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 AccessControl import ClassSecurityInfo |
---|
6 | from AccessControl import getSecurityManager |
---|
7 | from Globals import package_home |
---|
8 | |
---|
9 | import xml.etree.ElementTree as ET |
---|
10 | |
---|
11 | import os |
---|
12 | import sys |
---|
13 | import urllib |
---|
14 | import logging |
---|
15 | import math |
---|
16 | import urlparse |
---|
17 | import re |
---|
18 | import string |
---|
19 | import json |
---|
20 | |
---|
21 | from Products.MetaDataProvider import MetaDataFolder |
---|
22 | |
---|
23 | from SrvTxtUtils import getInt, utf8ify, getText, getHttpData, refreshingImageFileIndexHtml |
---|
24 | |
---|
25 | def serializeNode(node, encoding="utf-8"): |
---|
26 | """returns a string containing node as XML""" |
---|
27 | s = ET.tostring(node) |
---|
28 | |
---|
29 | # 4Suite: |
---|
30 | # stream = cStringIO.StringIO() |
---|
31 | # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
---|
32 | # s = stream.getvalue() |
---|
33 | # stream.close() |
---|
34 | return s |
---|
35 | |
---|
36 | def getMDText(node): |
---|
37 | """returns the @text content from the MetaDataProvider metadata node""" |
---|
38 | if isinstance(node, dict): |
---|
39 | return node.get('@text', None) |
---|
40 | |
---|
41 | return node |
---|
42 | |
---|
43 | def browserCheck(self): |
---|
44 | """check the browsers request to find out the browser type""" |
---|
45 | bt = {} |
---|
46 | ua = self.REQUEST.get_header("HTTP_USER_AGENT") |
---|
47 | bt['ua'] = ua |
---|
48 | bt['isIE'] = False |
---|
49 | bt['isN4'] = False |
---|
50 | bt['versFirefox']="" |
---|
51 | bt['versIE']="" |
---|
52 | bt['versSafariChrome']="" |
---|
53 | bt['versOpera']="" |
---|
54 | |
---|
55 | if string.find(ua, 'MSIE') > -1: |
---|
56 | bt['isIE'] = True |
---|
57 | else: |
---|
58 | bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) |
---|
59 | # Safari oder Chrome identification |
---|
60 | try: |
---|
61 | nav = ua[string.find(ua, '('):] |
---|
62 | nav1=ua[string.find(ua,')'):] |
---|
63 | nav2=nav1[string.find(nav1,'('):] |
---|
64 | nav3=nav2[string.find(nav2,')'):] |
---|
65 | ie = string.split(nav, "; ")[1] |
---|
66 | ie1 =string.split(nav1, " ")[2] |
---|
67 | ie2 =string.split(nav3, " ")[1] |
---|
68 | ie3 =string.split(nav3, " ")[2] |
---|
69 | if string.find(ie3, "Safari") >-1: |
---|
70 | bt['versSafariChrome']=string.split(ie2, "/")[1] |
---|
71 | except: pass |
---|
72 | # IE identification |
---|
73 | try: |
---|
74 | nav = ua[string.find(ua, '('):] |
---|
75 | ie = string.split(nav, "; ")[1] |
---|
76 | if string.find(ie, "MSIE") > -1: |
---|
77 | bt['versIE'] = string.split(ie, " ")[1] |
---|
78 | except:pass |
---|
79 | # Firefox identification |
---|
80 | try: |
---|
81 | nav = ua[string.find(ua, '('):] |
---|
82 | nav1=ua[string.find(ua,')'):] |
---|
83 | if string.find(ie1, "Firefox") >-1: |
---|
84 | nav5= string.split(ie1, "/")[1] |
---|
85 | logging.debug("FIREFOX: %s"%(nav5)) |
---|
86 | bt['versFirefox']=nav5[0:3] |
---|
87 | except:pass |
---|
88 | #Opera identification |
---|
89 | try: |
---|
90 | if string.find(ua,"Opera") >-1: |
---|
91 | nav = ua[string.find(ua, '('):] |
---|
92 | nav1=nav[string.find(nav,')'):] |
---|
93 | bt['versOpera']=string.split(nav1,"/")[2] |
---|
94 | except:pass |
---|
95 | |
---|
96 | bt['isMac'] = string.find(ua, 'Macintosh') > -1 |
---|
97 | bt['isWin'] = string.find(ua, 'Windows') > -1 |
---|
98 | bt['isIEWin'] = bt['isIE'] and bt['isWin'] |
---|
99 | bt['isIEMac'] = bt['isIE'] and bt['isMac'] |
---|
100 | bt['staticHTML'] = False |
---|
101 | |
---|
102 | return bt |
---|
103 | |
---|
104 | def getParentPath(path, cnt=1): |
---|
105 | """returns pathname shortened by cnt""" |
---|
106 | # make sure path doesn't end with / |
---|
107 | path = path.rstrip('/') |
---|
108 | # split by /, shorten, and reassemble |
---|
109 | return '/'.join(path.split('/')[0:-cnt]) |
---|
110 | |
---|
111 | ## |
---|
112 | ## documentViewer class |
---|
113 | ## |
---|
114 | class documentViewer(Folder): |
---|
115 | """document viewer""" |
---|
116 | meta_type="Document viewer" |
---|
117 | |
---|
118 | security=ClassSecurityInfo() |
---|
119 | manage_options=Folder.manage_options+( |
---|
120 | {'label':'Configuration','action':'changeDocumentViewerForm'}, |
---|
121 | ) |
---|
122 | |
---|
123 | metadataService = None |
---|
124 | """MetaDataFolder instance""" |
---|
125 | |
---|
126 | |
---|
127 | # |
---|
128 | # templates and forms |
---|
129 | # |
---|
130 | # viewMode templates |
---|
131 | viewer_text = PageTemplateFile('zpt/viewer_text', globals()) |
---|
132 | viewer_xml = PageTemplateFile('zpt/viewer_xml', globals()) |
---|
133 | viewer_images = PageTemplateFile('zpt/viewer_images', globals()) |
---|
134 | viewer_index = PageTemplateFile('zpt/viewer_index', globals()) |
---|
135 | viewer_thumbs = PageTemplateFile('zpt/viewer_thumbs', globals()) |
---|
136 | # available layer types (annotator not default) |
---|
137 | builtinLayers = {'text': ['dict','search','gis'], |
---|
138 | 'xml': None, 'images': None, 'index': ['extended']} |
---|
139 | availableLayers = builtinLayers; |
---|
140 | # layer templates |
---|
141 | layer_text_dict = PageTemplateFile('zpt/layer_text_dict', globals()) |
---|
142 | layer_text_search = PageTemplateFile('zpt/layer_text_search', globals()) |
---|
143 | layer_text_annotator = PageTemplateFile('zpt/layer_text_annotator', globals()) |
---|
144 | layer_text_gis = PageTemplateFile('zpt/layer_text_gis', globals()) |
---|
145 | layer_text_pundit = PageTemplateFile('zpt/layer_text_pundit', globals()) |
---|
146 | layer_index_extended = PageTemplateFile('zpt/layer_index_extended', globals()) |
