Mercurial > hg > documentViewer
annotate documentViewer.py @ 625:80a3b1fa5705
more move sslification to only client-visible urls.
author | casties |
---|---|
date | Mon, 15 Dec 2014 17:18:20 +0100 |
parents | 80a0191ae51c |
children | 7dafe8283312 |
rev | line source |
---|---|
0 | 1 from OFS.Folder import Folder |
2 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate | |
486 | 3 from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
487 | 4 from App.ImageFile import ImageFile |
0 | 5 from AccessControl import ClassSecurityInfo |
32 | 6 from AccessControl import getSecurityManager |
0 | 7 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
8 import xml.etree.ElementTree as ET |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
9 |
489
55e3398e395e
more new templates. monkey-patch for App.ImageFile.
casties
parents:
488
diff
changeset
|
10 import os |
0 | 11 import urllib |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
12 import logging |
61 | 13 import math |
46 | 14 import urlparse |
526 | 15 import json |
231 | 16 |
541 | 17 from Products.MetaDataProvider import MetaDataFolder |
18 | |
623 | 19 from SrvTxtUtils import getInt, utf8ify, getText, getHttpData, refreshingImageFileIndexHtml, sslifyUrl |
52 | 20 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
21 |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
22 def getMDText(node): |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
23 """returns the @text content from the MetaDataProvider metadata node""" |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
24 if isinstance(node, dict): |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
25 return node.get('@text', None) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
26 |
617 | 27 if isinstance(node,list): #more than one text file if there is an attribute don't choose it |
28 for nodeInList in node: | |
29 attr = nodeInList.get("@attr",None) | |
30 if attr is None: | |
31 return node.get('@text',None) | |
32 return None | |
33 | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
34 return node |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
35 |
464 | 36 def getParentPath(path, cnt=1): |
37 """returns pathname shortened by cnt""" | |
38 # make sure path doesn't end with / | |
39 path = path.rstrip('/') | |
40 # split by /, shorten, and reassemble | |
41 return '/'.join(path.split('/')[0:-cnt]) | |
42 | |
589 | 43 def getPnForPf(docinfo, pf, default=0): |
44 """returns image number for image file name or default""" | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
45 if 'imgFileNames' in docinfo: |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
46 pn = docinfo['imgFileNames'].get(pf, None) |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
47 if pn is None: |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
48 # try to cut extension |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
49 xi = pf.rfind('.') |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
50 if xi > 0: |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
51 pf = pf[:xi] |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
52 # try again, else return 0 |
589 | 53 pn = docinfo['imgFileNames'].get(pf, default) |
54 else: | |
55 # no extension | |
56 pn = default | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
57 |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
58 return pn |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
59 |
589 | 60 return default |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
61 |
591 | 62 def getPfForPn(docinfo, pn, default=None): |
63 """returns image file name for image number or default""" | |
64 if 'imgFileIndexes' in docinfo: | |
65 pn = docinfo['imgFileIndexes'].get(pn, default) | |
66 return pn | |
67 | |
68 return default | |
69 | |
585 | 70 |
22 | 71 ## |
72 ## documentViewer class | |
73 ## | |
74 class documentViewer(Folder): | |
0 | 75 """document viewer""" |
76 meta_type="Document viewer" | |
77 | |
78 security=ClassSecurityInfo() | |
22 | 79 manage_options=Folder.manage_options+( |
507 | 80 {'label':'Configuration','action':'changeDocumentViewerForm'}, |
0 | 81 ) |
463 | 82 |
83 metadataService = None | |
84 """MetaDataFolder instance""" | |
525 | 85 |
0 | 86 |
525 | 87 # |
22 | 88 # templates and forms |
525 | 89 # |
90 # viewMode templates | |
594 | 91 viewer_text = PageTemplateFile('zpt/viewer/viewer_text', globals()) |
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
92 viewer_hocr = PageTemplateFile('zpt/viewer/viewer_hocr', globals()) |
594 | 93 viewer_xml = PageTemplateFile('zpt/viewer/viewer_xml', globals()) |
94 viewer_image = PageTemplateFile('zpt/viewer/viewer_image', globals()) | |
95 viewer_index = PageTemplateFile('zpt/viewer/viewer_index', globals()) | |
96 viewer_thumbs = PageTemplateFile('zpt/viewer/viewer_thumbs', globals()) | |
97 viewer_indexonly = PageTemplateFile('zpt/viewer/viewer_indexonly', globals()) | |
546 | 98 # available layer types (annotator not default) |
99 builtinLayers = {'text': ['dict','search','gis'], | |
590 | 100 'xml': None, 'image': None, 'index': ['extended']} |
526 | 101 availableLayers = builtinLayers; |
525 | 102 # layer templates |
594 | 103 layer_text_dict = PageTemplateFile('zpt/viewer/layer_text_dict', globals()) |
104 layer_text_search = PageTemplateFile('zpt/viewer/layer_text_search', globals()) | |
105 layer_text_annotator = PageTemplateFile('zpt/viewer/layer_text_annotator', globals()) | |
106 layer_text_gis = PageTemplateFile('zpt/viewer/layer_text_gis', globals()) | |
107 layer_text_pundit = PageTemplateFile('zpt/viewer/layer_text_pundit', globals()) | |
108 layer_image_annotator = PageTemplateFile('zpt/viewer/layer_image_annotator', globals()) | |
109 layer_image_search = PageTemplateFile('zpt/viewer/layer_image_search', globals()) | |
110 layer_index_extended = PageTemplateFile('zpt/viewer/layer_index_extended', globals()) | |
525 | 111 # toc templates |
594 | 112 toc_thumbs = PageTemplateFile('zpt/viewer/toc_thumbs', globals()) |
113 toc_text = PageTemplateFile('zpt/viewer/toc_text', globals()) | |
114 toc_figures = PageTemplateFile('zpt/viewer/toc_figures', globals()) | |
115 toc_concordance = PageTemplateFile('zpt/viewer/toc_concordance', globals()) | |
609 | 116 toc_notes = PageTemplateFile('zpt/viewer/toc_notes', globals()) |
594 | 117 toc_handwritten = PageTemplateFile('zpt/viewer/toc_handwritten', globals()) |
118 toc_none = PageTemplateFile('zpt/viewer/toc_none', globals()) | |
525 | 119 # other templates |
594 | 120 common_template = PageTemplateFile('zpt/viewer/common_template', globals()) |
121 info_xml = PageTemplateFile('zpt/viewer/info_xml', globals()) | |
487 | 122 docuviewer_css = ImageFile('css/docuviewer.css',globals()) |
532 | 123 # make docuviewer_css refreshable for development |
490
6f116b86a226
more new template stuff. moved ImageFile index method to SrvTxtUtils
casties
parents:
489
diff
changeset
|
124 docuviewer_css.index_html = refreshingImageFileIndexHtml |
535
510bae2b593b
more fixes, e.g. IE support. first version of index page.
