Mercurial > hg > documentViewer
annotate documentViewer.py @ 629:e36bf3226fde
text image viewer eingecheckt
author | dwinter |
---|---|
date | Tue, 26 May 2015 10:58:27 +0200 |
parents | 7dafe8283312 |
children | 0c3aab828864 |
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()) | |
629 | 98 viewer_text_image = PageTemplateFile('zpt/viewer/viewer_text_image', globals()) |
546 | 99 # available layer types (annotator not default) |
100 builtinLayers = {'text': ['dict','search','gis'], | |
629 | 101 'xml': None, 'image': None, 'index': ['extended'],'text_image': ['dict'],} |
526 | 102 availableLayers = builtinLayers; |
525 | 103 # layer templates |
594 | 104 layer_text_dict = PageTemplateFile('zpt/viewer/layer_text_dict', globals()) |
629 | 105 layer_text_image_dict = PageTemplateFile('zpt/viewer/layer_text_image_dict', globals()) |
594 | 106 layer_text_search = PageTemplateFile('zpt/viewer/layer_text_search', globals()) |
107 layer_text_annotator = PageTemplateFile('zpt/viewer/layer_text_annotator', globals()) | |
108 layer_text_gis = PageTemplateFile('zpt/viewer/layer_text_gis', globals()) | |
109 layer_text_pundit = PageTemplateFile('zpt/viewer/layer_text_pundit', globals()) | |
110 layer_image_annotator = PageTemplateFile('zpt/viewer/layer_image_annotator', globals()) | |
111 layer_image_search = PageTemplateFile('zpt/viewer/layer_image_search', globals()) | |
112 layer_index_extended = PageTemplateFile('zpt/viewer/layer_index_extended', globals()) | |
525 | 113 # toc templates |
594 | 114 toc_thumbs = PageTemplateFile('zpt/viewer/toc_thumbs', globals()) |
115 toc_text = PageTemplateFile('zpt/viewer/toc_text', globals()) | |
116 toc_figures = PageTemplateFile('zpt/viewer/toc_figures', globals()) | |
117 toc_concordance = PageTemplateFile('zpt/viewer/toc_concordance', globals()) | |
609 | 118 toc_notes = PageTemplateFile('zpt/viewer/toc_notes', globals()) |
594 | 119 toc_handwritten = PageTemplateFile('zpt/viewer/toc_handwritten', globals()) |
120 toc_none = PageTemplateFile('zpt/viewer/toc_none', globals()) | |
525 | 121 # other templates |
594 | 122 common_template = PageTemplateFile('zpt/viewer/common_template', globals()) |
123 info_xml = PageTemplateFile('zpt/viewer/info_xml', globals()) | |
487 | 124 docuviewer_css = ImageFile('css/docuviewer.css',globals()) |
532 | 125 # make docuviewer_css refreshable for development |
490
6f116b86a226
more new template stuff. moved ImageFile index method to SrvTxtUtils
casties
parents:
489
diff
changeset
|
126 docuviewer_css.index_html = refreshingImageFileIndexHtml |
535
510bae2b593b
more fixes, e.g. IE support. first version of index page.
casties
parents:
532
diff
changeset
|
127 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
|
128 # make docuviewer_ie_css refreshable for development |
585 | 129 #docuviewer_ie_css.index_html = refreshingImageFileIndexHtml |
501 | 130 jquery_js = ImageFile('js/jquery.js',globals()) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
131 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
132 |
95 | 133 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
0 | 134 """init document viewer""" |
135 self.id=id | |
136 self.title=title | |
25 | 137 self.thumbcols = thumbcols |
138 self.thumbrows = thumbrows | |
32 | 139 # authgroups is list of authorized groups (delimited by ,) |
140 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
|
141 # 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
|
142 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
143 templateFolder = Folder('template') |
498 | 144 self['template'] = templateFolder # Zope-2.12 style |
145 #self._setObject('template',templateFolder) # old style | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
146 try: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
147 import MpdlXmlTextServer |
132 | 148 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
498 | 149 templateFolder['fulltextclient'] = textServer |
150 #templateFolder._setObject('fulltextclient',textServer) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
151 except Exception, e: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
152 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
463 | 153 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
154 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
155 from Products.zogiLib.zogiLib import zogiLib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
156 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
498 | 157 templateFolder['zogilib'] = zogilib |
158 #templateFolder._setObject('zogilib',zogilib) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
159 except Exception, e: |
607 | 160 logging.error("Unable to create zogiLib for 'zogilib': "+str(e)) |
463 | 161 |
162 try: | |
163 # assume MetaDataFolder instance is called metadata | |
164 self.metadataService = getattr(self, 'metadata') | |
165 except Exception, e: | |
166 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
167 | |
477 | 168 if digilibBaseUrl is not None: |
169 self.digilibBaseUrl = digilibBaseUrl | |
566 | 170 self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
171 self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' | |
477 | 172 |
623 | 173 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
174 # proxy text server methods to fulltextclient |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
175 def getTextPage(self, **args): |
498 | 176 """returns full text content of page""" |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
177 return self.template.fulltextclient.getTextPage(**args) |
22 | 178 |
508 | 179 def getSearchResults(self, **args): |
180 """loads list of search results and stores XML in docinfo""" | |
181 return self.template.fulltextclient.getSearchResults(**args) | |
182 | |
183 def getResultsPage(self, **args): | |
184 """returns one page of the search results""" | |
185 return self.template.fulltextclient.getResultsPage(**args) | |
186 | |
516 | 187 def getTextInfo(self, **args): |
188 """returns document info from the text server""" | |
189 return self.template.fulltextclient.getTextInfo(**args) | |
190 | |
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
191 def getToc(self, **args): |
508 | 192 """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
|
193 return self.template.fulltextclient.getToc(**args) |
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
194 |
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
195 def getTocPage(self, **args): |
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
196 """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
|
197 return self.template.fulltextclient.getTocPage(**args) |
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
198 |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