---|
147 | # toc templates |
---|
148 | toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) |
---|
149 | toc_text = PageTemplateFile('zpt/toc_text', globals()) |
---|
150 | toc_figures = PageTemplateFile('zpt/toc_figures', globals()) |
---|
151 | toc_concordance = PageTemplateFile('zpt/toc_concordance', globals()) |
---|
152 | toc_none = PageTemplateFile('zpt/toc_none', globals()) |
---|
153 | # other templates |
---|
154 | common_template = PageTemplateFile('zpt/common_template', globals()) |
---|
155 | info_xml = PageTemplateFile('zpt/info_xml', globals()) |
---|
156 | docuviewer_css = ImageFile('css/docuviewer.css',globals()) |
---|
157 | # make docuviewer_css refreshable for development |
---|
158 | docuviewer_css.index_html = refreshingImageFileIndexHtml |
---|
159 | docuviewer_ie_css = ImageFile('css/docuviewer_ie.css',globals()) |
---|
160 | # make docuviewer_ie_css refreshable for development |
---|
161 | docuviewer_ie_css.index_html = refreshingImageFileIndexHtml |
---|
162 | jquery_js = ImageFile('js/jquery.js',globals()) |
---|
163 | |
---|
164 | |
---|
165 | def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
---|
166 | """init document viewer""" |
---|
167 | self.id=id |
---|
168 | self.title=title |
---|
169 | self.thumbcols = thumbcols |
---|
170 | self.thumbrows = thumbrows |
---|
171 | # authgroups is list of authorized groups (delimited by ,) |
---|
172 | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
---|
173 | # create template folder so we can always use template.something |
---|
174 | |
---|
175 | templateFolder = Folder('template') |
---|
176 | self['template'] = templateFolder # Zope-2.12 style |
---|
177 | #self._setObject('template',templateFolder) # old style |
---|
178 | try: |
---|
179 | import MpdlXmlTextServer |
---|
180 | textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
---|
181 | templateFolder['fulltextclient'] = textServer |
---|
182 | #templateFolder._setObject('fulltextclient',textServer) |
---|
183 | except Exception, e: |
---|
184 | logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
---|
185 | |
---|
186 | try: |
---|
187 | from Products.zogiLib.zogiLib import zogiLib |
---|
188 | zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
---|
189 | templateFolder['zogilib'] = zogilib |
---|
190 | #templateFolder._setObject('zogilib',zogilib) |
---|
191 | except Exception, e: |
---|
192 | logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
---|
193 | |
---|
194 | try: |
---|
195 | # assume MetaDataFolder instance is called metadata |
---|
196 | self.metadataService = getattr(self, 'metadata') |
---|
197 | except Exception, e: |
---|
198 | logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) |
---|
199 | |
---|
200 | if digilibBaseUrl is not None: |
---|
201 | self.digilibBaseUrl = digilibBaseUrl |
---|
202 | self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
---|
203 | self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' |
---|
204 | |
---|
205 | |
---|
206 | # proxy text server methods to fulltextclient |
---|
207 | def getTextPage(self, **args): |
---|
208 | """returns full text content of page""" |
---|
209 | return self.template.fulltextclient.getTextPage(**args) |
---|
210 | |
---|
211 | def getSearchResults(self, **args): |
---|
212 | """loads list of search results and stores XML in docinfo""" |
---|
213 | return self.template.fulltextclient.getSearchResults(**args) |
---|
214 | |
---|
215 | def getResultsPage(self, **args): |
---|
216 | """returns one page of the search results""" |
---|
217 | return self.template.fulltextclient.getResultsPage(**args) |
---|
218 | |
---|
219 | def getTextInfo(self, **args): |
---|
220 | """returns document info from the text server""" |
---|
221 | return self.template.fulltextclient.getTextInfo(**args) |
---|
222 | |
---|
223 | def getToc(self, **args): |
---|
224 | """loads table of contents and stores XML in docinfo""" |
---|
225 | return self.template.fulltextclient.getToc(**args) |
---|
226 | |
---|
227 | def getTocPage(self, **args): |
---|
228 | """returns one page of the table of contents""" |
---|
229 | return self.template.fulltextclient.getTocPage(**args) |
---|
230 | |
---|
231 | def getRepositoryType(self, **args): |
---|
232 | """get repository type""" |
---|
233 | return self.template.fulltextclient.getRepositoryType(**args) |
---|
234 | |
---|
235 | def getTextDownloadUrl(self, **args): |
---|
236 | """get list of gis places on one page""" |
---|
237 | return self.template.fulltextclient.getTextDownloadUrl(**args) |
---|
238 | |
---|
239 | def getPlacesOnPage(self, **args): |
---|
240 | """get list of gis places on one page""" |
---|
241 | return self.template.fulltextclient.getPlacesOnPage(**args) |
---|
242 | |
---|
243 | # Thumb list for CoolIris Plugin |
---|
244 | thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
---|
245 | security.declareProtected('View','thumbs_rss') |
---|
246 | def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): |
---|
247 | ''' |
---|
248 | view it |
---|
249 | @param mode: defines how to access the document behind url |
---|
250 | @param url: url which contains display information |
---|
251 | @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
---|
252 | |
---|
253 | ''' |
---|
254 | |
---|
255 | if not hasattr(self, 'template'): |
---|
256 | # create template folder if it doesn't exist |
---|
257 | self.manage_addFolder('template') |
---|
258 | |
---|
259 | if not self.digilibBaseUrl: |
---|
260 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
---|
261 | |
---|
262 | docinfo = self.getDocinfo(mode=mode,url=url) |
---|