casties
parents:
532
diff
changeset
|
125 docuviewer_ie_css = ImageFile('css/docuviewer_ie.css',globals()) |
510bae2b593b
more fixes, e.g. IE support. first version of index page.
casties
parents:
532
diff
changeset
|
126 # make docuviewer_ie_css refreshable for development |
585 | 127 #docuviewer_ie_css.index_html = refreshingImageFileIndexHtml |
501 | 128 jquery_js = ImageFile('js/jquery.js',globals()) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
129 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
130 |
95 | 131 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
0 | 132 """init document viewer""" |
133 self.id=id | |
134 self.title=title | |
25 | 135 self.thumbcols = thumbcols |
136 self.thumbrows = thumbrows | |
32 | 137 # authgroups is list of authorized groups (delimited by ,) |
138 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
139 # create template folder so we can always use template.something |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
140 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
141 templateFolder = Folder('template') |
498 | 142 self['template'] = templateFolder # Zope-2.12 style |
143 #self._setObject('template',templateFolder) # old style | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
144 try: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
145 import MpdlXmlTextServer |
132 | 146 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
498 | 147 templateFolder['fulltextclient'] = textServer |
148 #templateFolder._setObject('fulltextclient',textServer) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
149 except Exception, e: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
150 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
463 | 151 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
152 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
153 from Products.zogiLib.zogiLib import zogiLib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
154 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
498 | 155 templateFolder['zogilib'] = zogilib |
156 #templateFolder._setObject('zogilib',zogilib) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
157 except Exception, e: |
607 | 158 logging.error("Unable to create zogiLib for 'zogilib': "+str(e)) |
463 | 159 |
160 try: | |
161 # assume MetaDataFolder instance is called metadata | |
162 self.metadataService = getattr(self, 'metadata') | |
163 except Exception, e: | |
164 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
165 | |
477 | 166 if digilibBaseUrl is not None: |
167 self.digilibBaseUrl = digilibBaseUrl | |
566 | 168 self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
169 self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' | |
477 | 170 |
623 | 171 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
172 # proxy text server methods to fulltextclient |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
173 def getTextPage(self, **args): |
498 | 174 """returns full text content of page""" |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
175 return self.template.fulltextclient.getTextPage(**args) |
22 | 176 |
508 | 177 def getSearchResults(self, **args): |
178 """loads list of search results and stores XML in docinfo""" | |
179 return self.template.fulltextclient.getSearchResults(**args) | |
180 | |
181 def getResultsPage(self, **args): | |
182 """returns one page of the search results""" | |
183 return self.template.fulltextclient.getResultsPage(**args) | |
184 | |
516 | 185 def getTextInfo(self, **args): |
186 """returns document info from the text server""" | |
187 return self.template.fulltextclient.getTextInfo(**args) | |
188 | |
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
189 def getToc(self, **args): |
508 | 190 """loads table of contents and stores XML in docinfo""" |
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
191 return self.template.fulltextclient.getToc(**args) |
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
192 |
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
193 def getTocPage(self, **args): |
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
194 """returns one page of the table of contents""" |
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
195 return self.template.fulltextclient.getTocPage(**args) |
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
196 |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
197 def getRepositoryType(self, **args): |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
198 """get repository type""" |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
199 return self.template.fulltextclient.getRepositoryType(**args) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
200 |
559 | 201 def getTextDownloadUrl(self, **args): |
610 | 202 """get URL to download the full text""" |
559 | 203 return self.template.fulltextclient.getTextDownloadUrl(**args) |
204 | |
506 | 205 def getPlacesOnPage(self, **args): |
206 """get list of gis places on one page""" | |
207 return self.template.fulltextclient.getPlacesOnPage(**args) | |
307 | 208 |
548 | 209 # Thumb list for CoolIris Plugin |
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
210 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
68 | 211 security.declareProtected('View','thumbs_rss') |
212 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
213 ''' | |
214 view it | |
215 @param mode: defines how to access the document behind url | |
216 @param url: url which contains display information | |
590 | 217 @param viewMode: image: display images, text: display text, default is auto (try text, else image) |
68 | 218 |
219 ''' | |
220 | |
221 if not hasattr(self, 'template'): | |
590 | 222 # this won't work |
223 logging.error("template folder missing!") | |
224 return "ERROR: template folder missing!" | |
225 | |
68 | 226 if not self.digilibBaseUrl: |
623 | 227 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
68 | 228 |
229 docinfo = self.getDocinfo(mode=mode,url=url) | |
338 | 230 #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
231 pageinfo = self.getPageinfo(start=start,pn=pn, docinfo=docinfo) |
331 | 232 ''' ZDES ''' |
68 | 233 pt = getattr(self.template, 'thumbs_main_rss') |
234 | |
235 if viewMode=="auto": # automodus gewaehlt | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
236 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
68 | 237 viewMode="text" |
238 else: | |
590 | 239 viewMode="image" |
68 | 240 |
241 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
465 | 242 |
68 | 243 |
22 | 244 security.declareProtected('View','index_html') |
589 | 245 def index_html(self, url, mode="texttool", viewMode="auto", viewLayer=None, tocMode=None, start=None, pn=None, pf=None): |
464 | 246 """ |
543 | 247 show page |
471 | 248 @param url: url which contains display information |
57 | 249 @param mode: defines how to access the document behind url |
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
250 @param viewMode: 'image': display images, 'text': display text, 'xml': display xml, default is 'auto', 'hocr' : hocr format |
543 | 251 @param viewLayer: sub-type of viewMode, e.g. layer 'dict' for viewMode='text' |
99 | 252 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
464 | 253 """ |
0 | 254 |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
255 logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewLayer=%s start=%s pn=%s pf=%s"%(mode,url,viewMode,viewLayer,start,pn,pf)) |
22 | 256 |
257 if not hasattr(self, 'template'): | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
258 # this won't work |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
