1: from OFS.Folder import Folder
2: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
4: from AccessControl import ClassSecurityInfo
5: from AccessControl import getSecurityManager
6: from Globals import package_home
7:
8: #from Ft.Xml import EMPTY_NAMESPACE, Parse
9: #import Ft.Xml.Domlette
10:
11: import xml.etree.ElementTree as ET
12:
13: import os.path
14: import sys
15: import urllib
16: import logging
17: import math
18: import urlparse
19: import re
20: import string
21:
22: from SrvTxtUtils import getInt, getText, getHttpData
23:
24: def logger(txt,method,txt2):
25: """logging"""
26: logging.info(txt+ txt2)
27:
28:
29: def serializeNode(node, encoding="utf-8"):
30: """returns a string containing node as XML"""
31: s = ET.tostring(node)
32:
33: # 4Suite:
34: # stream = cStringIO.StringIO()
35: # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
36: # s = stream.getvalue()
37: # stream.close()
38: return s
39:
40: def browserCheck(self):
41: """check the browsers request to find out the browser type"""
42: bt = {}
43: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
44: bt['ua'] = ua
45: bt['isIE'] = False
46: bt['isN4'] = False
47: bt['versFirefox']=""
48: bt['versIE']=""
49: bt['versSafariChrome']=""
50: bt['versOpera']=""
51:
52: if string.find(ua, 'MSIE') > -1:
53: bt['isIE'] = True
54: else:
55: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
56: # Safari oder Chrome identification
57: try:
58: nav = ua[string.find(ua, '('):]
59: nav1=ua[string.find(ua,')'):]
60: nav2=nav1[string.find(nav1,'('):]
61: nav3=nav2[string.find(nav2,')'):]
62: ie = string.split(nav, "; ")[1]
63: ie1 =string.split(nav1, " ")[2]
64: ie2 =string.split(nav3, " ")[1]
65: ie3 =string.split(nav3, " ")[2]
66: if string.find(ie3, "Safari") >-1:
67: bt['versSafariChrome']=string.split(ie2, "/")[1]
68: except: pass
69: # IE identification
70: try:
71: nav = ua[string.find(ua, '('):]
72: ie = string.split(nav, "; ")[1]
73: if string.find(ie, "MSIE") > -1:
74: bt['versIE'] = string.split(ie, " ")[1]
75: except:pass
76: # Firefox identification
77: try:
78: nav = ua[string.find(ua, '('):]
79: nav1=ua[string.find(ua,')'):]
80: if string.find(ie1, "Firefox") >-1:
81: nav5= string.split(ie1, "/")[1]
82: logging.debug("FIREFOX: %s"%(nav5))
83: bt['versFirefox']=nav5[0:3]
84: except:pass
85: #Opera identification
86: try:
87: if string.find(ua,"Opera") >-1:
88: nav = ua[string.find(ua, '('):]
89: nav1=nav[string.find(nav,')'):]
90: bt['versOpera']=string.split(nav1,"/")[2]
91: except:pass
92:
93: bt['isMac'] = string.find(ua, 'Macintosh') > -1
94: bt['isWin'] = string.find(ua, 'Windows') > -1
95: bt['isIEWin'] = bt['isIE'] and bt['isWin']
96: bt['isIEMac'] = bt['isIE'] and bt['isMac']
97: bt['staticHTML'] = False
98:
99: return bt
100:
101: def getParentDir(path):
102: """returns pathname shortened by one"""
103: return '/'.join(path.split('/')[0:-1])
104:
105: def getBibdataFromDom(dom):
106: """returns dict with all elements from bib-tag"""
107: bibinfo = {}
108: bib = dom.find(".//meta/bib")
109: if bib is not None:
110: # put type in @type
111: type = bib.get('type')
112: bibinfo['@type'] = type
113: # put all subelements in dict
114: for e in bib:
115: bibinfo[e.tag] = getText(e)
116:
117: return bibinfo
118:
119: ##
120: ## documentViewer class
121: ##
122: class documentViewer(Folder):
123: """document viewer"""
124: meta_type="Document viewer"
125:
126: security=ClassSecurityInfo()
127: manage_options=Folder.manage_options+(
128: {'label':'main config','action':'changeDocumentViewerForm'},
129: )
130:
131: # templates and forms
132: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
133: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
134: toc_text = PageTemplateFile('zpt/toc_text', globals())
135: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
136: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
137: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
138: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
139: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
140: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
141: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
142: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
143: head_main = PageTemplateFile('zpt/head_main', globals())
144: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
145: info_xml = PageTemplateFile('zpt/info_xml', globals())
146:
147:
148: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
149: security.declareProtected('View management screens','changeDocumentViewerForm')
150: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
151:
152:
153: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
154: """init document viewer"""
155: self.id=id
156: self.title=title
157: self.thumbcols = thumbcols
158: self.thumbrows = thumbrows
159: # authgroups is list of authorized groups (delimited by ,)
160: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
161: # create template folder so we can always use template.something
162:
163: templateFolder = Folder('template')
164: #self['template'] = templateFolder # Zope-2.12 style
165: self._setObject('template',templateFolder) # old style
166: try:
167: import MpdlXmlTextServer
168: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
169: #templateFolder['fulltextclient'] = xmlRpcClient
170: templateFolder._setObject('fulltextclient',textServer)
171: except Exception, e:
172: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
173: try:
174: from Products.zogiLib.zogiLib import zogiLib
175: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
176: #templateFolder['zogilib'] = zogilib
177: templateFolder._setObject('zogilib',zogilib)
178: except Exception, e:
179: logging.error("Unable to create zogiLib for zogilib: "+str(e))
180:
181:
182: # proxy text server methods to fulltextclient
183: def getTextPage(self, **args):
184: """get page"""
185: return self.template.fulltextclient.getTextPage(**args)
186:
187: def getOrigPages(self, **args):
188: """get page"""
189: return self.template.fulltextclient.getOrigPages(**args)
190:
191: def getOrigPagesNorm(self, **args):
192: """get page"""
193: return self.template.fulltextclient.getOrigPagesNorm(**args)
194:
195: def getQuery(self, **args):
196: """get query in search"""
197: return self.template.fulltextclient.getQuery(**args)
198:
199: def getSearch(self, **args):
200: """get search"""
201: return self.template.fulltextclient.getSearch(**args)
202:
203: def getGisPlaces(self, **args):
204: """get gis places"""
205: return self.template.fulltextclient.getGisPlaces(**args)
206:
207: def getAllGisPlaces(self, **args):
208: """get all gis places """
209: return self.template.fulltextclient.getAllGisPlaces(**args)
210:
211: def getTranslate(self, **args):
212: """get translate"""
213: return self.template.fulltextclient.getTranslate(**args)
214:
215: def getLemma(self, **args):
216: """get lemma"""
217: return self.template.fulltextclient.getLemma(**args)
218:
219: def getLemmaQuery(self, **args):
220: """get query"""
221: return self.template.fulltextclient.getLemmaQuery(**args)
222:
223: def getLex(self, **args):
224: """get lex"""
225: return self.template.fulltextclient.getLex(**args)
226:
227: def getToc(self, **args):
228: """get toc"""
229: return self.template.fulltextclient.getToc(**args)
230:
231: def getTocPage(self, **args):
232: """get tocpage"""
233: return self.template.fulltextclient.getTocPage(**args)
234:
235:
236: security.declareProtected('View','thumbs_rss')
237: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
238: '''
239: view it
240: @param mode: defines how to access the document behind url
241: @param url: url which contains display information
242: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
243:
244: '''
245: logging.debug("HHHHHHHHHHHHHH:load the rss")
246: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
247:
248: if not hasattr(self, 'template'):
249: # create template folder if it doesn't exist
250: self.manage_addFolder('template')
251:
252: if not self.digilibBaseUrl:
253: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
254:
255: docinfo = self.getDocinfo(mode=mode,url=url)
256: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
257: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
258: ''' ZDES '''
259: pt = getattr(self.template, 'thumbs_main_rss')
260:
261: if viewMode=="auto": # automodus gewaehlt
262: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
263: viewMode="text"
264: else:
265: viewMode="images"
266:
267: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
268:
269: security.declareProtected('View','index_html')
270: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
271: '''
272: view it
273: @param mode: defines how to access the document behind url
274: @param url: url which contains display information
275: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
276: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
277: @param characterNormalization type of text display (reg, norm, none)
278: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
279: '''
280:
281: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
282:
283: if not hasattr(self, 'template'):
284: # this won't work
285: logging.error("template folder missing!")