263 | #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
---|
264 | pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) |
---|
265 | ''' ZDES ''' |
---|
266 | pt = getattr(self.template, 'thumbs_main_rss') |
---|
267 | |
---|
268 | if viewMode=="auto": # automodus gewaehlt |
---|
269 | if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
---|
270 | viewMode="text" |
---|
271 | else: |
---|
272 | viewMode="images" |
---|
273 | |
---|
274 | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
---|
275 | |
---|
276 | |
---|
277 | security.declareProtected('View','index_html') |
---|
278 | def index_html(self,url,mode="texttool",viewMode="auto",viewLayer=None,tocMode=None,start=1,pn=1): |
---|
279 | """ |
---|
280 | show page |
---|
281 | @param url: url which contains display information |
---|
282 | @param mode: defines how to access the document behind url |
---|
283 | @param viewMode: 'images': display images, 'text': display text, 'xml': display xml, default is 'auto' |
---|
284 | @param viewLayer: sub-type of viewMode, e.g. layer 'dict' for viewMode='text' |
---|
285 | @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
---|
286 | """ |
---|
287 | |
---|
288 | logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewLayer=%s start=%s pn=%s"%(mode,url,viewMode,viewLayer,start,pn)) |
---|
289 | |
---|
290 | if not hasattr(self, 'template'): |
---|
291 | # this won't work |
---|
292 | logging.error("template folder missing!") |
---|
293 | return "ERROR: template folder missing!" |
---|
294 | |
---|
295 | if not getattr(self, 'digilibBaseUrl', None): |
---|
296 | self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
---|
297 | |
---|
298 | # mode=filepath should not have toc-thumbs |
---|
299 | if tocMode is None: |
---|
300 | if mode == "filepath": |
---|
301 | tocMode = "none" |
---|
302 | else: |
---|
303 | tocMode = "thumbs" |
---|
304 | |
---|
305 | # docinfo: information about document (cached) |
---|
306 | docinfo = self.getDocinfo(mode=mode,url=url,tocMode=tocMode) |
---|
307 | |
---|
308 | # userinfo: user settings (cached) |
---|
309 | userinfo = self.getUserinfo() |
---|
310 | |
---|
311 | # auto viewMode: text if there is a text else images |
---|
312 | if viewMode=="auto": |
---|
313 | if docinfo.get('textURLPath', None): |
---|
314 | # docinfo.get('textURL', None) not implemented yet |
---|
315 | viewMode = "text" |
---|
316 | if viewLayer is None and 'viewLayer' not in userinfo: |
---|
317 | # use layer dict as default |
---|
318 | viewLayer = "dict" |
---|
319 | else: |
---|
320 | viewMode = "images" |
---|
321 | |
---|
322 | elif viewMode == "text_dict": |
---|
323 | # legacy fix |
---|
324 | viewMode = "text" |
---|
325 | viewLayer = "dict" |
---|
326 | |
---|
327 | # safe viewLayer in userinfo |
---|
328 | userinfo['viewLayer'] = viewLayer |
---|
329 | |
---|
330 | # pageinfo: information about page (not cached) |
---|
331 | pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, userinfo=userinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode) |
---|
332 | |
---|
333 | # get template /template/viewer_$viewMode |
---|
334 | pt = getattr(self.template, 'viewer_%s'%viewMode, None) |
---|
335 | if pt is None: |
---|
336 | logging.error("No template for viewMode=%s!"%viewMode) |
---|
337 | # TODO: error page? |
---|
338 | return "No template for viewMode=%s!"%viewMode |
---|
339 | |
---|
340 | # and execute with parameters |
---|
341 | return pt(docinfo=docinfo, pageinfo=pageinfo) |
---|
342 | |
---|
343 | def getAvailableLayers(self): |
---|
344 | """returns dict with list of available layers per viewMode""" |
---|
345 | return self.availableLayers |
---|
346 | |
---|
347 | def getBrowser(self): |
---|
348 | """getBrowser the version of browser """ |
---|
349 | bt = browserCheck(self) |
---|
350 | logging.debug("BROWSER VERSION: %s"%(bt)) |
---|
351 | return bt |
---|
352 | |
---|
353 | def findDigilibUrl(self): |
---|
354 | """try to get the digilib URL from zogilib""" |
---|
355 | url = self.template.zogilib.getDLBaseUrl() |
---|
356 | return url |
---|
357 | |
---|
358 | def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None): |
---|
359 | """returns URL to digilib Scaler with params""" |
---|
360 | url = None |
---|
361 | if docinfo is not None: |
---|
362 | url = docinfo.get('imageURL', None) |
---|
363 | |
---|
364 | if url is None: |
---|
365 | url = self.digilibScalerUrl |
---|
366 | if fn is None and docinfo is not None: |
---|
367 | fn = docinfo.get('imagePath','') |
---|
368 | |
---|
369 | url += "fn=%s"%fn |
---|
370 | |
---|
371 | if pn: |
---|
372 | url += "&pn=%s"%pn |
---|
373 | |
---|
374 | url += "&dw=%s&dh=%s"%(dw,dh) |
---|
375 | return url |
---|
376 | |
---|
377 | def getDocumentViewerURL(self): |
---|
378 | """returns the URL of this instance""" |
---|
379 | return self.absolute_url() |
---|
380 | |
---|
381 | def getStyle(self, idx, selected, style=""): |
---|
382 | """returns a string with the given style and append 'sel' if idx == selected.""" |
---|
383 | #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
---|
384 | if idx == selected: |
---|
385 | return style + 'sel' |
---|
386 | else: |
---|
387 | return style |
---|
388 | |
---|
389 | def getParams(self, param=None, val=None, params=None, duplicates=None): |
---|
390 | """returns dict with URL parameters. |
---|
391 | |
---|
392 | Takes URL parameters and additionally param=val or dict params. |
---|
393 | Deletes key if value is None.""" |
---|
394 | # copy existing request params |
---|
395 | newParams=self.REQUEST.form.copy() |
---|
396 | # change single param |
---|
397 | if param is not None: |
---|
398 | if val is None: |
---|