259 logging.error("template folder missing!") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
260 return "ERROR: template folder missing!" |
617 | 261 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
262 if not getattr(self, 'digilibBaseUrl', None): |
132 | 263 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
22 | 264 |
548 | 265 # mode=filepath should not have toc-thumbs |
266 if tocMode is None: | |
267 if mode == "filepath": | |
268 tocMode = "none" | |
269 else: | |
270 tocMode = "thumbs" | |
271 | |
543 | 272 # docinfo: information about document (cached) |
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
273 docinfo = self.getDocinfo(mode=mode,url=url,tocMode=tocMode) |
97 | 274 |
543 | 275 # userinfo: user settings (cached) |
276 userinfo = self.getUserinfo() | |
277 | |
471 | 278 # auto viewMode: text if there is a text else images |
455 | 279 if viewMode=="auto": |
530 | 280 if docinfo.get('textURLPath', None): |
281 # docinfo.get('textURL', None) not implemented yet | |
471 | 282 viewMode = "text" |
543 | 283 if viewLayer is None and 'viewLayer' not in userinfo: |
284 # use layer dict as default | |
508 | 285 viewLayer = "dict" |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
286 else: |
590 | 287 viewMode = "image" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
288 |
474 | 289 elif viewMode == "text_dict": |
290 # legacy fix | |
291 viewMode = "text" | |
503 | 292 viewLayer = "dict" |
474 | 293 |
590 | 294 elif viewMode == 'images': |
295 # legacy fix | |
296 viewMode = 'image' | |
297 self.REQUEST['viewMode'] = 'image' | |
298 | |
543 | 299 # safe viewLayer in userinfo |
300 userinfo['viewLayer'] = viewLayer | |
548 | 301 |
543 | 302 # pageinfo: information about page (not cached) |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
303 pageinfo = self.getPageinfo(start=start, pn=pn, pf=pf, docinfo=docinfo, userinfo=userinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode) |
469 | 304 |
475 | 305 # get template /template/viewer_$viewMode |
306 pt = getattr(self.template, 'viewer_%s'%viewMode, None) | |
307 if pt is None: | |
308 logging.error("No template for viewMode=%s!"%viewMode) | |
309 # TODO: error page? | |
310 return "No template for viewMode=%s!"%viewMode | |
311 | |
455 | 312 # and execute with parameters |
471 | 313 return pt(docinfo=docinfo, pageinfo=pageinfo) |
0 | 314 |
525 | 315 def getAvailableLayers(self): |
316 """returns dict with list of available layers per viewMode""" | |
317 return self.availableLayers | |
318 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
319 def findDigilibUrl(self): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
320 """try to get the digilib URL from zogilib""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
321 url = self.template.zogilib.getDLBaseUrl() |
624 | 322 return url |
480 | 323 |
324 def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None): | |
325 """returns URL to digilib Scaler with params""" | |
326 url = None | |
327 if docinfo is not None: | |
328 url = docinfo.get('imageURL', None) | |
329 | |
330 if url is None: | |
566 | 331 url = self.digilibScalerUrl |
480 | 332 if fn is None and docinfo is not None: |
333 fn = docinfo.get('imagePath','') | |
334 | |
335 url += "fn=%s"%fn | |
336 | |
337 if pn: | |
338 url += "&pn=%s"%pn | |
339 | |
340 url += "&dw=%s&dh=%s"%(dw,dh) | |
624 | 341 return sslifyUrl(url, self, force=True) |
126 | 342 |
343 def getDocumentViewerURL(self): | |
344 """returns the URL of this instance""" | |
345 return self.absolute_url() | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
346 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
347 def getStyle(self, idx, selected, style=""): |
480 | 348 """returns a string with the given style and append 'sel' if idx == selected.""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
349 #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
350 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
351 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
352 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
353 return style |
74 | 354 |
478 | 355 def getParams(self, param=None, val=None, params=None, duplicates=None): |
469 | 356 """returns dict with URL parameters. |
357 | |
358 Takes URL parameters and additionally param=val or dict params. | |
359 Deletes key if value is None.""" | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
360 # copy existing request params |
469 | 361 newParams=self.REQUEST.form.copy() |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
362 # change single param |
25 | 363 if param is not None: |
31 | 364 if val is None: |
469 | 365 if newParams.has_key(param): |
366 del newParams[param] | |
25 | 367 else: |
469 | 368 newParams[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
369 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
370 # change more params |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
371 if params is not None: |
478 | 372 for (k, v) in params.items(): |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
373 if v is None: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
374 # val=None removes param |
469 | 375 if newParams.has_key(k): |
376 del newParams[k] | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
377 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
378 else: |
469 | 379 newParams[k] = v |
478 | 380 |
381 if duplicates: | |
382 # eliminate lists (coming from duplicate keys) | |
383 for (k,v) in newParams.items(): | |
384 if isinstance(v, list): | |
385 if duplicates == 'comma': | |
386 # make comma-separated list of non-empty entries | |
387 newParams[k] = ','.join([t for t in v if t]) | |
388 elif duplicates == 'first': | |
389 # take first non-empty entry | |
390 newParams[k] = [t for t in v if t][0] | |
391 | |
469 | 392 return newParams |
393 | |
478 | 394 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
469 | 395 """returns URL to documentviewer with parameter param set to val or from dict params""" |
478 | 396 urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates) |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
397 # quote values and assemble into query string (not escaping '/') |
514 | 398 ps = paramSep.join(["%s=%s"%(k, urllib.quote_plus(utf8ify(v), '/')) for (k, v) in urlParams.items()]) |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
399 if baseUrl is None: |
469 | 400 baseUrl = self.getDocumentViewerURL() |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
401 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
402 url = "%s?%s"%(baseUrl, ps) |
25 | 403 return url |
404 | |
478 | 405 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
68 | 406 """link to documentviewer with parameter param set to val""" |
478 | 407 return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&', duplicates=duplicates) |
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
408 |
526 | 409 |
410 def setAvailableLayers(self, newLayerString=None): | |
411 """sets availableLayers to newLayerString or tries to autodetect available layers. | |
412 assumes layer templates have the form layer_{m}_{l} for layer l in mode m. | |
413 newLayerString is parsed as JSON.""" | |
414 if newLayerString is not None: | |
415 try: | |
416 layers = json.loads(newLayerString) | |
590 | 417 if 'text' in layers and 'image' in layers: |
526 | 418 self.availableLayers = layers |
419 return | |
420 except: | |
421 pass | |
422 | |
423 logging.error("invalid layers=%s! autodetecting..."%repr(newLayerString)) | |
424 | |