199 def getRepositoryType(self, **args): |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
200 """get repository type""" |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
201 return self.template.fulltextclient.getRepositoryType(**args) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
202 |
559 | 203 def getTextDownloadUrl(self, **args): |
610 | 204 """get URL to download the full text""" |
559 | 205 return self.template.fulltextclient.getTextDownloadUrl(**args) |
206 | |
506 | 207 def getPlacesOnPage(self, **args): |
208 """get list of gis places on one page""" | |
209 return self.template.fulltextclient.getPlacesOnPage(**args) | |
307 | 210 |
548 | 211 # Thumb list for CoolIris Plugin |
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
212 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
68 | 213 security.declareProtected('View','thumbs_rss') |
214 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
215 ''' | |
216 view it | |
217 @param mode: defines how to access the document behind url | |
218 @param url: url which contains display information | |
590 | 219 @param viewMode: image: display images, text: display text, default is auto (try text, else image) |
68 | 220 |
221 ''' | |
222 | |
223 if not hasattr(self, 'template'): | |
590 | 224 # this won't work |
225 logging.error("template folder missing!") | |
226 return "ERROR: template folder missing!" | |
227 | |
68 | 228 if not self.digilibBaseUrl: |
623 | 229 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
68 | 230 |
231 docinfo = self.getDocinfo(mode=mode,url=url) | |
338 | 232 #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
|
233 pageinfo = self.getPageinfo(start=start,pn=pn, docinfo=docinfo) |
331 | 234 ''' ZDES ''' |
68 | 235 pt = getattr(self.template, 'thumbs_main_rss') |
236 | |
237 if viewMode=="auto": # automodus gewaehlt | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
238 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
68 | 239 viewMode="text" |
240 else: | |
590 | 241 viewMode="image" |
68 | 242 |
243 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
465 | 244 |
68 | 245 |
22 | 246 security.declareProtected('View','index_html') |
589 | 247 def index_html(self, url, mode="texttool", viewMode="auto", viewLayer=None, tocMode=None, start=None, pn=None, pf=None): |
464 | 248 """ |
543 | 249 show page |
471 | 250 @param url: url which contains display information |
57 | 251 @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
|
252 @param viewMode: 'image': display images, 'text': display text, 'xml': display xml, default is 'auto', 'hocr' : hocr format |
543 | 253 @param viewLayer: sub-type of viewMode, e.g. layer 'dict' for viewMode='text' |
99 | 254 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
464 | 255 """ |
0 | 256 |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
257 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 | 258 |
259 if not hasattr(self, 'template'): | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
260 # this won't work |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
261 logging.error("template folder missing!") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
262 return "ERROR: template folder missing!" |
617 | 263 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
264 if not getattr(self, 'digilibBaseUrl', None): |
132 | 265 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
22 | 266 |
548 | 267 # mode=filepath should not have toc-thumbs |
268 if tocMode is None: | |
269 if mode == "filepath": | |
270 tocMode = "none" | |
271 else: | |
272 tocMode = "thumbs" | |
273 | |
543 | 274 # docinfo: information about document (cached) |
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
275 docinfo = self.getDocinfo(mode=mode,url=url,tocMode=tocMode) |
97 | 276 |
543 | 277 # userinfo: user settings (cached) |
278 userinfo = self.getUserinfo() | |
279 | |
471 | 280 # auto viewMode: text if there is a text else images |
455 | 281 if viewMode=="auto": |
530 | 282 if docinfo.get('textURLPath', None): |
283 # docinfo.get('textURL', None) not implemented yet | |
471 | 284 viewMode = "text" |
543 | 285 if viewLayer is None and 'viewLayer' not in userinfo: |
286 # use layer dict as default | |
508 | 287 viewLayer = "dict" |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
288 else: |
590 | 289 viewMode = "image" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
290 |
474 | 291 elif viewMode == "text_dict": |
292 # legacy fix | |
293 viewMode = "text" | |
503 | 294 viewLayer = "dict" |
474 | 295 |
590 | 296 elif viewMode == 'images': |
297 # legacy fix | |
298 viewMode = 'image' | |
299 self.REQUEST['viewMode'] = 'image' | |
300 | |
543 | 301 # safe viewLayer in userinfo |
302 userinfo['viewLayer'] = viewLayer | |
548 | 303 |
543 | 304 # pageinfo: information about page (not cached) |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
305 pageinfo = self.getPageinfo(start=start, pn=pn, pf=pf, docinfo=docinfo, userinfo=userinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode) |
469 | 306 |
475 | 307 # get template /template/viewer_$viewMode |
308 pt = getattr(self.template, 'viewer_%s'%viewMode, None) | |
309 if pt is None: | |
310 logging.error("No template for viewMode=%s!"%viewMode) | |
311 # TODO: error page? | |
312 return "No template for viewMode=%s!"%viewMode | |
313 | |
455 | 314 # and execute with parameters |
471 | 315 return pt(docinfo=docinfo, pageinfo=pageinfo) |
0 | 316 |
525 | 317 def getAvailableLayers(self): |
318 """returns dict with list of available layers per viewMode""" | |
319 return self.availableLayers | |
320 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
321 def findDigilibUrl(self): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
322 """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
|
323 url = self.template.zogilib.getDLBaseUrl() |
624 | 324 return url |
480 | 325 |
326 def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None): | |
327 """returns URL to digilib Scaler with params""" | |
328 url = None | |
329 if docinfo is not None: | |
330 url = docinfo.get('imageURL', None) | |
331 | |
332 if url is None: | |
566 | 333 url = self.digilibScalerUrl |
480 | 334 if fn is None and docinfo is not None: |
335 fn = docinfo.get('imagePath','') | |
336 | |
337 url += "fn=%s"%fn | |
338 | |
339 if pn: | |
340 url += "&pn=%s"%pn | |
341 | |
342 url += "&dw=%s&dh=%s"%(dw,dh) | |
624 | 343 return sslifyUrl(url, self, force=True) |
126 | 344 |
345 def getDocumentViewerURL(self): | |
346 """returns the URL of this instance""" | |
347 return self.absolute_url() | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
348 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
349 def getStyle(self, idx, selected, style=""): |
