Mercurial > hg > documentViewer
annotate documentViewer.py @ 635:8d460ddb45b7 default tip
update digilib dirInfo-xml path.
| author | casties |
|---|---|
| date | Fri, 06 May 2016 18:59:35 +0200 |
| parents | 618b600c805a |
| children |
| 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 |
|
631
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
22 INDEXMETA_NS="http://md.mpiwg-berlin.mpg.de/ns/indexMeta#" |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
23 |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
24 def removeINDEXMETA_NS(root): #entfernt den namespace von indexmeta aus dem dom #TODO evertyhing should be changed that it can deal with NS |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
25 for elem in root.getiterator(): |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
26 print ("ETAG") |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
27 print(elem.tag) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
28 if not hasattr(elem.tag, 'find'): continue # (1) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
29 |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
30 i = elem.tag.find('{%s}'%INDEXMETA_NS) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
31 if i >= 0: |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
32 elem.tag = elem.tag[i+len(('{%s}'%INDEXMETA_NS)):] |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
33 |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
34 print(elem.tag) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
35 |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
36 def getMDText(node): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
37 """returns the @text content from the MetaDataProvider metadata node""" |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
38 if isinstance(node, dict): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
39 return node.get('@text', None) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
40 |
| 617 | 41 if isinstance(node,list): #more than one text file if there is an attribute don't choose it |
| 42 for nodeInList in node: | |
| 43 attr = nodeInList.get("@attr",None) | |
| 44 if attr is None: | |
| 45 return node.get('@text',None) | |
| 46 return None | |
| 47 | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
48 return node |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
49 |
| 464 | 50 def getParentPath(path, cnt=1): |
| 51 """returns pathname shortened by cnt""" | |
| 52 # make sure path doesn't end with / | |
| 53 path = path.rstrip('/') | |
| 54 # split by /, shorten, and reassemble | |
| 55 return '/'.join(path.split('/')[0:-cnt]) | |
| 56 | |
| 589 | 57 def getPnForPf(docinfo, pf, default=0): |
| 58 """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
|
59 if 'imgFileNames' in docinfo: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
60 pn = docinfo['imgFileNames'].get(pf, None) |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
61 if pn is None: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
62 # try to cut extension |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
63 xi = pf.rfind('.') |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
64 if xi > 0: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
65 pf = pf[:xi] |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
66 # try again, else return 0 |
| 589 | 67 pn = docinfo['imgFileNames'].get(pf, default) |
| 68 else: | |
| 69 # no extension | |
| 70 pn = default | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
71 |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
72 return pn |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
73 |
| 589 | 74 return default |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
75 |
| 591 | 76 def getPfForPn(docinfo, pn, default=None): |
| 77 """returns image file name for image number or default""" | |
| 78 if 'imgFileIndexes' in docinfo: | |
| 79 pn = docinfo['imgFileIndexes'].get(pn, default) | |
| 80 return pn | |
| 81 | |
| 82 return default | |
| 83 | |
| 585 | 84 |
| 22 | 85 ## |
| 86 ## documentViewer class | |
| 87 ## | |
| 88 class documentViewer(Folder): | |
| 0 | 89 """document viewer""" |
| 90 meta_type="Document viewer" | |
| 91 | |
| 92 security=ClassSecurityInfo() | |
| 22 | 93 manage_options=Folder.manage_options+( |
| 507 | 94 {'label':'Configuration','action':'changeDocumentViewerForm'}, |
| 0 | 95 ) |
| 463 | 96 |
| 97 metadataService = None | |
| 98 """MetaDataFolder instance""" | |
| 525 | 99 |
| 0 | 100 |
| 525 | 101 # |
| 22 | 102 # templates and forms |
| 525 | 103 # |
| 104 # viewMode templates | |
| 594 | 105 viewer_text = PageTemplateFile('zpt/viewer/viewer_text', globals()) |
|
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
106 viewer_hocr = PageTemplateFile('zpt/viewer/viewer_hocr', globals()) |
| 594 | 107 viewer_xml = PageTemplateFile('zpt/viewer/viewer_xml', globals()) |
| 108 viewer_image = PageTemplateFile('zpt/viewer/viewer_image', globals()) | |
| 109 viewer_index = PageTemplateFile('zpt/viewer/viewer_index', globals()) | |
| 110 viewer_thumbs = PageTemplateFile('zpt/viewer/viewer_thumbs', globals()) | |
| 111 viewer_indexonly = PageTemplateFile('zpt/viewer/viewer_indexonly', globals()) | |
| 629 | 112 viewer_text_image = PageTemplateFile('zpt/viewer/viewer_text_image', globals()) |
| 546 | 113 # available layer types (annotator not default) |