425 # start with builtin layers | |
426 self.availableLayers = self.builtinLayers.copy() | |
427 # add layers from templates | |
428 for t in self.template: | |
429 if t.startswith('layer_'): | |
430 try: | |
431 (x, m, l) = t.split('_', 3) | |
432 if m not in self.availableLayers: | |
433 # mode m doesn't exist -> new list | |
434 self.availableLayers[m] = [l] | |
435 | |
436 else: | |
437 # m exists -> append | |
438 if l not in self.availableLayers[m]: | |
439 self.availableLayers[m].append() | |
440 | |
441 except: | |
442 pass | |
443 | |
444 def getAvailableLayersJson(self): | |
445 """returns available layers as JSON string.""" | |
446 return json.dumps(self.availableLayers) | |
447 | |
469 | 448 |
57 | 449 def getInfo_xml(self,url,mode): |
450 """returns info about the document as XML""" | |
451 if not self.digilibBaseUrl: | |
514 | 452 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
57 | 453 |
454 docinfo = self.getDocinfo(mode=mode,url=url) | |
455 pt = getattr(self.template, 'info_xml') | |
456 return pt(docinfo=docinfo) | |
457 | |
528 | 458 def getAuthenticatedUser(self, anon=None): |
459 """returns the authenticated user object or None. (ignores Zopes anonymous user)""" | |
460 user = getSecurityManager().getUser() | |
461 if user is not None and user.getUserName() != "Anonymous User": | |
462 return user | |
463 else: | |
464 return anon | |
465 | |
35 | 466 def isAccessible(self, docinfo): |
32 | 467 """returns if access to the resource is granted""" |
468 access = docinfo.get('accessType', None) | |
167 | 469 logging.debug("documentViewer (accessOK) access type %s"%access) |
465 | 470 if access == 'free': |
167 | 471 logging.debug("documentViewer (accessOK) access is free") |
32 | 472 return True |
465 | 473 |
45 | 474 elif access is None or access in self.authgroups: |
35 | 475 # only local access -- only logged in users |
528 | 476 user = self.getAuthenticatedUser() |
167 | 477 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
528 | 478 return (user is not None) |
32 | 479 |
167 | 480 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
32 | 481 return False |
464 | 482 |
543 | 483 def getUserinfo(self): |
484 """returns userinfo object""" | |
485 logging.debug("getUserinfo") | |
486 userinfo = {} | |
487 # look for cached userinfo in session | |
488 if self.REQUEST.SESSION.has_key('userinfo'): | |
489 userinfo = self.REQUEST.SESSION['userinfo'] | |
490 # check if its still current? | |
491 else: | |
492 # store in session | |
493 self.REQUEST.SESSION['userinfo'] = userinfo | |
494 | |
495 return userinfo | |
496 | |
612 | 497 def getDocinfoJSON(self, mode, url, tocMode=None): |
498 """returns docinfo depending on mode""" | |
499 import json | |
500 | |
501 dc = self.getDocinfo( mode, url, tocMode) | |
502 | |
503 return json.dumps(dc) | |
504 | |
505 | |
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
506 def getDocinfo(self, mode, url, tocMode=None): |
464 | 507 """returns docinfo depending on mode""" |
508 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) | |
509 # look for cached docinfo in session | |
510 if self.REQUEST.SESSION.has_key('docinfo'): | |
511 docinfo = self.REQUEST.SESSION['docinfo'] | |
512 # check if its still current | |
513 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: | |
514 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
515 return docinfo | |
516 | |
517 # new docinfo | |
518 docinfo = {'mode': mode, 'url': url} | |
519 # add self url | |
520 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
625
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
521 docinfo['digilibBaseUrl'] = sslifyUrl(self.digilibBaseUrl, self, force=True) |
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
522 docinfo['digilibScalerUrl'] = sslifyUrl(self.digilibScalerUrl, self, force=True) |
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
523 docinfo['digilibViewerUrl'] = sslifyUrl(self.digilibViewerUrl, self, force=True) |
464 | 524 # get index.meta DOM |
525 docUrl = None | |
526 metaDom = None | |
527 if mode=="texttool": | |
528 # url points to document dir or index.meta | |
529 metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
530 if metaDom is None: | |
531 raise IOError("Unable to find index.meta for mode=texttool!") | |
580
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
532 |
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
533 docUrl = url.replace('/index.meta', '') |
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
534 if url.startswith('/mpiwg/online/'): |
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
535 docUrl = url.replace('/mpiwg/online/', '', 1) |
464 | 536 |
537 elif mode=="imagepath": | |
538 # url points to folder with images, index.meta optional | |
539 # asssume index.meta in parent dir | |
540 docUrl = getParentPath(url) | |
541 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
599 | 542 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
543 |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
544 elif mode=="hocr": |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
545 # url points to folder with images, index.meta optional |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
546 # asssume index.meta in parent dir |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
547 docUrl = getParentPath(url) |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
548 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
549 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
550 docinfo['textURLPath'] = url.replace('/mpiwg/online', '', 1) |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
551 if docinfo.get("creator", None) is None: |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
552 docinfo['creator'] = "" |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
553 |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
554 if docinfo.get("title", None) is None: |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
555 docinfo['title'] = "" |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
556 |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
557 if docinfo.get("documentPath", None) is None: |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
558 docinfo['documentPath'] = url.replace('/mpiwg/online', '', 1) |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
559 docinfo['documentPath'] = url.replace('/pages', '', 1) |
464 | 560 |
561 elif mode=="filepath": | |
562 # url points to image file, index.meta optional | |
566 | 563 docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, url) |
548 | 564 docinfo['numPages'] = 1 |
464 | 565 # asssume index.meta is two path segments up |
566 docUrl = getParentPath(url, 2) | |
567 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
568 | |
569 else: | |
570 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
571 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
572 | |
573 docinfo['documentUrl'] = docUrl | |
574 # process index.meta contents | |
473 | 575 if metaDom is not None and metaDom.tag == 'resource': |
464 | 576 # document directory name and path |
608 | 577 resource = self.metadataService.getResourceData(dom=metaDom, recursive=1) |
464 | 578 if resource: |
579 docinfo = self.getDocinfoFromResource(docinfo, resource) | |
580 | |
581 # texttool info | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
582 texttool = self.metadataService.getTexttoolData(dom=metaDom, recursive=1, all=True) |
464 | 583 if texttool: |
584 docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
568 | 585 # document info from full text server |
516 | 586 if docinfo.get('textURLPath', None): |