399 | if newParams.has_key(param): |
---|
400 | del newParams[param] |
---|
401 | else: |
---|
402 | newParams[param] = str(val) |
---|
403 | |
---|
404 | # change more params |
---|
405 | if params is not None: |
---|
406 | for (k, v) in params.items(): |
---|
407 | if v is None: |
---|
408 | # val=None removes param |
---|
409 | if newParams.has_key(k): |
---|
410 | del newParams[k] |
---|
411 | |
---|
412 | else: |
---|
413 | newParams[k] = v |
---|
414 | |
---|
415 | if duplicates: |
---|
416 | # eliminate lists (coming from duplicate keys) |
---|
417 | for (k,v) in newParams.items(): |
---|
418 | if isinstance(v, list): |
---|
419 | if duplicates == 'comma': |
---|
420 | # make comma-separated list of non-empty entries |
---|
421 | newParams[k] = ','.join([t for t in v if t]) |
---|
422 | elif duplicates == 'first': |
---|
423 | # take first non-empty entry |
---|
424 | newParams[k] = [t for t in v if t][0] |
---|
425 | |
---|
426 | return newParams |
---|
427 | |
---|
428 | def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
---|
429 | """returns URL to documentviewer with parameter param set to val or from dict params""" |
---|
430 | urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates) |
---|
431 | # quote values and assemble into query string (not escaping '/') |
---|
432 | ps = paramSep.join(["%s=%s"%(k, urllib.quote_plus(utf8ify(v), '/')) for (k, v) in urlParams.items()]) |
---|
433 | if baseUrl is None: |
---|
434 | baseUrl = self.getDocumentViewerURL() |
---|
435 | |
---|
436 | url = "%s?%s"%(baseUrl, ps) |
---|
437 | return url |
---|
438 | |
---|
439 | def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
---|
440 | """link to documentviewer with parameter param set to val""" |
---|
441 | return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&', duplicates=duplicates) |
---|
442 | |
---|
443 | |
---|
444 | def setAvailableLayers(self, newLayerString=None): |
---|
445 | """sets availableLayers to newLayerString or tries to autodetect available layers. |
---|
446 | assumes layer templates have the form layer_{m}_{l} for layer l in mode m. |
---|
447 | newLayerString is parsed as JSON.""" |
---|
448 | if newLayerString is not None: |
---|
449 | try: |
---|
450 | layers = json.loads(newLayerString) |
---|
451 | if 'text' in layers and 'images' in layers: |
---|
452 | self.availableLayers = layers |
---|
453 | return |
---|
454 | except: |
---|
455 | pass |
---|
456 | |
---|
457 | logging.error("invalid layers=%s! autodetecting..."%repr(newLayerString)) |
---|
458 | |
---|
459 | # start with builtin layers |
---|
460 | self.availableLayers = self.builtinLayers.copy() |
---|
461 | # add layers from templates |
---|
462 | for t in self.template: |
---|
463 | if t.startswith('layer_'): |
---|
464 | try: |
---|
465 | (x, m, l) = t.split('_', 3) |
---|
466 | if m not in self.availableLayers: |
---|
467 | # mode m doesn't exist -> new list |
---|
468 | self.availableLayers[m] = [l] |
---|
469 | |
---|
470 | else: |
---|
471 | # m exists -> append |
---|
472 | if l not in self.availableLayers[m]: |
---|
473 | self.availableLayers[m].append() |
---|
474 | |
---|
475 | except: |
---|
476 | pass |
---|
477 | |
---|
478 | def getAvailableLayersJson(self): |
---|
479 | """returns available layers as JSON string.""" |
---|
480 | return json.dumps(self.availableLayers) |
---|
481 | |
---|
482 | |
---|
483 | def getInfo_xml(self,url,mode): |
---|
484 | """returns info about the document as XML""" |
---|
485 | if not self.digilibBaseUrl: |
---|
486 | self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
---|
487 | |
---|
488 | docinfo = self.getDocinfo(mode=mode,url=url) |
---|
489 | pt = getattr(self.template, 'info_xml') |
---|
490 | return pt(docinfo=docinfo) |
---|
491 | |
---|
492 | def getAuthenticatedUser(self, anon=None): |
---|
493 | """returns the authenticated user object or None. (ignores Zopes anonymous user)""" |
---|
494 | user = getSecurityManager().getUser() |
---|
495 | if user is not None and user.getUserName() != "Anonymous User": |
---|
496 | return user |
---|
497 | else: |
---|
498 | return anon |
---|
499 | |
---|
500 | def isAccessible(self, docinfo): |
---|
501 | """returns if access to the resource is granted""" |
---|
502 | access = docinfo.get('accessType', None) |
---|
503 | logging.debug("documentViewer (accessOK) access type %s"%access) |
---|
504 | if access == 'free': |
---|
505 | logging.debug("documentViewer (accessOK) access is free") |
---|
506 | return True |
---|
507 | |
---|
508 | elif access is None or access in self.authgroups: |
---|
509 | # only local access -- only logged in users |
---|
510 | user = self.getAuthenticatedUser() |
---|
511 | logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
---|
512 | return (user is not None) |
---|
513 | |
---|
514 | logging.error("documentViewer (accessOK) unknown access type %s"%access) |
---|
515 | return False |
---|
516 | |
---|
517 | |
---|
518 | def getUserinfo(self): |
---|
519 | """returns userinfo object""" |
---|
520 | logging.debug("getUserinfo") |
---|
521 | userinfo = {} |
---|
522 | # look for cached userinfo in session |
---|
523 | if self.REQUEST.SESSION.has_key('userinfo'): |
---|
524 | userinfo = self.REQUEST.SESSION['userinfo'] |
---|
525 | # check if its still current? |
---|
526 | else: |
---|
527 | # store in session |
---|
528 | self.REQUEST.SESSION['userinfo'] = userinfo |
---|
529 | |
---|
530 | return userinfo |
---|
531 | |
---|
532 | def getDocinfo(self, mode, url, tocMode=None): |
---|
533 | """returns docinfo depending on mode""" |
---|
534 | logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) |
---|
535 | # look for cached docinfo in session |