286: return "ERROR: template folder missing!"
287:
288: if not getattr(self, 'digilibBaseUrl', None):
289: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
290:
291: docinfo = self.getDocinfo(mode=mode,url=url)
292:
293: if tocMode != "thumbs":
294: # get table of contents
295: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
296:
297: # auto viewMode: text_dict if text else images
298: if viewMode=="auto":
299: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
300: #texturl gesetzt und textViewer konfiguriert
301: viewMode="text_dict"
302: else:
303: viewMode="images"
304:
305: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode)
306:
307: if viewMode != 'images' and docinfo.get('textURLPath', None):
308: # get full text page
309: page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
310: pageinfo['textPage'] = page
311:
312: # get template /template/viewer_main
313: pt = getattr(self.template, 'viewer_main')
314: # and execute with parameters
315: return pt(docinfo=docinfo, pageinfo=pageinfo, viewMode=viewMode, mk=self.generateMarks(mk))
316:
317: def generateMarks(self,mk):
318: ret=""
319: if mk is None:
320: return ""
321: if not isinstance(mk, list):
322: mk=[mk]
323: for m in mk:
324: ret+="mk=%s"%m
325: return ret
326:
327:
328: def getBrowser(self):
329: """getBrowser the version of browser """
330: bt = browserCheck(self)
331: logging.debug("BROWSER VERSION: %s"%(bt))
332: return bt
333:
334: def findDigilibUrl(self):
335: """try to get the digilib URL from zogilib"""
336: url = self.template.zogilib.getDLBaseUrl()
337: return url
338:
339: def getDocumentViewerURL(self):
340: """returns the URL of this instance"""
341: return self.absolute_url()
342:
343: def getStyle(self, idx, selected, style=""):
344: """returns a string with the given style and append 'sel' if path == selected."""
345: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
346: if idx == selected:
347: return style + 'sel'
348: else:
349: return style
350:
351: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
352: """returns URL to documentviewer with parameter param set to val or from dict params"""
353: # copy existing request params
354: urlParams=self.REQUEST.form.copy()
355: # change single param
356: if param is not None:
357: if val is None:
358: if urlParams.has_key(param):
359: del urlParams[param]
360: else:
361: urlParams[param] = str(val)
362:
363: # change more params
364: if params is not None:
365: for k in params.keys():
366: v = params[k]
367: if v is None:
368: # val=None removes param
369: if urlParams.has_key(k):
370: del urlParams[k]
371:
372: else:
373: urlParams[k] = v
374:
375: # FIXME: does this belong here?
376: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
377: urlParams["mode"] = "imagepath"
378: urlParams["url"] = getParentDir(urlParams["url"])
379:
380: # quote values and assemble into query string (not escaping '/')
381: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
382: #ps = urllib.urlencode(urlParams)
383: if baseUrl is None:
384: baseUrl = self.REQUEST['URL1']
385:
386: url = "%s?%s"%(baseUrl, ps)
387: return url
388:
389:
390: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
391: """link to documentviewer with parameter param set to val"""
392: return self.getLink(param, val, params, baseUrl, '&')
393:
394: def getInfo_xml(self,url,mode):
395: """returns info about the document as XML"""
396:
397: if not self.digilibBaseUrl:
398: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
399:
400: docinfo = self.getDocinfo(mode=mode,url=url)
401: pt = getattr(self.template, 'info_xml')
402: return pt(docinfo=docinfo)
403:
404: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
405: """returns new option state"""
406: if not self.REQUEST.SESSION.has_key(optionName):
407: # not in session -- initial