480 | 350 """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
|
351 #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
|
352 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
353 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
354 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
355 return style |
74 | 356 |
478 | 357 def getParams(self, param=None, val=None, params=None, duplicates=None): |
469 | 358 """returns dict with URL parameters. |
359 | |
360 Takes URL parameters and additionally param=val or dict params. | |
361 Deletes key if value is None.""" | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
362 # copy existing request params |
469 | 363 newParams=self.REQUEST.form.copy() |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
364 # change single param |
25 | 365 if param is not None: |
31 | 366 if val is None: |
469 | 367 if newParams.has_key(param): |
368 del newParams[param] | |
25 | 369 else: |
469 | 370 newParams[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
371 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
372 # change more params |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
373 if params is not None: |
478 | 374 for (k, v) in params.items(): |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
375 if v is None: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
376 # val=None removes param |
469 | 377 if newParams.has_key(k): |
378 del newParams[k] | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
379 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
380 else: |
469 | 381 newParams[k] = v |
478 | 382 |
383 if duplicates: | |
384 # eliminate lists (coming from duplicate keys) | |
385 for (k,v) in newParams.items(): | |
386 if isinstance(v, list): | |
387 if duplicates == 'comma': | |
388 # make comma-separated list of non-empty entries | |
389 newParams[k] = ','.join([t for t in v if t]) | |
390 elif duplicates == 'first': | |
391 # take first non-empty entry | |
392 newParams[k] = [t for t in v if t][0] | |
393 | |
469 | 394 return newParams |
395 | |
478 | 396 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
469 | 397 """returns URL to documentviewer with parameter param set to val or from dict params""" |
478 | 398 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
|
399 # quote values and assemble into query string (not escaping '/') |
514 | 400 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
|
401 if baseUrl is None: |
469 | 402 baseUrl = self.getDocumentViewerURL() |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
403 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
404 url = "%s?%s"%(baseUrl, ps) |
25 | 405 return url |
406 | |
478 | 407 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
68 | 408 """link to documentviewer with parameter param set to val""" |
478 | 409 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
|
410 |
526 | 411 |
412 def setAvailableLayers(self, newLayerString=None): | |
413 """sets availableLayers to newLayerString or tries to autodetect available layers. | |
414 assumes layer templates have the form layer_{m}_{l} for layer l in mode m. | |
415 newLayerString is parsed as JSON.""" | |
416 if newLayerString is not None: | |
417 try: | |
418 layers = json.loads(newLayerString) | |
590 | 419 if 'text' in layers and 'image' in layers: |
526 | 420 self.availableLayers = layers |
421 return | |
422 except: | |
423 pass | |
424 | |
425 logging.error("invalid layers=%s! autodetecting..."%repr(newLayerString)) | |
426 | |
427 # start with builtin layers | |
428 self.availableLayers = self.builtinLayers.copy() | |
429 # add layers from templates | |
430 for t in self.template: | |
431 if t.startswith('layer_'): | |
432 try: | |
433 (x, m, l) = t.split('_', 3) | |
434 if m not in self.availableLayers: | |
435 # mode m doesn't exist -> new list | |
436 self.availableLayers[m] = [l] | |
437 | |
438 else: | |
439 # m exists -> append | |
440 if l not in self.availableLayers[m]: | |
441 self.availableLayers[m].append() | |
442 | |
443 except: | |
444 pass | |
445 | |
446 def getAvailableLayersJson(self): | |
447 """returns available layers as JSON string.""" | |
448 return json.dumps(self.availableLayers) | |
449 | |
469 | 450 |
57 | 451 def getInfo_xml(self,url,mode): |
452 """returns info about the document as XML""" | |
453 if not self.digilibBaseUrl: | |
514 | 454 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
57 | 455 |
456 docinfo = self.getDocinfo(mode=mode,url=url) | |
457 pt = getattr(self.template, 'info_xml') | |
458 return pt(docinfo=docinfo) | |
459 | |
528 | 460 def getAuthenticatedUser(self, anon=None): |
461 """returns the authenticated user object or None. (ignores Zopes anonymous user)""" | |
462 user = getSecurityManager().getUser() | |
463 if user is not None and user.getUserName() != "Anonymous User": | |
464 return user | |
465 else: | |
466 return anon | |
467 | |
35 | 468 def isAccessible(self, docinfo): |
32 | 469 """returns if access to the resource is granted""" |
470 access = docinfo.get('accessType', None) | |
167 | 471 logging.debug("documentViewer (accessOK) access type %s"%access) |
465 | 472 if access == 'free': |
167 | 473 logging.debug("documentViewer (accessOK) access is free") |
32 | 474 return True |
465 | 475 |
45 | 476 elif access is None or access in self.authgroups: |
35 | 477 # only local access -- only logged in users |
528 | 478 user = self.getAuthenticatedUser() |
167 | 479 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
528 | 480 return (user is not None) |
32 | 481 |
167 | 482 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
32 | 483 return False |
464 | 484 |
543 | 485 def getUserinfo(self): |
486 """returns userinfo object""" | |
487 logging.debug("getUserinfo") | |
488 userinfo = {} | |
489 # look for cached userinfo in session | |
490 if self.REQUEST.SESSION.has_key('userinfo'): | |
491 userinfo = self.REQUEST.SESSION['userinfo'] | |
492 # check if its still current? | |
493 else: | |
494 # store in session | |
495 self.REQUEST.SESSION['userinfo'] = userinfo | |
496 | |
497 return userinfo | |
498 | |
612 | 499 def getDocinfoJSON(self, mode, url, tocMode=None): |
500 """returns docinfo depending on mode""" | |
501 import json | |
502 | |
503 dc = self.getDocinfo( mode, url, tocMode) | |
504 | |
505 return json.dumps(dc) | |
506 | |
507 | |
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
508 def getDocinfo(self, mode, url, tocMode=None): |
464 | 509 """returns docinfo depending on mode""" |
510 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) | |
511 # look for cached docinfo in session | |
512 if self.REQUEST.SESSION.has_key('docinfo'): | |
513 docinfo = self.REQUEST.SESSION['docinfo'] | |
514 # check if its still current | |