| 114 builtinLayers = {'text': ['dict','search','gis'], | |
| 629 | 115 'xml': None, 'image': None, 'index': ['extended'],'text_image': ['dict'],} |
| 526 | 116 availableLayers = builtinLayers; |
| 525 | 117 # layer templates |
| 594 | 118 layer_text_dict = PageTemplateFile('zpt/viewer/layer_text_dict', globals()) |
| 629 | 119 layer_text_image_dict = PageTemplateFile('zpt/viewer/layer_text_image_dict', globals()) |
| 594 | 120 layer_text_search = PageTemplateFile('zpt/viewer/layer_text_search', globals()) |
| 121 layer_text_annotator = PageTemplateFile('zpt/viewer/layer_text_annotator', globals()) | |
| 122 layer_text_gis = PageTemplateFile('zpt/viewer/layer_text_gis', globals()) | |
| 123 layer_text_pundit = PageTemplateFile('zpt/viewer/layer_text_pundit', globals()) | |
| 124 layer_image_annotator = PageTemplateFile('zpt/viewer/layer_image_annotator', globals()) | |
| 125 layer_image_search = PageTemplateFile('zpt/viewer/layer_image_search', globals()) | |
| 126 layer_index_extended = PageTemplateFile('zpt/viewer/layer_index_extended', globals()) | |
| 525 | 127 # toc templates |
| 594 | 128 toc_thumbs = PageTemplateFile('zpt/viewer/toc_thumbs', globals()) |
| 129 toc_text = PageTemplateFile('zpt/viewer/toc_text', globals()) | |
| 130 toc_figures = PageTemplateFile('zpt/viewer/toc_figures', globals()) | |
| 131 toc_concordance = PageTemplateFile('zpt/viewer/toc_concordance', globals()) | |
| 609 | 132 toc_notes = PageTemplateFile('zpt/viewer/toc_notes', globals()) |
| 594 | 133 toc_handwritten = PageTemplateFile('zpt/viewer/toc_handwritten', globals()) |
| 134 toc_none = PageTemplateFile('zpt/viewer/toc_none', globals()) | |
| 525 | 135 # other templates |
| 594 | 136 common_template = PageTemplateFile('zpt/viewer/common_template', globals()) |
| 137 info_xml = PageTemplateFile('zpt/viewer/info_xml', globals()) | |
| 487 | 138 docuviewer_css = ImageFile('css/docuviewer.css',globals()) |
| 532 | 139 # make docuviewer_css refreshable for development |
|
490
6f116b86a226
more new template stuff. moved ImageFile index method to SrvTxtUtils
casties
parents:
489
diff
changeset
|
140 docuviewer_css.index_html = refreshingImageFileIndexHtml |
|
535
510bae2b593b
more fixes, e.g. IE support. first version of index page.
casties
parents:
532
diff
changeset
|
141 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
|
142 # make docuviewer_ie_css refreshable for development |
| 585 | 143 #docuviewer_ie_css.index_html = refreshingImageFileIndexHtml |
| 501 | 144 jquery_js = ImageFile('js/jquery.js',globals()) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
145 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
146 |
| 95 | 147 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
| 0 | 148 """init document viewer""" |
| 149 self.id=id | |
| 150 self.title=title | |
| 25 | 151 self.thumbcols = thumbcols |
| 152 self.thumbrows = thumbrows | |
| 32 | 153 # authgroups is list of authorized groups (delimited by ,) |
| 154 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
|
155 # 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
|
156 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
157 templateFolder = Folder('template') |
| 498 | 158 self['template'] = templateFolder # Zope-2.12 style |
| 159 #self._setObject('template',templateFolder) # old style | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
160 try: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
161 import MpdlXmlTextServer |
| 132 | 162 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
| 498 | 163 templateFolder['fulltextclient'] = textServer |
| 164 #templateFolder._setObject('fulltextclient',textServer) | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
165 except Exception, e: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
166 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
| 463 | 167 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
168 try: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
169 from Products.zogiLib.zogiLib import zogiLib |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
170 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
| 498 | 171 templateFolder['zogilib'] = zogilib |
| 172 #templateFolder._setObject('zogilib',zogilib) | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
173 except Exception, e: |
| 607 | 174 logging.error("Unable to create zogiLib for 'zogilib': "+str(e)) |
| 463 | 175 |
| 176 try: | |
| 177 # assume MetaDataFolder instance is called metadata | |
| 178 self.metadataService = getattr(self, 'metadata') | |
| 179 except Exception, e: | |
| 180 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 181 | |
| 477 | 182 if digilibBaseUrl is not None: |
| 183 self.digilibBaseUrl = digilibBaseUrl | |
| 566 | 184 self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
| 185 self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' | |
| 477 | 186 |
| 623 | 187 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
188 # proxy text server methods to fulltextclient |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
189 def getTextPage(self, **args): |
| 498 | 190 """returns full text content of page""" |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
191 return self.template.fulltextclient.getTextPage(**args) |
| 22 | 192 |
| 508 | 193 def getSearchResults(self, **args): |
| 194 """loads list of search results and stores XML in docinfo""" | |