408: opt = {'lastState': newState, 'state': initialState}
409: else:
410: opt = self.REQUEST.SESSION.get(optionName)
411: if opt['lastState'] != newState:
412: # state in session has changed -- toggle
413: opt['state'] = not opt['state']
414: opt['lastState'] = newState
415:
416: self.REQUEST.SESSION[optionName] = opt
417: return opt['state']
418:
419: def isAccessible(self, docinfo):
420: """returns if access to the resource is granted"""
421: access = docinfo.get('accessType', None)
422: logging.debug("documentViewer (accessOK) access type %s"%access)
423: if access is not None and access == 'free':
424: logging.debug("documentViewer (accessOK) access is free")
425: return True
426: elif access is None or access in self.authgroups:
427: # only local access -- only logged in users
428: user = getSecurityManager().getUser()
429: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
430: if user is not None:
431: #print "user: ", user
432: return (user.getUserName() != "Anonymous User")
433: else:
434: return False
435:
436: logging.error("documentViewer (accessOK) unknown access type %s"%access)
437: return False
438:
439:
440: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
441: """gibt param von dlInfo aus"""
442: if docinfo is None:
443: docinfo = {}
444:
445: for x in range(cut):
446: path=getParentDir(path)
447:
448: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
449:
450: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
451:
452: txt = getHttpData(infoUrl)
453: if txt is None:
454: raise IOError("Unable to get dir-info from %s"%(infoUrl))
455:
456: dom = ET.fromstring(txt)
457: #dom = Parse(txt)
458: size=getText(dom.find("size"))
459: #sizes=dom.xpath("//dir/size")
460: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size)
461:
462: if size:
463: docinfo['numPages'] = int(size)
464: else:
465: docinfo['numPages'] = 0
466:
467: # TODO: produce and keep list of image names and numbers
468:
469: return docinfo
470:
471: def getIndexMetaPath(self,url):
472: """gib nur den Pfad zurueck"""
473: regexp = re.compile(r".*(experimental|permanent)/(.*)")
474: regpath = regexp.match(url)
475: if (regpath==None):
476: return ""
477: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
478: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
479:
480:
481:
482: def getIndexMetaUrl(self,url):
483: """returns utr of index.meta document at url"""
484:
485: metaUrl = None
486: if url.startswith("http://"):
487: # real URL
488: metaUrl = url
489: else:
490: # online path
491: server=self.digilibBaseUrl+"/servlet/Texter?fn="
492: metaUrl=server+url.replace("/mpiwg/online","")
493: if not metaUrl.endswith("index.meta"):
494: metaUrl += "/index.meta"
495:
496: return metaUrl
497:
498: def getDomFromIndexMeta(self, url):
499: """get dom from index meta"""
500: dom = None
501: metaUrl = self.getIndexMetaUrl(url)
502:
503: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
504: txt=getHttpData(metaUrl)
505: if txt is None:
506: raise IOError("Unable to read index meta from %s"%(url))
507:
508: dom = ET.fromstring(txt)
509: #dom = Parse(txt)
510: return dom
511:
512: def getPresentationInfoXML(self, url):
513: """returns dom of info.xml document at url"""
514: dom = None
515: metaUrl = None
516: if url.startswith("http://"):
517: # real URL
518: metaUrl = url
519: else:
520: # online path
521: server=self.digilibBaseUrl+"/servlet/Texter?fn="
522: metaUrl=server+url.replace("/mpiwg/online","")
523:
524: txt=getHttpData(metaUrl)
525: if txt is None:
526: raise IOError("Unable to read infoXMLfrom %s"%(url))
527:
528: dom = ET.fromstring(txt)
529: #dom = Parse(txt)
530: return dom
531:
532:
533: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
534: """gets authorization info from the index.meta file at path or given by dom"""
535: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