565 | 587 docinfo = self.getTextInfo(mode=None, docinfo=docinfo) |
568 | 588 # include list of pages TODO: do we need this always? |
589 docinfo = self.getTextInfo(mode='pages', docinfo=docinfo) | |
464 | 590 |
591 # bib info | |
592 bib = self.metadataService.getBibData(dom=metaDom) | |
593 if bib: | |
548 | 594 # save extended version as 'bibx' TODO: ugly |
541 | 595 bibx = self.metadataService.getBibData(dom=metaDom, all=True, recursive=1) |
596 if len(bibx) == 1: | |
597 # unwrap list if possible | |
598 bibx = bibx[0] | |
599 | |
600 docinfo['bibx'] = bibx | |
601 docinfo = self.getDocinfoFromBib(docinfo, bib, bibx) | |
465 | 602 else: |
603 # no bib - try info.xml | |
604 docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) | |
464 | 605 |
606 # auth info | |
607 access = self.metadataService.getAccessData(dom=metaDom) | |
608 if access: | |
609 docinfo = self.getDocinfoFromAccess(docinfo, access) | |
610 | |
466 | 611 # attribution info |
612 attribution = self.metadataService.getAttributionData(dom=metaDom) | |
613 if attribution: | |
614 logging.debug("getDocinfo: attribution=%s"%repr(attribution)) | |
615 docinfo['attribution'] = attribution | |
616 | |
617 # copyright info | |
618 copyright = self.metadataService.getCopyrightData(dom=metaDom) | |
619 if copyright: | |
620 logging.debug("getDocinfo: copyright=%s"%repr(copyright)) | |
621 docinfo['copyright'] = copyright | |
538 | 622 |
623 # DRI (permanent ID) | |
581 | 624 dri = self.metadataService.getDRI(dom=metaDom, type='mpiwg') |
538 | 625 if dri: |
626 docinfo['DRI'] = dri | |
466 | 627 |
578 | 628 # (presentation) context |
629 ctx = self.metadataService.getContextData(dom=metaDom, all=True) | |
630 if ctx: | |
631 logging.debug("getcontext: ctx=%s"%repr(ctx)) | |
632 docinfo['presentationContext'] = ctx | |
633 | |
464 | 634 # image path |
635 if mode != 'texttool': | |
532 | 636 # override image path from texttool with url parameter TODO: how about mode=auto? |
599 | 637 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
464 | 638 |
548 | 639 # check numPages |
640 if docinfo.get('numPages', 0) == 0: | |
641 # number of images from digilib | |
642 if docinfo.get('imagePath', None): | |
599 | 643 imgpath = docinfo['imagePath'].replace('/mpiwg/online', '', 1) |
580
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
644 logging.debug("imgpath=%s"%imgpath) |
625
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
645 docinfo['imageURL'] = sslifyUrl("%s?fn=%s"%(self.digilibScalerUrl, imgpath), self, force=True) |
562 | 646 docinfo = self.getDocinfoFromDigilib(docinfo, imgpath) |
548 | 647 else: |
648 # imagePath still missing? try "./pageimg" | |
649 imgPath = os.path.join(docUrl, 'pageimg') | |
650 docinfo = self.getDocinfoFromDigilib(docinfo, imgPath) | |
651 if docinfo.get('numPages', 0) > 0: | |
652 # there are pages | |
653 docinfo['imagePath'] = imgPath | |
625
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
654 docinfo['imageURL'] = sslifyUrl("%s?fn=%s"%(self.digilibScalerUrl, docinfo['imagePath']), self, force=True) |
464 | 655 |
516 | 656 # check numPages |
657 if docinfo.get('numPages', 0) == 0: | |
658 if docinfo.get('numTextPages', 0) > 0: | |
659 # replace with numTextPages (text-only?) | |
660 docinfo['numPages'] = docinfo['numTextPages'] | |
607 | 661 |
662 # min and max page no | |
663 docinfo['minPageNo'] = docinfo.get('minPageNo', 1) | |
664 docinfo['maxPageNo'] = docinfo.get('maxPageNo', docinfo['numPages']) | |
516 | 665 |
608 | 666 # part-of information |
667 partOfPath = docinfo.get('partOfPath', None) | |
668 if partOfPath is not None: | |
669 partOfDom = self.metadataService.getDomFromPathOrUrl(partOfPath) | |
670 if partOfDom is not None: | |
671 docinfo['partOfLabel'] = self.metadataService.getBibFormattedLabel(dom=partOfDom) | |
672 docinfo['partOfUrl'] = "%s?url=%s"%(self.getDocumentViewerURL(), partOfPath) | |
673 logging.debug("partOfLabel=%s partOfUrl=%s"%(docinfo['partOfLabel'],docinfo['partOfUrl'])) | |
674 | |
599 | 675 # normalize path |
676 if 'imagePath' in docinfo and not docinfo['imagePath'].startswith('/'): | |
677 docinfo['imagePath'] = '/' + docinfo['imagePath'] | |
678 | |
464 | 679 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
680 # store in session | |
681 self.REQUEST.SESSION['docinfo'] = docinfo | |
682 return docinfo | |
683 | |
516 | 684 |
464 | 685 def getDocinfoFromResource(self, docinfo, resource): |
686 """reads contents of resource element into docinfo""" | |
608 | 687 logging.debug("getDocinfoFromResource: resource=%s"%(repr(resource))) |
688 docName = getMDText(resource.get('name', None)) | |
464 | 689 docinfo['documentName'] = docName |
608 | 690 docPath = getMDText(resource.get('archive-path', None)) |
464 | 691 if docPath: |
692 # clean up document path | |
693 if docPath[0] != '/': | |
694 docPath = '/' + docPath | |
695 | |
696 if docName and (not docPath.endswith(docName)): | |
697 docPath += "/" + docName | |
698 | |
699 else: | |
700 # use docUrl as docPath | |
701 docUrl = docinfo['documentURL'] | |
702 if not docUrl.startswith('http:'): | |
703 docPath = docUrl | |
608 | 704 |
465 | 705 if docPath: |
706 # fix URLs starting with /mpiwg/online | |
707 docPath = docPath.replace('/mpiwg/online', '', 1) | |
708 | |
464 | 709 docinfo['documentPath'] = docPath |
608 | 710 |
711 # is this part-of? | |
712 partOf = resource.get('is-part-of', None) | |
713 if partOf is not None: | |
714 partOf = getMDText(partOf.get('archive-path', None)) | |
715 if partOf is not None: | |
716 docinfo['partOfPath'] = partOf.strip() | |
717 | |
464 | 718 return docinfo |
719 | |
720 def getDocinfoFromTexttool(self, docinfo, texttool): | |
721 """reads contents of texttool element into docinfo""" | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
722 logging.debug("texttool=%s"%repr(texttool)) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
723 # unpack list if necessary |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
724 if isinstance(texttool, list): |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
725 texttool = texttool[0] |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
726 |
464 | 727 # image dir |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
728 imageDir = getMDText(texttool.get('image', None)) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
729 docPath = getMDText(docinfo.get('documentPath', None)) |
607 | 730 if imageDir: |
731 if imageDir.startswith('/'): | |
732 # absolute path | |
733 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
734 docinfo['imagePath'] = imageDir | |
735 | |
736 elif docPath: | |
737 # relative path | |
738 imageDir = os.path.join(docPath, imageDir) | |
739 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
740 docinfo['imagePath'] = imageDir | |
741 | |
742 # start and end page (for subdocuments of other documents) | |
743 imgStartNo = getMDText(texttool.get('image-start-no', None)) | |
744 minPageNo = getInt(imgStartNo, 1) | |
745 docinfo['minPageNo'] = minPageNo | |
746 | |
747 imgEndNo = getMDText(texttool.get('image-end-no', None)) | |
748 if imgEndNo: | |
749 docinfo['maxPageNo'] = getInt(imgEndNo) | |
464 | 750 |
751 # old style text URL | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
752 textUrl = getMDText(texttool.get('text', None)) |
617 | 753 |
464 | 754 if textUrl and docPath: |
755 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
756 textUrl = os.path.join(docPath, textUrl) | |
757 | |
758 docinfo['textURL'] = textUrl | |
759 | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