515 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: | |
516 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
517 return docinfo | |
518 | |
519 # new docinfo | |
520 docinfo = {'mode': mode, 'url': url} | |
521 # add self url | |
522 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
625
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
523 docinfo['digilibBaseUrl'] = sslifyUrl(self.digilibBaseUrl, self, force=True) |
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
524 docinfo['digilibScalerUrl'] = sslifyUrl(self.digilibScalerUrl, self, force=True) |
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
525 docinfo['digilibViewerUrl'] = sslifyUrl(self.digilibViewerUrl, self, force=True) |
464 | 526 # get index.meta DOM |
527 docUrl = None | |
528 metaDom = None | |
529 if mode=="texttool": | |
530 # url points to document dir or index.meta | |
531 metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
532 if metaDom is None: | |
533 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
|
534 |
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
535 docUrl = url.replace('/index.meta', '') |
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
536 if url.startswith('/mpiwg/online/'): |
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
537 docUrl = url.replace('/mpiwg/online/', '', 1) |
464 | 538 |
539 elif mode=="imagepath": | |
540 # url points to folder with images, index.meta optional | |
541 # asssume index.meta in parent dir | |
542 docUrl = getParentPath(url) | |
543 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
599 | 544 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
545 |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
546 elif mode=="hocr": |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
547 # url points to folder with images, index.meta optional |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
548 # asssume index.meta in parent dir |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
549 docUrl = getParentPath(url) |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
550 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
551 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
552 docinfo['textURLPath'] = url.replace('/mpiwg/online', '', 1) |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
553 if docinfo.get("creator", None) is None: |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
554 docinfo['creator'] = "" |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
555 |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
556 if docinfo.get("title", None) is None: |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
557 docinfo['title'] = "" |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
558 |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
559 if docinfo.get("documentPath", None) is None: |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
560 docinfo['documentPath'] = url.replace('/mpiwg/online', '', 1) |
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
561 docinfo['documentPath'] = url.replace('/pages', '', 1) |
464 | 562 |
563 elif mode=="filepath": | |
564 # url points to image file, index.meta optional | |
566 | 565 docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, url) |
548 | 566 docinfo['numPages'] = 1 |
464 | 567 # asssume index.meta is two path segments up |
568 docUrl = getParentPath(url, 2) | |
569 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
570 | |
571 else: | |
572 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
573 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
574 | |
575 docinfo['documentUrl'] = docUrl | |
576 # process index.meta contents | |
473 | 577 if metaDom is not None and metaDom.tag == 'resource': |
464 | 578 # document directory name and path |
608 | 579 resource = self.metadataService.getResourceData(dom=metaDom, recursive=1) |
464 | 580 if resource: |
581 docinfo = self.getDocinfoFromResource(docinfo, resource) | |
582 | |
583 # texttool info | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
584 texttool = self.metadataService.getTexttoolData(dom=metaDom, recursive=1, all=True) |
464 | 585 if texttool: |
586 docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
568 | 587 # document info from full text server |
516 | 588 if docinfo.get('textURLPath', None): |
565 | 589 docinfo = self.getTextInfo(mode=None, docinfo=docinfo) |
568 | 590 # include list of pages TODO: do we need this always? |
591 docinfo = self.getTextInfo(mode='pages', docinfo=docinfo) | |
464 | 592 |
593 # bib info | |
594 bib = self.metadataService.getBibData(dom=metaDom) | |
595 if bib: | |
548 | 596 # save extended version as 'bibx' TODO: ugly |
541 | 597 bibx = self.metadataService.getBibData(dom=metaDom, all=True, recursive=1) |
598 if len(bibx) == 1: | |
599 # unwrap list if possible | |
600 bibx = bibx[0] | |
601 | |
602 docinfo['bibx'] = bibx | |
603 docinfo = self.getDocinfoFromBib(docinfo, bib, bibx) | |
465 | 604 else: |
605 # no bib - try info.xml | |
606 docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) | |
464 | 607 |
608 # auth info | |
609 access = self.metadataService.getAccessData(dom=metaDom) | |
610 if access: | |
611 docinfo = self.getDocinfoFromAccess(docinfo, access) | |
612 | |
466 | 613 # attribution info |
614 attribution = self.metadataService.getAttributionData(dom=metaDom) | |
615 if attribution: | |
616 logging.debug("getDocinfo: attribution=%s"%repr(attribution)) | |
617 docinfo['attribution'] = attribution | |
618 | |
619 # copyright info | |
620 copyright = self.metadataService.getCopyrightData(dom=metaDom) | |
621 if copyright: | |
622 logging.debug("getDocinfo: copyright=%s"%repr(copyright)) | |
623 docinfo['copyright'] = copyright | |
538 | 624 |
625 # DRI (permanent ID) | |
581 | 626 dri = self.metadataService.getDRI(dom=metaDom, type='mpiwg') |
538 | 627 if dri: |
628 docinfo['DRI'] = dri | |
466 | 629 |
578 | 630 # (presentation) context |
631 ctx = self.metadataService.getContextData(dom=metaDom, all=True) | |
632 if ctx: | |
633 logging.debug("getcontext: ctx=%s"%repr(ctx)) | |
634 docinfo['presentationContext'] = ctx | |
635 | |
464 | 636 # image path |
637 if mode != 'texttool': | |
532 | 638 # override image path from texttool with url parameter TODO: how about mode=auto? |
599 | 639 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
464 | 640 |
548 | 641 # check numPages |
642 if docinfo.get('numPages', 0) == 0: | |
643 # number of images from digilib | |
644 if docinfo.get('imagePath', None): | |
599 | 645 imgpath = docinfo['imagePath'].replace('/mpiwg/online', '', 1) |
580
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
646 logging.debug("imgpath=%s"%imgpath) |
625
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