536:
537: access = None
538:
539: if docinfo is None:
540: docinfo = {}
541:
542: if dom is None:
543: for x in range(cut):
544: path=getParentDir(path)
545: dom = self.getDomFromIndexMeta(path)
546:
547: acc = dom.find(".//access-conditions/access")
548: if acc is not None:
549: acctype = acc.get('type')
550: #acctype = dom.xpath("//access-conditions/access/@type")
551: if acctype:
552: access=acctype
553: if access in ['group', 'institution']:
554: access = dom.find(".//access-conditions/access/name").text.lower()
555:
556: docinfo['accessType'] = access
557: return docinfo
558:
559:
560: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
561: """gets bibliographical info from the index.meta file at path or given by dom"""
562: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
563:
564: if docinfo is None:
565: docinfo = {}
566:
567: if dom is None:
568: for x in range(cut):
569: path=getParentDir(path)
570: dom = self.getDomFromIndexMeta(path)
571:
572: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
573:
574: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
575: # put all raw bib fields in dict "bib"
576: bib = getBibdataFromDom(dom)
577: docinfo['bib'] = bib
578:
579: # extract some fields (author, title, year) according to their mapping
580: metaData=self.metadata.main.meta.bib
581: bibtype=bib.get("@type")
582: #bibtype=dom.xpath("//bib/@type")
583: if not bibtype:
584: bibtype="generic"
585:
586: bibtype=bibtype.replace("-"," ") # wrong types in index meta "-" instead of " " (not wrong! ROC)
587: docinfo['bib_type'] = bibtype
588: bibmap=metaData.generateMappingForType(bibtype)
589: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
590: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
591: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
592: if len(bibmap) > 0 and bibmap.get('author',None) or bibmap.get('title',None):
593: try:
594: docinfo['author']=bib.get(bibmap['author'][0])
595: except: pass
596: try:
597: docinfo['title']=bib.get(bibmap['title'][0])
598: except: pass
599: try:
600: docinfo['year']=bib.get(bibmap['year'][0])
601: except: pass
602:
603: # ROC: why is this here?
604: # logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
605: # try:
606: # docinfo['lang']=getTextFromNode(dom.find(".//bib/lang")[0])
607: # except:
608: # docinfo['lang']=''
609: # try:
610: # docinfo['city']=getTextFromNode(dom.find(".//bib/city")[0])
611: # except:
612: # docinfo['city']=''
613: # try:
614: # docinfo['number_of_pages']=getTextFromNode(dom.find(".//bib/number_of_pages")[0])
615: # except:
616: # docinfo['number_of_pages']=''
617: # try:
618: # docinfo['series_volume']=getTextFromNode(dom.find(".//bib/series_volume")[0])
619: # except:
620: # docinfo['series_volume']=''
621: # try:
622: # docinfo['number_of_volumes']=getTextFromNode(dom.find(".//bib/number_of_volumes")[0])
623: # except:
624: # docinfo['number_of_volumes']=''
625: # try:
626: # docinfo['translator']=getTextFromNode(dom.find(".//bib/translator")[0])
627: # except:
628: # docinfo['translator']=''
629: # try:
630: # docinfo['edition']=getTextFromNode(dom.find(".//bib/edition")[0])
631: # except:
632: # docinfo['edition']=''
633: # try:
634: # docinfo['series_author']=getTextFromNode(dom.find(".//bib/series_author")[0])
635: # except:
636: # docinfo['series_author']=''
637: # try:
638: # docinfo['publisher']=getTextFromNode(dom.find(".//bib/publisher")[0])
639: # except:
640: # docinfo['publisher']=''
641: # try:
642: # docinfo['series_title']=getTextFromNode(dom.find(".//bib/series_title")[0])
643: # except:
644: # docinfo['series_title']=''
645: # try:
646: # docinfo['isbn_issn']=getTextFromNode(dom.find(".//bib/isbn_issn")[0])
647: # except:
648: # docinfo['isbn_issn']=''
649: return docinfo
650:
651:
652: # TODO: is this needed?