760 # new style text-url-path (can be more than one with "repository" attribute) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
761 textUrlNode = texttool.get('text-url-path', None) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
762 if not isinstance(textUrlNode, list): |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
763 textUrlNode = [textUrlNode] |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
764 |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
765 for tun in textUrlNode: |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
766 textUrl = getMDText(tun) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
767 if textUrl: |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
768 textUrlAtts = tun.get('@attr') |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
769 if (textUrlAtts and 'repository' in textUrlAtts): |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
770 textRepo = textUrlAtts['repository'] |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
771 # use matching repository |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
772 if self.getRepositoryType() == textRepo: |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
773 docinfo['textURLPath'] = textUrl |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
774 docinfo['textURLRepository'] = textRepo |
564 | 775 break |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
776 |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
777 else: |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
778 # no repo attribute - use always |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
779 docinfo['textURLPath'] = textUrl |
468 | 780 |
781 # page flow | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
782 docinfo['pageFlow'] = getMDText(texttool.get('page-flow', 'ltr')) |
468 | 783 |
784 # odd pages are left | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
785 docinfo['oddPage'] = getMDText(texttool.get('odd-scan-position', 'left')) |
468 | 786 |
541 | 787 # number of title page (default 1) |
607 | 788 docinfo['titlePage'] = getMDText(texttool.get('title-scan-no', minPageNo)) |
464 | 789 |
790 # old presentation stuff | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
791 presentation = getMDText(texttool.get('presentation', None)) |
464 | 792 if presentation and docPath: |
465 | 793 if presentation.startswith('http:'): |
794 docinfo['presentationUrl'] = presentation | |
795 else: | |
796 docinfo['presentationUrl'] = os.path.join(docPath, presentation) | |
602 | 797 |
798 # make sure we have at least fake DC data | |
799 if 'creator' not in docinfo: | |
800 docinfo['creator'] = '[no author found]' | |
801 | |
802 if 'title' not in docinfo: | |
803 docinfo['title'] = '[no title found]' | |
804 | |
805 if 'date' not in docinfo: | |
806 docinfo['date'] = '[no date found]' | |
468 | 807 |
464 | 808 return docinfo |
809 | |
541 | 810 def getDocinfoFromBib(self, docinfo, bib, bibx=None): |
464 | 811 """reads contents of bib element into docinfo""" |
465 | 812 logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
464 | 813 # put all raw bib fields in dict "bib" |
814 docinfo['bib'] = bib | |
815 bibtype = bib.get('@type', None) | |
816 docinfo['bibType'] = bibtype | |
817 # also store DC metadata for convenience | |
818 dc = self.metadataService.getDCMappedData(bib) | |
536
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
819 docinfo['creator'] = dc.get('creator','') |
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
820 docinfo['title'] = dc.get('title','') |
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
821 docinfo['date'] = dc.get('date','') |
464 | 822 return docinfo |
823 | |
824 def getDocinfoFromAccess(self, docinfo, acc): | |
825 """reads contents of access element into docinfo""" | |
826 #TODO: also read resource type | |
465 | 827 logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
464 | 828 try: |
465 | 829 acctype = acc['@attr']['type'] |
464 | 830 if acctype: |
831 access=acctype | |
832 if access in ['group', 'institution']: | |
833 access = acc['name'].lower() | |
834 | |
835 docinfo['accessType'] = access | |
836 | |
837 except: | |
838 pass | |
839 | |
840 return docinfo | |
841 | |
842 def getDocinfoFromDigilib(self, docinfo, path): | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
843 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?fn="+path |
464 | 844 # fetch data |
845 txt = getHttpData(infoUrl) | |
846 if not txt: | |
847 logging.error("Unable to get dir-info from %s"%(infoUrl)) | |
848 return docinfo | |
849 | |
850 dom = ET.fromstring(txt) | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
851 dir = dom |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
852 # save size |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
853 size = dir.findtext('size') |
464 | 854 logging.debug("getDocinfoFromDigilib: size=%s"%size) |
855 if size: | |
856 docinfo['numPages'] = int(size) | |
857 else: | |
858 docinfo['numPages'] = 0 | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
859 return docinfo |
464 | 860 |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
861 # save list of image names and numbers |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
862 imgNames = {} |
591 | 863 imgIndexes = {} |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
864 for f in dir: |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
865 fn = f.findtext('name') |
591 | 866 pn = getInt(f.findtext('index')) |
867 imgNames[fn] = pn | |
868 imgIndexes[pn] = fn | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
869 |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
870 docinfo['imgFileNames'] = imgNames |
591 | 871 docinfo['imgFileIndexes'] = imgIndexes |
464 | 872 return docinfo |
873 | |
874 | |
465 | 875 def getDocinfoFromPresentationInfoXml(self,docinfo): |
876 """gets DC-like bibliographical information from the presentation entry in texttools""" | |
877 url = docinfo.get('presentationUrl', None) | |
878 if not url: | |
879 logging.error("getDocinfoFromPresentation: no URL!") | |
880 return docinfo | |
881 | |
882 dom = None | |
883 metaUrl = None | |
884 if url.startswith("http://"): | |
885 # real URL | |
886 metaUrl = url | |
887 else: | |
888 # online path | |
889 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
890 metaUrl=server+url | |
891 | |
892 txt=getHttpData(metaUrl) | |
893 if txt is None: | |
894 logging.error("Unable to read info.xml from %s"%(url)) | |
895 return docinfo | |
896 | |
897 dom = ET.fromstring(txt) | |
898 docinfo['creator']=getText(dom.find(".//author")) | |
899 docinfo['title']=getText(dom.find(".//title")) | |
900 docinfo['date']=getText(dom.find(".//date")) | |
901 return docinfo | |
902 | |
903 | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
904 def getPageinfo(self, pn=None, pf=None, start=None, rows=None, cols=None, docinfo=None, userinfo=None, viewMode=None, viewLayer=None, tocMode=None): |
22 | 905 """returns pageinfo with the given parameters""" |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
906 logging.debug("getPageInfo(pn=%s, pf=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewLayer=%s, tocMode=%s)"%(pn,pf,start,rows,cols,viewMode,viewLayer,tocMode)) |
22 | 907 pageinfo = {} |
471 | 908 pageinfo['viewMode'] = viewMode |
508 | 909 # split viewLayer if necessary |
910 if isinstance(viewLayer,basestring): | |
911 viewLayer = viewLayer.split(',') | |
912 | |
913 if isinstance(viewLayer, list): | |
914 logging.debug("getPageinfo: viewLayer is list:%s"%viewLayer) | |
915 # save (unique) list in viewLayers | |
916 seen = set() | |