647 docinfo['imageURL'] = sslifyUrl("%s?fn=%s"%(self.digilibScalerUrl, imgpath), self, force=True) |
562 | 648 docinfo = self.getDocinfoFromDigilib(docinfo, imgpath) |
548 | 649 else: |
650 # imagePath still missing? try "./pageimg" | |
651 imgPath = os.path.join(docUrl, 'pageimg') | |
652 docinfo = self.getDocinfoFromDigilib(docinfo, imgPath) | |
653 if docinfo.get('numPages', 0) > 0: | |
654 # there are pages | |
655 docinfo['imagePath'] = imgPath | |
625
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
656 docinfo['imageURL'] = sslifyUrl("%s?fn=%s"%(self.digilibScalerUrl, docinfo['imagePath']), self, force=True) |
464 | 657 |
516 | 658 # check numPages |
659 if docinfo.get('numPages', 0) == 0: | |
660 if docinfo.get('numTextPages', 0) > 0: | |
661 # replace with numTextPages (text-only?) | |
662 docinfo['numPages'] = docinfo['numTextPages'] | |
607 | 663 |
664 # min and max page no | |
665 docinfo['minPageNo'] = docinfo.get('minPageNo', 1) | |
666 docinfo['maxPageNo'] = docinfo.get('maxPageNo', docinfo['numPages']) | |
516 | 667 |
608 | 668 # part-of information |
669 partOfPath = docinfo.get('partOfPath', None) | |
670 if partOfPath is not None: | |
671 partOfDom = self.metadataService.getDomFromPathOrUrl(partOfPath) | |
672 if partOfDom is not None: | |
673 docinfo['partOfLabel'] = self.metadataService.getBibFormattedLabel(dom=partOfDom) | |
674 docinfo['partOfUrl'] = "%s?url=%s"%(self.getDocumentViewerURL(), partOfPath) | |
675 logging.debug("partOfLabel=%s partOfUrl=%s"%(docinfo['partOfLabel'],docinfo['partOfUrl'])) | |
676 | |
599 | 677 # normalize path |
678 if 'imagePath' in docinfo and not docinfo['imagePath'].startswith('/'): | |
679 docinfo['imagePath'] = '/' + docinfo['imagePath'] | |
680 | |
464 | 681 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
682 # store in session | |
683 self.REQUEST.SESSION['docinfo'] = docinfo | |
684 return docinfo | |
685 | |
516 | 686 |
464 | 687 def getDocinfoFromResource(self, docinfo, resource): |
688 """reads contents of resource element into docinfo""" | |
608 | 689 logging.debug("getDocinfoFromResource: resource=%s"%(repr(resource))) |
690 docName = getMDText(resource.get('name', None)) | |
464 | 691 docinfo['documentName'] = docName |
608 | 692 docPath = getMDText(resource.get('archive-path', None)) |
464 | 693 if docPath: |
694 # clean up document path | |
695 if docPath[0] != '/': | |
696 docPath = '/' + docPath | |
697 | |
698 if docName and (not docPath.endswith(docName)): | |
699 docPath += "/" + docName | |
700 | |
701 else: | |
702 # use docUrl as docPath | |
703 docUrl = docinfo['documentURL'] | |
704 if not docUrl.startswith('http:'): | |
705 docPath = docUrl | |
608 | 706 |
465 | 707 if docPath: |
708 # fix URLs starting with /mpiwg/online | |
709 docPath = docPath.replace('/mpiwg/online', '', 1) | |
710 | |
464 | 711 docinfo['documentPath'] = docPath |
608 | 712 |
713 # is this part-of? | |
714 partOf = resource.get('is-part-of', None) | |
715 if partOf is not None: | |
716 partOf = getMDText(partOf.get('archive-path', None)) | |
717 if partOf is not None: | |
718 docinfo['partOfPath'] = partOf.strip() | |
719 | |
464 | 720 return docinfo |
721 | |
722 def getDocinfoFromTexttool(self, docinfo, texttool): | |
723 """reads contents of texttool element into docinfo""" | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
724 logging.debug("texttool=%s"%repr(texttool)) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
725 # unpack list if necessary |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
726 if isinstance(texttool, list): |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
727 texttool = texttool[0] |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
728 |
464 | 729 # image dir |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
730 imageDir = getMDText(texttool.get('image', None)) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
731 docPath = getMDText(docinfo.get('documentPath', None)) |
607 | 732 if imageDir: |
733 if imageDir.startswith('/'): | |
734 # absolute path | |
735 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
736 docinfo['imagePath'] = imageDir | |
737 | |
738 elif docPath: | |
739 # relative path | |
740 imageDir = os.path.join(docPath, imageDir) | |
741 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
742 docinfo['imagePath'] = imageDir | |
743 | |
744 # start and end page (for subdocuments of other documents) | |
745 imgStartNo = getMDText(texttool.get('image-start-no', None)) | |
746 minPageNo = getInt(imgStartNo, 1) | |
747 docinfo['minPageNo'] = minPageNo | |
748 | |
749 imgEndNo = getMDText(texttool.get('image-end-no', None)) | |
750 if imgEndNo: | |
751 docinfo['maxPageNo'] = getInt(imgEndNo) | |
464 | 752 |
753 # old style text URL | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
754 textUrl = getMDText(texttool.get('text', None)) |
617 | 755 |
464 | 756 if textUrl and docPath: |
757 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
758 textUrl = os.path.join(docPath, textUrl) | |
759 | |
760 docinfo['textURL'] = textUrl | |
761 | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
762 # 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
|
763 textUrlNode = texttool.get('text-url-path', None) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
764 if not isinstance(textUrlNode, list): |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
765 textUrlNode = [textUrlNode] |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
766 |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
767 for tun in textUrlNode: |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
768 textUrl = getMDText(tun) |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
769 if textUrl: |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
770 textUrlAtts = tun.get('@attr') |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
771 if (textUrlAtts and 'repository' in textUrlAtts): |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
772 textRepo = textUrlAtts['repository'] |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
773 # use matching repository |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
774 if self.getRepositoryType() == textRepo: |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
775 docinfo['textURLPath'] = textUrl |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
776 docinfo['textURLRepository'] = textRepo |
564 | 777 break |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
778 |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
779 else: |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
780 # no repo attribute - use always |
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
781 docinfo['textURLPath'] = textUrl |
468 | 782 |
783 # page flow | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