653: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
654: """gets name info from the index.meta file at path or given by dom"""
655: if docinfo is None:
656: docinfo = {}
657:
658: if dom is None:
659: for x in range(cut):
660: path=getParentDir(path)
661: dom = self.getDomFromIndexMeta(path)
662:
663: docinfo['name']=getText(dom.find("name"))
664: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
665: return docinfo
666:
667: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
668: """parse texttool tag in index meta"""
669: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
670: if docinfo is None:
671: docinfo = {}
672: if docinfo.get('lang', None) is None:
673: docinfo['lang'] = '' # default keine Sprache gesetzt
674: if dom is None:
675: dom = self.getDomFromIndexMeta(url)
676:
677: archivePath = None
678: archiveName = None
679:
680: archiveName = getText(dom.find("name"))
681: if not archiveName:
682: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
683:
684: archivePath = getText(dom.find("archive-path"))
685: if archivePath:
686: # clean up archive path
687: if archivePath[0] != '/':
688: archivePath = '/' + archivePath
689: if archiveName and (not archivePath.endswith(archiveName)):
690: archivePath += "/" + archiveName
691: else:
692: # try to get archive-path from url
693: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
694: if (not url.startswith('http')):
695: archivePath = url.replace('index.meta', '')
696:
697: if archivePath is None:
698: # we balk without archive-path
699: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
700:
701: imageDir = getText(dom.find(".//texttool/image"))
702:
703: if not imageDir:
704: # we balk with no image tag / not necessary anymore because textmode is now standard
705: #raise IOError("No text-tool info in %s"%(url))
706: imageDir = ""
707: #xquery="//pb"
708: docinfo['imagePath'] = "" # keine Bilder
709: docinfo['imageURL'] = ""
710:
711: if imageDir and archivePath:
712: #print "image: ", imageDir, " archivepath: ", archivePath
713: imageDir = os.path.join(archivePath, imageDir)
714: imageDir = imageDir.replace("/mpiwg/online", '')
715: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
716: docinfo['imagePath'] = imageDir
717:
718: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
719:
720: viewerUrl = getText(dom.find(".//texttool/digiliburlprefix"))
721: if viewerUrl:
722: docinfo['viewerURL'] = viewerUrl
723:
724: # old style text URL
725: textUrl = getText(dom.find(".//texttool/text"))
726: if textUrl:
727: if urlparse.urlparse(textUrl)[0] == "": #keine url
728: textUrl = os.path.join(archivePath, textUrl)
729: # fix URLs starting with /mpiwg/online
730: if textUrl.startswith("/mpiwg/online"):
731: textUrl = textUrl.replace("/mpiwg/online", '', 1)
732:
733: docinfo['textURL'] = textUrl
734:
735: # new style text-url-path
736: textUrl = getText(dom.find(".//texttool/text-url-path"))
737: if textUrl:
738: docinfo['textURLPath'] = textUrl
739: textUrlkurz = string.split(textUrl, ".")[0]
740: docinfo['textURLPathkurz'] = textUrlkurz
741: #if not docinfo['imagePath']:
742: # text-only, no page images
743: #docinfo = self.getNumTextPages(docinfo)
744:
745:
746: presentationUrl = getText(dom.find(".//texttool/presentation"))
747: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
748: # TODO: is this needed here?
749: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
750:
751:
752: if presentationUrl: # ueberschreibe diese durch presentation informationen
753: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
754: # durch den relativen Pfad auf die presentation infos
755: presentationPath = presentationUrl
756: if url.endswith("index.meta"):
757: presentationUrl = url.replace('index.meta', presentationPath)
758: else:
759: presentationUrl = url + "/" + presentationPath
760:
761: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
762:
763: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
764:
765: return docinfo
766:
767:
768: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
769: """gets the bibliographical information from the preseantion entry in texttools
770: """
771: dom=self.getPresentationInfoXML(url)
772: docinfo['author']=getText(dom.find(".//author"))
773: docinfo['title']=getText(dom.find(".//title"))
774: docinfo['year']=getText(dom.find(".//date"))
775: return docinfo
776:
777: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
778: """path ist the path to the images it assumes that the index.meta file is one level higher."""
779: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
780: if docinfo is None:
781: docinfo = {}
782: path=path.replace("/mpiwg/online","")
783: docinfo['imagePath'] = path
784: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
785:
786: pathorig=path
787: for x in range(cut):
788: path=getParentDir(path)
789: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
790: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
791: docinfo['imageURL'] = imageUrl
792:
793: #path ist the path to the images it assumes that the index.meta file is one level higher.