917 viewLayers = [l for l in viewLayer if l and l not in seen and not seen.add(l)] | |
918 pageinfo['viewLayers'] = viewLayers | |
919 # stringify viewLayer | |
920 viewLayer = ','.join(viewLayers) | |
921 else: | |
922 #create list | |
923 pageinfo['viewLayers'] = [viewLayer] | |
924 | |
503 | 925 pageinfo['viewLayer'] = viewLayer |
471 | 926 pageinfo['tocMode'] = tocMode |
927 | |
607 | 928 minPageNo = docinfo.get('minPageNo', 1) |
929 | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
930 # pf takes precedence over pn |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
931 if pf: |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
932 pageinfo['pf'] = pf |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
933 pn = getPnForPf(docinfo, pf) |
589 | 934 # replace pf in request params (used for creating new URLs) |
935 self.REQUEST.form.pop('pf', None) | |
936 self.REQUEST.form['pn'] = pn | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
937 else: |
607 | 938 pn = getInt(pn, minPageNo) |
591 | 939 pf = getPfForPn(docinfo, pn) |
940 pageinfo['pf'] = pf | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
941 |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
942 pageinfo['pn'] = pn |
25 | 943 rows = int(rows or self.thumbrows) |
944 pageinfo['rows'] = rows | |
945 cols = int(cols or self.thumbcols) | |
946 pageinfo['cols'] = cols | |
947 grpsize = cols * rows | |
948 pageinfo['groupsize'] = grpsize | |
607 | 949 # if start is empty use one around pn |
950 grouppn = math.ceil(float(pn)/float(grpsize))*grpsize-(grpsize-1) | |
951 # but not smaller than minPageNo | |
952 start = getInt(start, max(grouppn, minPageNo)) | |
22 | 953 pageinfo['start'] = start |
511 | 954 # get number of pages |
607 | 955 numPages = int(docinfo.get('numPages', 0)) |
956 if numPages == 0: | |
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
957 # try numTextPages |
607 | 958 numPages = docinfo.get('numTextPages', 0) |
959 if numPages != 0: | |
960 docinfo['numPages'] = numPages | |
961 | |
962 maxPageNo = docinfo.get('maxPageNo', numPages) | |
963 logging.debug("minPageNo=%s maxPageNo=%s start=%s numPages=%s"%(minPageNo,maxPageNo,start,numPages)) | |
964 np = maxPageNo | |
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
965 |
511 | 966 # cache table of contents |
967 pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) | |
469 | 968 pageinfo['numgroups'] = int(np / grpsize) |
969 if np % grpsize > 0: | |
970 pageinfo['numgroups'] += 1 | |
476 | 971 |
972 pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' | |
973 oddScanLeft = docinfo.get('oddPage', 'left') != 'right' | |
974 # add zeroth page for two columns | |
975 pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) | |
976 pageinfo['pageZero'] = pageZero | |
607 | 977 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=minPageNo, maxIdx=np) |
516 | 978 # more page parameters |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
979 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
516 | 980 if docinfo.get('pageNumbers'): |
981 # get original page numbers | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
982 pageNumber = docinfo['pageNumbers'].get(pn, None) |
516 | 983 if pageNumber is not None: |
984 pageinfo['pageNumberOrig'] = pageNumber['no'] | |
985 pageinfo['pageNumberOrigNorm'] = pageNumber['non'] | |
158 | 986 |
511 | 987 # cache search results |
988 query = self.REQUEST.get('query',None) | |
989 pageinfo['query'] = query | |
591 | 990 if query and viewMode == 'text': |
991 pageinfo['resultPageSize'] = getInt(self.REQUEST.get('resultPageSize', 10)) | |
511 | 992 queryType = self.REQUEST.get('queryType', 'fulltextMorph') |
993 pageinfo['queryType'] = queryType | |
994 pageinfo['resultStart'] = getInt(self.REQUEST.get('resultStart', '1')) | |
995 self.getSearchResults(mode=queryType, query=query, pageinfo=pageinfo, docinfo=docinfo) | |
996 | |
997 # highlighting | |
998 highlightQuery = self.REQUEST.get('highlightQuery', None) | |
999 if highlightQuery: | |
1000 pageinfo['highlightQuery'] = highlightQuery | |
1001 pageinfo['highlightElement'] = self.REQUEST.get('highlightElement', '') | |
1002 pageinfo['highlightElementPos'] = self.REQUEST.get('highlightElementPos', '') | |
460 | 1003 |
22 | 1004 return pageinfo |
460 | 1005 |
463 | 1006 |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1007 def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0): |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1008 """Return dict with array of page information for one screenfull of thumbnails. |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1009 |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1010 :param start: index of current page |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1011 :param rows: number of rows in one batch |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1012 :param cols: number of columns in one batch |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1013 :param pageFlowLtr: do indexes increase from left to right |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1014 :param pageZero: is there a zeroth non-visible page |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1015 :param minIdx: minimum index to use |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1016 :param maxIdx: maximum index to use |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1017 :returns: dict with |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1018 first: first page index |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1019 last: last page index |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1020 batches: list of all possible batches(dict: 'start': index, 'end': index) |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1021 pages: list for current batch of rows(list of cols(list of pages(dict: 'idx': index))) |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1022 nextStart: first index of next batch |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1023 prevStart: first index of previous batch |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1024 """ |
607 | 1025 logging.debug("getPageBatch start=%s minIdx=%s maxIdx=%s"%(start,minIdx,maxIdx)) |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1026 batch = {} |
480 | 1027 grpsize = rows * cols |
476 | 1028 if maxIdx == 0: |
480 | 1029 maxIdx = start + grpsize |
476 | 1030 |
607 | 1031 np = maxIdx - minIdx + 1 |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1032 if pageZero: |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1033 # correct number of pages for batching |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1034 np += 1 |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1035 |
607 | 1036 nb = int(math.ceil(np / float(grpsize))) |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1037 |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1038 # list of all batch start and end points |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1039 batches = [] |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1040 if pageZero: |
607 | 1041 ofs = minIdx - 1 |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1042 else: |
607 | 1043 ofs = minIdx |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1044 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1045 for i in range(nb): |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1046 s = i * grpsize + ofs |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1047 e = min((i + 1) * grpsize + ofs - 1, maxIdx) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1048 batches.append({'start':s, 'end':e}) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1049 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1050 batch['batches'] = batches |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1051 |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1052 # list of pages for current screen |