784 docinfo['pageFlow'] = getMDText(texttool.get('page-flow', 'ltr')) |
468 | 785 |
786 # odd pages are left | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
787 docinfo['oddPage'] = getMDText(texttool.get('odd-scan-position', 'left')) |
468 | 788 |
541 | 789 # number of title page (default 1) |
607 | 790 docinfo['titlePage'] = getMDText(texttool.get('title-scan-no', minPageNo)) |
464 | 791 |
792 # old presentation stuff | |
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
793 presentation = getMDText(texttool.get('presentation', None)) |
464 | 794 if presentation and docPath: |
465 | 795 if presentation.startswith('http:'): |
796 docinfo['presentationUrl'] = presentation | |
797 else: | |
798 docinfo['presentationUrl'] = os.path.join(docPath, presentation) | |
602 | 799 |
800 # make sure we have at least fake DC data | |
801 if 'creator' not in docinfo: | |
802 docinfo['creator'] = '[no author found]' | |
803 | |
804 if 'title' not in docinfo: | |
805 docinfo['title'] = '[no title found]' | |
806 | |
807 if 'date' not in docinfo: | |
808 docinfo['date'] = '[no date found]' | |
468 | 809 |
464 | 810 return docinfo |
811 | |
541 | 812 def getDocinfoFromBib(self, docinfo, bib, bibx=None): |
464 | 813 """reads contents of bib element into docinfo""" |
465 | 814 logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
464 | 815 # put all raw bib fields in dict "bib" |
816 docinfo['bib'] = bib | |
817 bibtype = bib.get('@type', None) | |
818 docinfo['bibType'] = bibtype | |
819 # also store DC metadata for convenience | |
820 dc = self.metadataService.getDCMappedData(bib) | |
536
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
821 docinfo['creator'] = dc.get('creator','') |
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
822 docinfo['title'] = dc.get('title','') |
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
823 docinfo['date'] = dc.get('date','') |
464 | 824 return docinfo |
825 | |
826 def getDocinfoFromAccess(self, docinfo, acc): | |
827 """reads contents of access element into docinfo""" | |
828 #TODO: also read resource type | |
465 | 829 logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
464 | 830 try: |
465 | 831 acctype = acc['@attr']['type'] |
464 | 832 if acctype: |
833 access=acctype | |
834 if access in ['group', 'institution']: | |
835 access = acc['name'].lower() | |
836 | |
837 docinfo['accessType'] = access | |
838 | |
839 except: | |
840 pass | |
841 | |
842 return docinfo | |
843 | |
844 def getDocinfoFromDigilib(self, docinfo, path): | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
845 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?fn="+path |
464 | 846 # fetch data |
847 txt = getHttpData(infoUrl) | |
848 if not txt: | |
849 logging.error("Unable to get dir-info from %s"%(infoUrl)) | |
850 return docinfo | |
851 | |
852 dom = ET.fromstring(txt) | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
853 dir = dom |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
854 # save size |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
855 size = dir.findtext('size') |
464 | 856 logging.debug("getDocinfoFromDigilib: size=%s"%size) |
857 if size: | |
858 docinfo['numPages'] = int(size) | |
859 else: | |
860 docinfo['numPages'] = 0 | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
861 return docinfo |
464 | 862 |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
863 # save list of image names and numbers |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
864 imgNames = {} |
591 | 865 imgIndexes = {} |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
866 for f in dir: |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
867 fn = f.findtext('name') |
591 | 868 pn = getInt(f.findtext('index')) |
869 imgNames[fn] = pn | |
870 imgIndexes[pn] = fn | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
871 |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
872 docinfo['imgFileNames'] = imgNames |
591 | 873 docinfo['imgFileIndexes'] = imgIndexes |
464 | 874 return docinfo |
875 | |
876 | |
465 | 877 def getDocinfoFromPresentationInfoXml(self,docinfo): |
878 """gets DC-like bibliographical information from the presentation entry in texttools""" | |
879 url = docinfo.get('presentationUrl', None) | |
880 if not url: | |
881 logging.error("getDocinfoFromPresentation: no URL!") | |
882 return docinfo | |
883 | |
884 dom = None | |
885 metaUrl = None | |
886 if url.startswith("http://"): | |
887 # real URL | |
888 metaUrl = url | |
889 else: | |
890 # online path | |
891 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
892 metaUrl=server+url | |
893 | |
894 txt=getHttpData(metaUrl) | |
895 if txt is None: | |
896 logging.error("Unable to read info.xml from %s"%(url)) | |
897 return docinfo | |
898 | |
899 dom = ET.fromstring(txt) | |
900 docinfo['creator']=getText(dom.find(".//author")) | |
901 docinfo['title']=getText(dom.find(".//title")) | |
902 docinfo['date']=getText(dom.find(".//date")) | |
903 return docinfo | |
904 | |
905 | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
906 def getPageinfo(self, pn=None, pf=None, start=None, rows=None, cols=None, docinfo=None, userinfo=None, viewMode=None, viewLayer=None, tocMode=None): |
22 | 907 """returns pageinfo with the given parameters""" |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
908 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 | 909 pageinfo = {} |
471 | 910 pageinfo['viewMode'] = viewMode |
508 | 911 # split viewLayer if necessary |
912 if isinstance(viewLayer,basestring): | |
913 viewLayer = viewLayer.split(',') | |
914 | |
915 if isinstance(viewLayer, list): | |
916 logging.debug("getPageinfo: viewLayer is list:%s"%viewLayer) | |
917 # save (unique) list in viewLayers | |
918 seen = set() | |
919 viewLayers = [l for l in viewLayer if l and l not in seen and not seen.add(l)] | |
920 pageinfo['viewLayers'] = viewLayers | |
921 # stringify viewLayer | |
922 viewLayer = ','.join(viewLayers) | |
923 else: | |
924 #create list | |
925 pageinfo['viewLayers'] = [viewLayer] | |
926 | |
503 | 927 pageinfo['viewLayer'] = viewLayer |
471 | 928 pageinfo['tocMode'] = tocMode |
929 | |
607 | 930 minPageNo = docinfo.get('minPageNo', 1) |
931 | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
932 # pf takes precedence over pn |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
933 if pf: |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
934 pageinfo['pf'] = pf |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
935 pn = getPnForPf(docinfo, pf) |
589 | 936 # replace pf in request params (used for creating new URLs) |
937 self.REQUEST.form.pop('pf', None) | |
938 self.REQUEST.form['pn'] = pn | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
939 else: |
607 | 940 pn = getInt(pn, minPageNo) |