---|
536 | if self.REQUEST.SESSION.has_key('docinfo'): |
---|
537 | docinfo = self.REQUEST.SESSION['docinfo'] |
---|
538 | # check if its still current |
---|
539 | if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: |
---|
540 | logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) |
---|
541 | return docinfo |
---|
542 | |
---|
543 | # new docinfo |
---|
544 | docinfo = {'mode': mode, 'url': url} |
---|
545 | # add self url |
---|
546 | docinfo['viewerUrl'] = self.getDocumentViewerURL() |
---|
547 | docinfo['digilibBaseUrl'] = self.digilibBaseUrl |
---|
548 | docinfo['digilibScalerUrl'] = self.digilibScalerUrl |
---|
549 | docinfo['digilibViewerUrl'] = self.digilibViewerUrl |
---|
550 | # get index.meta DOM |
---|
551 | docUrl = None |
---|
552 | metaDom = None |
---|
553 | if mode=="texttool": |
---|
554 | # url points to document dir or index.meta |
---|
555 | metaDom = self.metadataService.getDomFromPathOrUrl(url) |
---|
556 | docUrl = url.replace('/index.meta', '') |
---|
557 | if metaDom is None: |
---|
558 | raise IOError("Unable to find index.meta for mode=texttool!") |
---|
559 | |
---|
560 | elif mode=="imagepath": |
---|
561 | # url points to folder with images, index.meta optional |
---|
562 | # asssume index.meta in parent dir |
---|
563 | docUrl = getParentPath(url) |
---|
564 | metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
---|
565 | docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1) |
---|
566 | |
---|
567 | elif mode=="filepath": |
---|
568 | # url points to image file, index.meta optional |
---|
569 | docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, url) |
---|
570 | docinfo['numPages'] = 1 |
---|
571 | # asssume index.meta is two path segments up |
---|
572 | docUrl = getParentPath(url, 2) |
---|
573 | metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
---|
574 | |
---|
575 | else: |
---|
576 | logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
---|
577 | raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
---|
578 | |
---|
579 | docinfo['documentUrl'] = docUrl |
---|
580 | # process index.meta contents |
---|
581 | if metaDom is not None and metaDom.tag == 'resource': |
---|
582 | # document directory name and path |
---|
583 | resource = self.metadataService.getResourceData(dom=metaDom) |
---|
584 | if resource: |
---|
585 | docinfo = self.getDocinfoFromResource(docinfo, resource) |
---|
586 | |
---|
587 | # texttool info |
---|
588 | texttool = self.metadataService.getTexttoolData(dom=metaDom, recursive=1, all=True) |
---|
589 | if texttool: |
---|
590 | docinfo = self.getDocinfoFromTexttool(docinfo, texttool) |
---|
591 | # document info (including toc) from full text |
---|
592 | if docinfo.get('textURLPath', None): |
---|
593 | docinfo = self.getTextInfo(mode=None, docinfo=docinfo) |
---|
594 | |
---|
595 | # bib info |
---|
596 | bib = self.metadataService.getBibData(dom=metaDom) |
---|
597 | if bib: |
---|
598 | # save extended version as 'bibx' TODO: ugly |
---|
599 | bibx = self.metadataService.getBibData(dom=metaDom, all=True, recursive=1) |
---|
600 | if len(bibx) == 1: |
---|
601 | # unwrap list if possible |
---|
602 | bibx = bibx[0] |
---|
603 | |
---|
604 | docinfo['bibx'] = bibx |
---|
605 | docinfo = self.getDocinfoFromBib(docinfo, bib, bibx) |
---|
606 | else: |
---|
607 | # no bib - try info.xml |
---|
608 | docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) |
---|
609 | |
---|
610 | # auth info |
---|
611 | access = self.metadataService.getAccessData(dom=metaDom) |
---|
612 | if access: |
---|
613 | docinfo = self.getDocinfoFromAccess(docinfo, access) |
---|
614 | |
---|
615 | # attribution info |
---|
616 | attribution = self.metadataService.getAttributionData(dom=metaDom) |
---|
617 | if attribution: |
---|
618 | logging.debug("getDocinfo: attribution=%s"%repr(attribution)) |
---|
619 | docinfo['attribution'] = attribution |
---|
620 | |
---|
621 | # copyright info |
---|
622 | copyright = self.metadataService.getCopyrightData(dom=metaDom) |
---|
623 | if copyright: |
---|
624 | logging.debug("getDocinfo: copyright=%s"%repr(copyright)) |
---|
625 | docinfo['copyright'] = copyright |
---|
626 | |
---|
627 | # DRI (permanent ID) |
---|
628 | dri = self.metadataService.getDRI(dom=metaDom, type='escidoc') |
---|
629 | if dri: |
---|
630 | logging.debug("getDRI: dri=%s"%repr(dri)) |
---|
631 | docinfo['DRI'] = dri |
---|
632 | |
---|
633 | # image path |
---|
634 | if mode != 'texttool': |
---|
635 | # override image path from texttool with url parameter TODO: how about mode=auto? |
---|
636 | docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1) |
---|
637 | |
---|
638 | # check numPages |
---|
639 | if docinfo.get('numPages', 0) == 0: |
---|
640 | # number of images from digilib |
---|
641 | if docinfo.get('imagePath', None): |
---|
642 | imgpath = docinfo['imagePath'].replace('/mpiwg/online/', '', 1) |
---|
643 | docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, imgpath) |
---|
644 | docinfo = self.getDocinfoFromDigilib(docinfo, imgpath) |
---|
645 | else: |
---|
646 | # imagePath still missing? try "./pageimg" |
---|
647 | imgPath = os.path.join(docUrl, 'pageimg') |
---|
648 | docinfo = self.getDocinfoFromDigilib(docinfo, imgPath) |
---|
649 | if docinfo.get('numPages', 0) > 0: |
---|
650 | # there are pages |
---|
651 | docinfo['imagePath'] = imgPath |
---|
652 | docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, docinfo['imagePath']) |
---|
653 | |
---|
654 | # check numPages |
---|
655 | if docinfo.get('numPages', 0) == 0: |
---|
656 | if docinfo.get('numTextPages', 0) > 0: |
---|
657 | # replace with numTextPages (text-only?) |
---|