476 | 1053 pages = [] |
607 | 1054 if pageZero and start == minIdx: |
476 | 1055 # correct beginning |
607 | 1056 idx = minIdx - 1 |
476 | 1057 else: |
1058 idx = start | |
1059 | |
1060 for r in range(rows): | |
1061 row = [] | |
1062 for c in range(cols): | |
1063 if idx < minIdx or idx > maxIdx: | |
1064 page = {'idx':None} | |
1065 else: | |
1066 page = {'idx':idx} | |
1067 | |
1068 idx += 1 | |
1069 if pageFlowLtr: | |
1070 row.append(page) | |
1071 else: | |
1072 row.insert(0, page) | |
1073 | |
1074 pages.append(row) | |
1075 | |
607 | 1076 if start > minIdx: |
1077 batch['prevStart'] = max(start - grpsize, minIdx) | |
480 | 1078 else: |
1079 batch['prevStart'] = None | |
1080 | |
526 | 1081 if start + grpsize <= maxIdx: |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1082 if pageZero and start == minIdx: |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1083 # correct nextStart for pageZero |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1084 batch['nextStart'] = grpsize |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1085 else: |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1086 batch['nextStart'] = start + grpsize |
480 | 1087 else: |
1088 batch['nextStart'] = None | |
1089 | |
1090 batch['pages'] = pages | |
571 | 1091 batch['first'] = minIdx |
1092 batch['last'] = maxIdx | |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1093 logging.debug("batch: %s"%repr(batch)) |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1094 return batch |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1095 |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1096 |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1097 def getBatch(self, start=1, size=10, end=0, data=None, fullData=True): |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1098 """returns dict with information for one screenfull of data.""" |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1099 batch = {} |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1100 if end == 0: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1101 end = start + size |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1102 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1103 nb = int(math.ceil(end / float(size))) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1104 # list of all batch start and end points |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1105 batches = [] |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1106 for i in range(nb): |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1107 s = i * size + 1 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1108 e = min((i + 1) * size, end) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1109 batches.append({'start':s, 'end':e}) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1110 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1111 batch['batches'] = batches |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1112 # list of elements in this batch |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1113 this = [] |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1114 j = 0 |
526 | 1115 for i in range(start, min(start+size, end+1)): |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1116 if data: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1117 if fullData: |
526 | 1118 d = data.get(i, None) |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1119 else: |
526 | 1120 d = data.get(j, None) |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1121 j += 1 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1122 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1123 else: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1124 d = i+1 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1125 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1126 this.append(d) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1127 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1128 batch['this'] = this |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1129 if start > 1: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1130 batch['prevStart'] = max(start - size, 1) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1131 else: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1132 batch['prevStart'] = None |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1133 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1134 if start + size < end: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1135 batch['nextStart'] = start + size |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1136 else: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1137 batch['nextStart'] = None |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1138 |
571 | 1139 batch['first'] = start |
1140 batch['last'] = end | |
480 | 1141 return batch |
476 | 1142 |
1143 | |
546 | 1144 def getAnnotatorGroupsForUser(self, user, annotationServerUrl="http://tuxserve03.mpiwg-berlin.mpg.de/AnnotationManager"): |
1145 """returns list of groups {name:*, id:*} on the annotation server for the user""" | |
1146 groups = [] | |
623 | 1147 # add matching http(s) from our URL |
1148 annotationServerUrl = sslifyUrl(annotationServerUrl, self) | |
622
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1149 |
546 | 1150 groupsUrl = "%s/annotator/groups?user=%s"%(annotationServerUrl,user) |
1151 data = getHttpData(url=groupsUrl, noExceptions=True) | |
1152 if data: | |
1153 res = json.loads(data) | |
1154 rows = res.get('rows', None) | |
1155 if rows is None: | |
1156 return groups | |
1157 for r in rows: | |
1158 groups.append({'id': r.get('id', None), 'name': r.get('name', None), 'uri': r.get('uri', None)}) | |
1159 | |
1160 return groups | |
1161 | |
1162 | |
463 | 1163 security.declareProtected('View management screens','changeDocumentViewerForm') |
1164 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
22 | 1165 |
526 | 1166 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',availableLayers=None,RESPONSE=None): |
22 | 1167 """init document viewer""" |
1168 self.title=title | |
1169 self.digilibBaseUrl = digilibBaseUrl | |
566 | 1170 self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
1171 self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' | |
25 | 1172 self.thumbrows = thumbrows |
1173 self.thumbcols = thumbcols | |
32 | 1174 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
463 | 1175 try: |
1176 # assume MetaDataFolder instance is called metadata | |
1177 self.metadataService = getattr(self, 'metadata') | |
1178 except Exception, e: | |
1179 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
526 | 1180 |
1181 self.setAvailableLayers(availableLayers) | |
463 | 1182 |
22 | 1183 if RESPONSE is not None: |
1184 RESPONSE.redirect('manage_main') | |
623 | 1185 |
0 | 1186 |
1187 def manage_AddDocumentViewerForm(self): | |
1188 """add the viewer form""" | |
22 | 1189 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 1190 return pt() |
1191 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1192 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 1193 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1194 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 1195 self._setObject(id,newObj) |
1196 | |
1197 if RESPONSE is not None: | |
1198 RESPONSE.redirect('manage_main') |