591 | 941 pf = getPfForPn(docinfo, pn) |
942 pageinfo['pf'] = pf | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
943 |
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
944 pageinfo['pn'] = pn |
25 | 945 rows = int(rows or self.thumbrows) |
946 pageinfo['rows'] = rows | |
947 cols = int(cols or self.thumbcols) | |
948 pageinfo['cols'] = cols | |
949 grpsize = cols * rows | |
950 pageinfo['groupsize'] = grpsize | |
607 | 951 # if start is empty use one around pn |
952 grouppn = math.ceil(float(pn)/float(grpsize))*grpsize-(grpsize-1) | |
953 # but not smaller than minPageNo | |
954 start = getInt(start, max(grouppn, minPageNo)) | |
22 | 955 pageinfo['start'] = start |
511 | 956 # get number of pages |
607 | 957 numPages = int(docinfo.get('numPages', 0)) |
958 if numPages == 0: | |
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
959 # try numTextPages |
607 | 960 numPages = docinfo.get('numTextPages', 0) |
961 if numPages != 0: | |
962 docinfo['numPages'] = numPages | |
963 | |
964 maxPageNo = docinfo.get('maxPageNo', numPages) | |
965 logging.debug("minPageNo=%s maxPageNo=%s start=%s numPages=%s"%(minPageNo,maxPageNo,start,numPages)) | |
966 np = maxPageNo | |
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
967 |
511 | 968 # cache table of contents |
969 pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) | |
469 | 970 pageinfo['numgroups'] = int(np / grpsize) |
971 if np % grpsize > 0: | |
972 pageinfo['numgroups'] += 1 | |
476 | 973 |
974 pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' | |
975 oddScanLeft = docinfo.get('oddPage', 'left') != 'right' | |
976 # add zeroth page for two columns | |
977 pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) | |
978 pageinfo['pageZero'] = pageZero | |
607 | 979 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=minPageNo, maxIdx=np) |
516 | 980 # more page parameters |
629 | 981 #pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
982 #becuase it is buggy this currently disabled and set to orig. | |
983 pageinfo['characterNormalization'] = 'orig' | |
516 | 984 if docinfo.get('pageNumbers'): |
985 # get original page numbers | |
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
986 pageNumber = docinfo['pageNumbers'].get(pn, None) |
516 | 987 if pageNumber is not None: |
988 pageinfo['pageNumberOrig'] = pageNumber['no'] | |
989 pageinfo['pageNumberOrigNorm'] = pageNumber['non'] | |
158 | 990 |
511 | 991 # cache search results |
992 query = self.REQUEST.get('query',None) | |
993 pageinfo['query'] = query | |
591 | 994 if query and viewMode == 'text': |
995 pageinfo['resultPageSize'] = getInt(self.REQUEST.get('resultPageSize', 10)) | |
511 | 996 queryType = self.REQUEST.get('queryType', 'fulltextMorph') |
997 pageinfo['queryType'] = queryType | |
998 pageinfo['resultStart'] = getInt(self.REQUEST.get('resultStart', '1')) | |
999 self.getSearchResults(mode=queryType, query=query, pageinfo=pageinfo, docinfo=docinfo) | |
1000 | |
1001 # highlighting | |
1002 highlightQuery = self.REQUEST.get('highlightQuery', None) | |
1003 if highlightQuery: | |
1004 pageinfo['highlightQuery'] = highlightQuery | |
1005 pageinfo['highlightElement'] = self.REQUEST.get('highlightElement', '') | |
1006 pageinfo['highlightElementPos'] = self.REQUEST.get('highlightElementPos', '') | |
460 | 1007 |
22 | 1008 return pageinfo |
460 | 1009 |
463 | 1010 |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1011 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
|
1012 """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
|
1013 |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1014 :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
|
1015 :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
|
1016 :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
|
1017 :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
|
1018 :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
|
1019 :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
|
1020 :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
|
1021 :returns: dict with |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1022 first: first page index |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1023 last: last page index |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1024 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
|
1025 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
|
1026 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
|
1027 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
|
1028 """ |
607 | 1029 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
|
1030 batch = {} |
480 | 1031 grpsize = rows * cols |
476 | 1032 if maxIdx == 0: |
480 | 1033 maxIdx = start + grpsize |
476 | 1034 |
607 | 1035 np = maxIdx - minIdx + 1 |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1036 if pageZero: |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1037 # 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
|
1038 np += 1 |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1039 |
607 | 1040 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
|
1041 |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1042 # list of all batch start and end points |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1043 batches = [] |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1044 if pageZero: |
607 | 1045 ofs = minIdx - 1 |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1046 else: |
607 | 1047 ofs = minIdx |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1048 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1049 for i in range(nb): |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1050 s = i * grpsize + ofs |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1051 e = min((i + 1) * grpsize + ofs - 1, maxIdx) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1052 batches.append({'start':s, 'end':e}) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1053 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1054 batch['batches'] = batches |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1055 |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1056 # list of pages for current screen |
476 | 1057 pages = [] |
607 | 1058 if pageZero and start == minIdx: |
476 | 1059 # correct beginning |
607 | 1060 idx = minIdx - 1 |
476 | 1061 else: |
1062 idx = start | |
1063 | |
1064 for r in range(rows): | |
1065 row = [] | |
1066 for c in range(cols): | |
1067 if idx < minIdx or idx > maxIdx: | |
1068 page = {'idx':None} | |
1069 else: | |
1070 page = {'idx':idx} | |
1071 | |
1072 idx += 1 | |
1073 if pageFlowLtr: | |
1074 row.append(page) | |
1075 else: | |
1076 row.insert(0, page) | |
1077 | |
1078 pages.append(row) | |
1079 | |
607 | 1080 if start > minIdx: |