658 | docinfo['numPages'] = docinfo['numTextPages'] |
---|
659 | |
---|
660 | logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
---|
661 | #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
---|
662 | # store in session |
---|
663 | self.REQUEST.SESSION['docinfo'] = docinfo |
---|
664 | return docinfo |
---|
665 | |
---|
666 | |
---|
667 | def getDocinfoFromResource(self, docinfo, resource): |
---|
668 | """reads contents of resource element into docinfo""" |
---|
669 | docName = resource.get('name', None) |
---|
670 | docinfo['documentName'] = docName |
---|
671 | docPath = resource.get('archive-path', None) |
---|
672 | if docPath: |
---|
673 | # clean up document path |
---|
674 | if docPath[0] != '/': |
---|
675 | docPath = '/' + docPath |
---|
676 | |
---|
677 | if docName and (not docPath.endswith(docName)): |
---|
678 | docPath += "/" + docName |
---|
679 | |
---|
680 | else: |
---|
681 | # use docUrl as docPath |
---|
682 | docUrl = docinfo['documentURL'] |
---|
683 | if not docUrl.startswith('http:'): |
---|
684 | docPath = docUrl |
---|
685 | if docPath: |
---|
686 | # fix URLs starting with /mpiwg/online |
---|
687 | docPath = docPath.replace('/mpiwg/online', '', 1) |
---|
688 | |
---|
689 | docinfo['documentPath'] = docPath |
---|
690 | return docinfo |
---|
691 | |
---|
692 | def getDocinfoFromTexttool(self, docinfo, texttool): |
---|
693 | """reads contents of texttool element into docinfo""" |
---|
694 | logging.debug("texttool=%s"%repr(texttool)) |
---|
695 | # unpack list if necessary |
---|
696 | if isinstance(texttool, list): |
---|
697 | texttool = texttool[0] |
---|
698 | |
---|
699 | # image dir |
---|
700 | imageDir = getMDText(texttool.get('image', None)) |
---|
701 | docPath = getMDText(docinfo.get('documentPath', None)) |
---|
702 | if imageDir and docPath: |
---|
703 | imageDir = os.path.join(docPath, imageDir) |
---|
704 | imageDir = imageDir.replace('/mpiwg/online', '', 1) |
---|
705 | docinfo['imagePath'] = imageDir |
---|
706 | |
---|
707 | # old style text URL |
---|
708 | textUrl = getMDText(texttool.get('text', None)) |
---|
709 | if textUrl and docPath: |
---|
710 | if urlparse.urlparse(textUrl)[0] == "": #keine url |
---|
711 | textUrl = os.path.join(docPath, textUrl) |
---|
712 | |
---|
713 | docinfo['textURL'] = textUrl |
---|
714 | |
---|
715 | # new style text-url-path (can be more than one with "repository" attribute) |
---|
716 | textUrlNode = texttool.get('text-url-path', None) |
---|
717 | if not isinstance(textUrlNode, list): |
---|
718 | textUrlNode = [textUrlNode] |
---|
719 | |
---|
720 | for tun in textUrlNode: |
---|
721 | textUrl = getMDText(tun) |
---|
722 | if textUrl: |
---|
723 | textUrlAtts = tun.get('@attr') |
---|
724 | if (textUrlAtts and 'repository' in textUrlAtts): |
---|
725 | textRepo = textUrlAtts['repository'] |
---|
726 | # use matching repository |
---|
727 | if self.getRepositoryType() == textRepo: |
---|
728 | docinfo['textURLPath'] = textUrl |
---|
729 | docinfo['textURLRepository'] = textRepo |
---|
730 | break |
---|
731 | |
---|
732 | else: |
---|
733 | # no repo attribute - use always |
---|
734 | docinfo['textURLPath'] = textUrl |
---|
735 | |
---|
736 | # page flow |
---|
737 | docinfo['pageFlow'] = getMDText(texttool.get('page-flow', 'ltr')) |
---|
738 | |
---|
739 | # odd pages are left |
---|
740 | docinfo['oddPage'] = getMDText(texttool.get('odd-scan-position', 'left')) |
---|
741 | |
---|
742 | # number of title page (default 1) |
---|
743 | docinfo['titlePage'] = getMDText(texttool.get('title-scan-no', 1)) |
---|
744 | |
---|
745 | # old presentation stuff |
---|
746 | presentation = getMDText(texttool.get('presentation', None)) |
---|
747 | if presentation and docPath: |
---|
748 | if presentation.startswith('http:'): |
---|
749 | docinfo['presentationUrl'] = presentation |
---|
750 | else: |
---|
751 | docinfo['presentationUrl'] = os.path.join(docPath, presentation) |
---|
752 | |
---|
753 | return docinfo |
---|
754 | |
---|
755 | def getDocinfoFromBib(self, docinfo, bib, bibx=None): |
---|
756 | """reads contents of bib element into docinfo""" |
---|
757 | logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
---|
758 | # put all raw bib fields in dict "bib" |
---|
759 | docinfo['bib'] = bib |
---|
760 | bibtype = bib.get('@type', None) |
---|
761 | docinfo['bibType'] = bibtype |
---|
762 | # also store DC metadata for convenience |
---|
763 | dc = self.metadataService.getDCMappedData(bib) |
---|
764 | docinfo['creator'] = dc.get('creator','') |
---|
765 | docinfo['title'] = dc.get('title','') |
---|
766 | docinfo['date'] = dc.get('date','') |
---|
767 | return docinfo |
---|
768 | |
---|
769 | def getDocinfoFromAccess(self, docinfo, acc): |
---|
770 | """reads contents of access element into docinfo""" |
---|
771 | #TODO: also read resource type |
---|
772 | logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
---|
773 | try: |
---|
774 | acctype = acc['@attr']['type'] |
---|
775 | if acctype: |
---|
776 | access=acctype |
---|
777 | if access in ['group', 'institution']: |
---|
778 | access = acc['name'].lower() |
---|
779 | |
---|
780 | docinfo['accessType'] = access |
---|
781 | |
---|
782 | except: |
---|
783 | pass |
---|
784 | |
---|
785 | return docinfo |
---|
786 | |
---|
787 | def getDocinfoFromDigilib(self, docinfo, path): |
---|
788 | infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
---|
789 | # fetch data |
---|
790 | txt = getHttpData(infoUrl) |
---|
791 | if not txt: |
---|
792 | logging.error("Unable to get dir-info from %s"%(infoUrl)) |
---|
793 | return docinfo |
---|
794 | |
---|
795 | dom = ET.fromstring(txt) |
---|
796 | size = getText(dom.find("size")) |
