBaseUrl
898: self.thumbrows = thumbrows
899: self.thumbcols = thumbcols
900: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
901: try:
902: # assume MetaDataFolder instance is called metadata
903: self.metadataService = getattr(self, 'metadata')
904: except Exception, e:
905: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
906:
907: if RESPONSE is not None:
908: RESPONSE.redirect('manage_main')
909:
910: def manage_AddDocumentViewerForm(self):
911: """add the viewer form"""
912: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
913: return pt()
914:
915: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
916: """add the viewer"""
917: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
918: self._setObject(id,newObj)
919:
920: if RESPONSE is not None:
921: RESPONSE.redirect('manage_main')
922:
923: ## DocumentViewerTemplate class
924: class DocumentViewerTemplate(ZopePageTemplate):
925: """Template for document viewer"""
926: meta_type="DocumentViewer Template"
927:
928:
929: def manage_addDocumentViewerTemplateForm(self):
930: """Form for adding"""
931: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
932: return pt()
933:
934: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
935: REQUEST=None, submit=None):
936: "Add a Page Template with optional file content."
937:
938: self._setObject(id, DocumentViewerTemplate(id))
939: ob = getattr(self, id)
940: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
941: logging.info("txt %s:"%txt)
942: ob.pt_edit(txt,"text/html")
943: if title:
944: ob.pt_setTitle(title)
945: try:
946: u = self.DestinationURL()
947: except AttributeError:
948: u = REQUEST['URL1']
949:
950: u = "%s/%s" % (u, urllib.quote(id))
951: REQUEST.RESPONSE.redirect(u+'/manage_main')
952: return ''
953:
954:
955:
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