1081 batch['prevStart'] = max(start - grpsize, minIdx) | |
480 | 1082 else: |
1083 batch['prevStart'] = None | |
1084 | |
526 | 1085 if start + grpsize <= maxIdx: |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1086 if pageZero and start == minIdx: |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1087 # correct nextStart for pageZero |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1088 batch['nextStart'] = grpsize |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1089 else: |
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1090 batch['nextStart'] = start + grpsize |
480 | 1091 else: |
1092 batch['nextStart'] = None | |
1093 | |
1094 batch['pages'] = pages | |
571 | 1095 batch['first'] = minIdx |
1096 batch['last'] = maxIdx | |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1097 logging.debug("batch: %s"%repr(batch)) |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1098 return batch |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1099 |
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1100 |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1101 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
|
1102 """returns dict with information for one screenfull of data.""" |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1103 batch = {} |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1104 if end == 0: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1105 end = start + size |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1106 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1107 nb = int(math.ceil(end / float(size))) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1108 # list of all batch start and end points |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1109 batches = [] |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1110 for i in range(nb): |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1111 s = i * size + 1 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1112 e = min((i + 1) * size, end) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1113 batches.append({'start':s, 'end':e}) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1114 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1115 batch['batches'] = batches |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1116 # list of elements in this batch |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1117 this = [] |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1118 j = 0 |
526 | 1119 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
|
1120 if data: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1121 if fullData: |
526 | 1122 d = data.get(i, None) |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1123 else: |
526 | 1124 d = data.get(j, None) |
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1125 j += 1 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1126 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1127 else: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1128 d = i+1 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1129 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1130 this.append(d) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1131 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1132 batch['this'] = this |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1133 if start > 1: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1134 batch['prevStart'] = max(start - size, 1) |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1135 else: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1136 batch['prevStart'] = None |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1137 |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1138 if start + size < end: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1139 batch['nextStart'] = start + size |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1140 else: |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1141 batch['nextStart'] = None |
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1142 |
571 | 1143 batch['first'] = start |
1144 batch['last'] = end | |
480 | 1145 return batch |
476 | 1146 |
1147 | |
546 | 1148 def getAnnotatorGroupsForUser(self, user, annotationServerUrl="http://tuxserve03.mpiwg-berlin.mpg.de/AnnotationManager"): |
1149 """returns list of groups {name:*, id:*} on the annotation server for the user""" | |
1150 groups = [] | |
623 | 1151 # add matching http(s) from our URL |
1152 annotationServerUrl = sslifyUrl(annotationServerUrl, self) | |
622
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1153 |
546 | 1154 groupsUrl = "%s/annotator/groups?user=%s"%(annotationServerUrl,user) |
1155 data = getHttpData(url=groupsUrl, noExceptions=True) | |
1156 if data: | |
1157 res = json.loads(data) | |
1158 rows = res.get('rows', None) | |
1159 if rows is None: | |
1160 return groups | |
1161 for r in rows: | |
1162 groups.append({'id': r.get('id', None), 'name': r.get('name', None), 'uri': r.get('uri', None)}) | |
1163 | |
1164 return groups | |
1165 | |
626 | 1166 def sslifyUrl(self, url, **args): |
1167 """returns URL with http or https""" | |
1168 return sslifyUrl(url, **args) | |
546 | 1169 |
463 | 1170 security.declareProtected('View management screens','changeDocumentViewerForm') |
1171 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
22 | 1172 |
526 | 1173 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',availableLayers=None,RESPONSE=None): |
22 | 1174 """init document viewer""" |
1175 self.title=title | |
1176 self.digilibBaseUrl = digilibBaseUrl | |
566 | 1177 self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
1178 self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' | |
25 | 1179 self.thumbrows = thumbrows |
1180 self.thumbcols = thumbcols | |
32 | 1181 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
463 | 1182 try: |
1183 # assume MetaDataFolder instance is called metadata | |
1184 self.metadataService = getattr(self, 'metadata') | |
1185 except Exception, e: | |
1186 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
526 | 1187 |
1188 self.setAvailableLayers(availableLayers) | |
463 | 1189 |
22 | 1190 if RESPONSE is not None: |
1191 RESPONSE.redirect('manage_main') | |
623 | 1192 |
0 | 1193 |
1194 def manage_AddDocumentViewerForm(self): | |
1195 """add the viewer form""" | |
22 | 1196 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 1197 return pt() |
1198 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1199 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 1200 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1201 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 1202 self._setObject(id,newObj) |
1203 | |
1204 if RESPONSE is not None: | |
1205 RESPONSE.redirect('manage_main') |