---|
797 | logging.debug("getDocinfoFromDigilib: size=%s"%size) |
---|
798 | if size: |
---|
799 | docinfo['numPages'] = int(size) |
---|
800 | else: |
---|
801 | docinfo['numPages'] = 0 |
---|
802 | |
---|
803 | # TODO: produce and keep list of image names and numbers |
---|
804 | return docinfo |
---|
805 | |
---|
806 | |
---|
807 | def getDocinfoFromPresentationInfoXml(self,docinfo): |
---|
808 | """gets DC-like bibliographical information from the presentation entry in texttools""" |
---|
809 | url = docinfo.get('presentationUrl', None) |
---|
810 | if not url: |
---|
811 | logging.error("getDocinfoFromPresentation: no URL!") |
---|
812 | return docinfo |
---|
813 | |
---|
814 | dom = None |
---|
815 | metaUrl = None |
---|
816 | if url.startswith("http://"): |
---|
817 | # real URL |
---|
818 | metaUrl = url |
---|
819 | else: |
---|
820 | # online path |
---|
821 | |
---|
822 | server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
---|
823 | metaUrl=server+url |
---|
824 | |
---|
825 | txt=getHttpData(metaUrl) |
---|
826 | if txt is None: |
---|
827 | logging.error("Unable to read info.xml from %s"%(url)) |
---|
828 | return docinfo |
---|
829 | |
---|
830 | dom = ET.fromstring(txt) |
---|
831 | docinfo['creator']=getText(dom.find(".//author")) |
---|
832 | docinfo['title']=getText(dom.find(".//title")) |
---|
833 | docinfo['date']=getText(dom.find(".//date")) |
---|
834 | return docinfo |
---|
835 | |
---|
836 | |
---|
837 | def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, userinfo=None, viewMode=None, viewLayer=None, tocMode=None): |
---|
838 | """returns pageinfo with the given parameters""" |
---|
839 | logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewLayer=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewLayer,tocMode)) |
---|
840 | pageinfo = {} |
---|
841 | pageinfo['viewMode'] = viewMode |
---|
842 | # split viewLayer if necessary |
---|
843 | if isinstance(viewLayer,basestring): |
---|
844 | viewLayer = viewLayer.split(',') |
---|
845 | |
---|
846 | if isinstance(viewLayer, list): |
---|
847 | logging.debug("getPageinfo: viewLayer is list:%s"%viewLayer) |
---|
848 | # save (unique) list in viewLayers |
---|
849 | seen = set() |
---|
850 | viewLayers = [l for l in viewLayer if l and l not in seen and not seen.add(l)] |
---|
851 | pageinfo['viewLayers'] = viewLayers |
---|
852 | # stringify viewLayer |
---|
853 | viewLayer = ','.join(viewLayers) |
---|
854 | else: |
---|
855 | #create list |
---|
856 | pageinfo['viewLayers'] = [viewLayer] |
---|
857 | |
---|
858 | pageinfo['viewLayer'] = viewLayer |
---|
859 | pageinfo['tocMode'] = tocMode |
---|
860 | |
---|
861 | # TODO: unify current and pn! |
---|
862 | current = getInt(current) |
---|
863 | pageinfo['current'] = current |
---|
864 | pageinfo['pn'] = current |
---|
865 | rows = int(rows or self.thumbrows) |
---|
866 | pageinfo['rows'] = rows |
---|
867 | cols = int(cols or self.thumbcols) |
---|
868 | pageinfo['cols'] = cols |
---|
869 | grpsize = cols * rows |
---|
870 | pageinfo['groupsize'] = grpsize |
---|
871 | # is start is empty use one around current |
---|
872 | start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
---|
873 | # int(current / grpsize) * grpsize +1)) |
---|
874 | pageinfo['start'] = start |
---|
875 | # get number of pages |
---|
876 | np = int(docinfo.get('numPages', 0)) |
---|
877 | if np == 0: |
---|
878 | # try numTextPages |
---|
879 | np = docinfo.get('numTextPages', 0) |
---|
880 | if np != 0: |
---|
881 | docinfo['numPages'] = np |
---|
882 | |
---|
883 | # cache table of contents |
---|
884 | pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) |
---|
885 | pageinfo['numgroups'] = int(np / grpsize) |
---|
886 | if np % grpsize > 0: |
---|
887 | pageinfo['numgroups'] += 1 |
---|
888 | |
---|
889 | pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' |
---|
890 | oddScanLeft = docinfo.get('oddPage', 'left') != 'right' |
---|
891 | # add zeroth page for two columns |
---|
892 | pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) |
---|
893 | pageinfo['pageZero'] = pageZero |
---|
894 | pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np) |
---|
895 | # more page parameters |
---|
896 | pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
---|
897 | if docinfo.get('pageNumbers'): |
---|
898 | # get original page numbers |
---|
899 | pageNumber = docinfo['pageNumbers'].get(current, None) |
---|
900 | if pageNumber is not None: |
---|
901 | pageinfo['pageNumberOrig'] = pageNumber['no'] |
---|
902 | pageinfo['pageNumberOrigNorm'] = pageNumber['non'] |
---|
903 | |
---|
904 | # cache search results |
---|
905 | pageinfo['resultPageSize'] = getInt(self.REQUEST.get('resultPageSize', 10)) |
---|
906 | query = self.REQUEST.get('query',None) |
---|
907 | pageinfo['query'] = query |
---|
908 | if query: |
---|
909 | queryType = self.REQUEST.get('queryType', 'fulltextMorph') |
---|
910 | pageinfo['queryType'] = queryType |
---|
911 | pageinfo['resultStart'] = getInt(self.REQUEST.get('resultStart', '1')) |
---|
912 | self.getSearchResults(mode=queryType, query=query, pageinfo=pageinfo, docinfo=docinfo) |
---|
913 | |
---|
914 | # highlighting |
---|
915 | highlightQuery = self.REQUEST.get('highlightQuery', None) |
---|
916 | if highlightQuery: |
---|
917 | pageinfo['highlightQuery'] = highlightQuery |
---|
918 | pageinfo['highlightElement'] = self.REQUEST.get('highlightElement', '') |
---|
919 | pageinfo['highlightElementPos'] = self.REQUEST.get('highlightElementPos', '') |
---|
920 | |
---|
921 | return pageinfo |
---|
922 | |
---|
923 | |
---|
924 | def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0): |
---|