794: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
795: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
796: return docinfo
797:
798:
799: def getDocinfo(self, mode, url):
800: """returns docinfo depending on mode"""
801: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
802: # look for cached docinfo in session
803: if self.REQUEST.SESSION.has_key('docinfo'):
804: docinfo = self.REQUEST.SESSION['docinfo']
805: # check if its still current
806: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
807: logging.debug("documentViewer (getdocinfo) docinfo in session. keys=%s"%docinfo.keys())
808: return docinfo
809:
810: # new docinfo
811: docinfo = {'mode': mode, 'url': url}
812: # add self url
813: docinfo['viewerUrl'] = self.getDocumentViewerURL()
814: if mode=="texttool":
815: # index.meta with texttool information
816: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
817: elif mode=="imagepath":
818: # folder with images, index.meta optional
819: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
820: elif mode=="filepath":
821: # filename
822: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
823: else:
824: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
825: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
826:
827: # FIXME: fake texturlpath
828: if not docinfo.has_key('textURLPath'):
829: docinfo['textURLPath'] = None
830:
831: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
832: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
833: self.REQUEST.SESSION['docinfo'] = docinfo
834: return docinfo
835:
836: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
837: """returns pageinfo with the given parameters"""
838: pageinfo = {}
839: current = getInt(current)
840:
841: pageinfo['current'] = current
842: rows = int(rows or self.thumbrows)
843: pageinfo['rows'] = rows
844: cols = int(cols or self.thumbcols)
845: pageinfo['cols'] = cols
846: grpsize = cols * rows
847: pageinfo['groupsize'] = grpsize
848: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
849: # int(current / grpsize) * grpsize +1))
850: pageinfo['start'] = start
851: pageinfo['end'] = start + grpsize
852: if (docinfo is not None) and ('numPages' in docinfo):
853: np = int(docinfo['numPages'])
854: pageinfo['end'] = min(pageinfo['end'], np)
855: pageinfo['numgroups'] = int(np / grpsize)
856: if np % grpsize > 0:
857: pageinfo['numgroups'] += 1
858: pageinfo['viewMode'] = viewMode
859: pageinfo['tocMode'] = tocMode
860: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
861: #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
862: pageinfo['query'] = self.REQUEST.get('query','')
863: pageinfo['queryType'] = self.REQUEST.get('queryType','')
864: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
865: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
866: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
867: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
868: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
869: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
870: toc = int (pageinfo['tocPN'])
871: pageinfo['textPages'] =int (toc)
872:
873: if 'tocSize_%s'%tocMode in docinfo:
874: tocSize = int(docinfo['tocSize_%s'%tocMode])
875: tocPageSize = int(pageinfo['tocPageSize'])
876: # cached toc
877: if tocSize%tocPageSize>0:
878: tocPages=tocSize/tocPageSize+1
879: else:
880: tocPages=tocSize/tocPageSize
881: pageinfo['tocPN'] = min (tocPages,toc)
882: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
883: pageinfo['sn'] =self.REQUEST.get('sn','')
884: return pageinfo
885:
886: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
887: """init document viewer"""
888: self.title=title
889: self.digilibBaseUrl = digilibBaseUrl
890: self.thumbrows = thumbrows
891: self.thumbcols = thumbcols
892: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
893: if RESPONSE is not None:
894: RESPONSE.redirect('manage_main')
895:
896: def manage_AddDocumentViewerForm(self):
897: """add the viewer form"""
898: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
899: return pt()
900:
901: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
902: """add the viewer"""
903: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
904: self._setObject(id,newObj)
905:
906: if RESPONSE is not None:
907: RESPONSE.redirect('manage_main')
908:
909: ## DocumentViewerTemplate class
910: class DocumentViewerTemplate(ZopePageTemplate):
911: """Template for document viewer"""
912: meta_type="DocumentViewer Template"
913:
914:
915: def manage_addDocumentViewerTemplateForm(self):
916: """Form for adding"""
917: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
918: return pt()
919:
920: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
921: REQUEST=None, submit=None):
922: "Add a Page Template with optional file content."
923:
924: self._setObject(id, DocumentViewerTemplate(id))
925: ob = getattr(self, id)
926: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
927: logging.info("txt %s:"%txt)
928: ob.pt_edit(txt,"text/html")
929: if title:
930: ob.pt_setTitle(title)
931: try:
932: u = self.DestinationURL()
933: except AttributeError:
934: u = REQUEST['URL1']
935:
936: u = "%s/%s" % (u, urllib.quote(id))
937: REQUEST.RESPONSE.redirect(u+'/manage_main')
938: return ''
939:
940:
941:
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