925 | """returns dict with array of page informations for one screenfull of thumbnails""" |
---|
926 | batch = {} |
---|
927 | grpsize = rows * cols |
---|
928 | if maxIdx == 0: |
---|
929 | maxIdx = start + grpsize |
---|
930 | |
---|
931 | nb = int(math.ceil(maxIdx / float(grpsize))) |
---|
932 | # list of all batch start and end points |
---|
933 | batches = [] |
---|
934 | if pageZero: |
---|
935 | ofs = 0 |
---|
936 | else: |
---|
937 | ofs = 1 |
---|
938 | |
---|
939 | for i in range(nb): |
---|
940 | s = i * grpsize + ofs |
---|
941 | e = min((i + 1) * grpsize + ofs - 1, maxIdx) |
---|
942 | batches.append({'start':s, 'end':e}) |
---|
943 | |
---|
944 | batch['batches'] = batches |
---|
945 | |
---|
946 | pages = [] |
---|
947 | if pageZero and start == 1: |
---|
948 | # correct beginning |
---|
949 | idx = 0 |
---|
950 | else: |
---|
951 | idx = start |
---|
952 | |
---|
953 | for r in range(rows): |
---|
954 | row = [] |
---|
955 | for c in range(cols): |
---|
956 | if idx < minIdx or idx > maxIdx: |
---|
957 | page = {'idx':None} |
---|
958 | else: |
---|
959 | page = {'idx':idx} |
---|
960 | |
---|
961 | idx += 1 |
---|
962 | if pageFlowLtr: |
---|
963 | row.append(page) |
---|
964 | else: |
---|
965 | row.insert(0, page) |
---|
966 | |
---|
967 | pages.append(row) |
---|
968 | |
---|
969 | if start > 1: |
---|
970 | batch['prevStart'] = max(start - grpsize, 1) |
---|
971 | else: |
---|
972 | batch['prevStart'] = None |
---|
973 | |
---|
974 | if start + grpsize <= maxIdx: |
---|
975 | batch['nextStart'] = start + grpsize |
---|
976 | else: |
---|
977 | batch['nextStart'] = None |
---|
978 | |
---|
979 | batch['pages'] = pages |
---|
980 | return batch |
---|
981 | |
---|
982 | def getBatch(self, start=1, size=10, end=0, data=None, fullData=True): |
---|
983 | """returns dict with information for one screenfull of data.""" |
---|
984 | batch = {} |
---|
985 | if end == 0: |
---|
986 | end = start + size |
---|
987 | |
---|
988 | nb = int(math.ceil(end / float(size))) |
---|
989 | # list of all batch start and end points |
---|
990 | batches = [] |
---|
991 | for i in range(nb): |
---|
992 | s = i * size + 1 |
---|
993 | e = min((i + 1) * size, end) |
---|
994 | batches.append({'start':s, 'end':e}) |
---|
995 | |
---|
996 | batch['batches'] = batches |
---|
997 | # list of elements in this batch |
---|
998 | this = [] |
---|
999 | j = 0 |
---|
1000 | for i in range(start, min(start+size, end+1)): |
---|
1001 | if data: |
---|
1002 | if fullData: |
---|
1003 | d = data.get(i, None) |
---|
1004 | else: |
---|
1005 | d = data.get(j, None) |
---|
1006 | j += 1 |
---|
1007 | |
---|
1008 | else: |
---|
1009 | d = i+1 |
---|
1010 | |
---|
1011 | this.append(d) |
---|
1012 | |
---|
1013 | batch['this'] = this |
---|
1014 | if start > 1: |
---|
1015 | batch['prevStart'] = max(start - size, 1) |
---|
1016 | else: |
---|
1017 | batch['prevStart'] = None |
---|
1018 | |
---|
1019 | if start + size < end: |
---|
1020 | batch['nextStart'] = start + size |
---|
1021 | else: |
---|
1022 | batch['nextStart'] = None |
---|
1023 | |
---|
1024 | logging.debug("getBatch start=%s size=%s end=%s batch=%s"%(start,size,end,repr(batch))) |
---|
1025 | return batch |
---|
1026 | |
---|
1027 | |
---|
1028 | def getAnnotatorGroupsForUser(self, user, annotationServerUrl="http://tuxserve03.mpiwg-berlin.mpg.de/AnnotationManager"): |
---|
1029 | """returns list of groups {name:*, id:*} on the annotation server for the user""" |
---|
1030 | groups = [] |
---|
1031 | groupsUrl = "%s/annotator/groups?user=%s"%(annotationServerUrl,user) |
---|
1032 | data = getHttpData(url=groupsUrl, noExceptions=True) |
---|
1033 | if data: |
---|
1034 | res = json.loads(data) |
---|
1035 | rows = res.get('rows', None) |
---|
1036 | if rows is None: |
---|
1037 | return groups |
---|
1038 | for r in rows: |
---|
1039 | groups.append({'id': r.get('id', None), 'name': r.get('name', None), 'uri': r.get('uri', None)}) |
---|
1040 | |
---|
1041 | return groups |
---|
1042 | |
---|
1043 | |
---|
1044 | security.declareProtected('View management screens','changeDocumentViewerForm') |
---|
1045 | changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
---|
1046 | |
---|
1047 | def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',availableLayers=None,RESPONSE=None): |
---|
1048 | """init document viewer""" |
---|
1049 | self.title=title |
---|
1050 | self.digilibBaseUrl = digilibBaseUrl |
---|
1051 | self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
---|
1052 | self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' |
---|
1053 | self.thumbrows = thumbrows |
---|
1054 | self.thumbcols = thumbcols |
---|
1055 | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
---|
1056 | try: |
---|
1057 | # assume MetaDataFolder instance is called metadata |
---|
1058 | self.metadataService = getattr(self, 'metadata') |
---|
1059 | except Exception, e: |
---|
1060 | logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) |
---|
1061 | |
---|
1062 | self.setAvailableLayers(availableLayers) |
---|
1063 | |
---|
1064 | if RESPONSE is not None: |
---|
1065 | RESPONSE.redirect('manage_main') |
---|
1066 | |
---|
1067 | def manage_AddDocumentViewerForm(self): |
---|
1068 | """add the viewer form""" |
---|
1069 | pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
---|
1070 | return pt() |
---|
1071 | |
---|
1072 | def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
---|
1073 | """add the viewer""" |
---|
1074 | newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
---|
1075 | self._setObject(id,newObj) |
---|
1076 | |
---|
1077 | if RESPONSE is not None: |
---|
1078 | RESPONSE.redirect('manage_main') |
---|