| 195 return self.template.fulltextclient.getSearchResults(**args) | |
| 196 | |
| 197 def getResultsPage(self, **args): | |
| 198 """returns one page of the search results""" | |
| 199 return self.template.fulltextclient.getResultsPage(**args) | |
| 200 | |
| 516 | 201 def getTextInfo(self, **args): |
| 202 """returns document info from the text server""" | |
| 203 return self.template.fulltextclient.getTextInfo(**args) | |
| 204 | |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
205 def getToc(self, **args): |
| 508 | 206 """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
|
207 return self.template.fulltextclient.getToc(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
208 |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
209 def getTocPage(self, **args): |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
210 """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
|
211 return self.template.fulltextclient.getTocPage(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
212 |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
213 def getRepositoryType(self, **args): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
214 """get repository type""" |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
215 return self.template.fulltextclient.getRepositoryType(**args) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
216 |
| 559 | 217 def getTextDownloadUrl(self, **args): |
| 610 | 218 """get URL to download the full text""" |
| 559 | 219 return self.template.fulltextclient.getTextDownloadUrl(**args) |
| 220 | |
| 506 | 221 def getPlacesOnPage(self, **args): |
| 222 """get list of gis places on one page""" | |
| 223 return self.template.fulltextclient.getPlacesOnPage(**args) | |
| 307 | 224 |
| 548 | 225 # Thumb list for CoolIris Plugin |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
226 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
| 68 | 227 security.declareProtected('View','thumbs_rss') |
| 228 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
| 229 ''' | |
| 230 view it | |
| 231 @param mode: defines how to access the document behind url | |
| 232 @param url: url which contains display information | |
| 590 | 233 @param viewMode: image: display images, text: display text, default is auto (try text, else image) |
| 68 | 234 |
| 235 ''' | |
| 236 | |
| 237 if not hasattr(self, 'template'): | |
| 590 | 238 # this won't work |
| 239 logging.error("template folder missing!") | |
| 240 return "ERROR: template folder missing!" | |
| 241 | |
| 68 | 242 if not self.digilibBaseUrl: |
| 623 | 243 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 68 | 244 |
| 245 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 338 | 246 #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
|
247 pageinfo = self.getPageinfo(start=start,pn=pn, docinfo=docinfo) |
| 331 | 248 ''' ZDES ''' |
| 68 | 249 pt = getattr(self.template, 'thumbs_main_rss') |
| 250 | |
| 251 if viewMode=="auto": # automodus gewaehlt | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
252 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
| 68 | 253 viewMode="text" |
| 254 else: | |
| 590 | 255 viewMode="image" |
| 68 | 256 |
| 257 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
| 465 | 258 |
| 68 | 259 |
| 22 | 260 security.declareProtected('View','index_html') |
| 589 | 261 def index_html(self, url, mode="texttool", viewMode="auto", viewLayer=None, tocMode=None, start=None, pn=None, pf=None): |
| 464 | 262 """ |
| 543 | 263 show page |
| 471 | 264 @param url: url which contains display information |
| 57 | 265 @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
|
266 @param viewMode: 'image': display images, 'text': display text, 'xml': display xml, default is 'auto', 'hocr' : hocr format |
| 543 | 267 @param viewLayer: sub-type of viewMode, e.g. layer 'dict' for viewMode='text' |
| 99 | 268 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
| 464 | 269 """ |
| 0 | 270 |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
271 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 | 272 |
| 273 if not hasattr(self, 'template'): | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
274 # this won't work |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
275 logging.error("template folder missing!") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
276 return "ERROR: template folder missing!" |
| 617 | 277 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
278 if not getattr(self, 'digilibBaseUrl', None): |
| 132 | 279 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 22 | 280 |
| 548 | 281 # mode=filepath should not have toc-thumbs |
| 282 if tocMode is None: | |
| 283 if mode == "filepath": | |
| 284 tocMode = "none" | |
| 285 else: | |
| 286 tocMode = "thumbs" | |
| 287 | |
| 543 | 288 # docinfo: information about document (cached) |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
289 docinfo = self.getDocinfo(mode=mode,url=url,tocMode=tocMode) |
| 97 | 290 |
| 543 | 291 # userinfo: user settings (cached) |
| 292 userinfo = self.getUserinfo() | |
| 293 | |
| 471 | 294 # auto viewMode: text if there is a text else images |
| 455 | 295 if viewMode=="auto": |
| 530 | 296 if docinfo.get('textURLPath', None): |
| 297 # docinfo.get('textURL', None) not implemented yet | |
| 471 | 298 viewMode = "text" |
| 543 | 299 if viewLayer is None and 'viewLayer' not in userinfo: |
| 300 # use layer dict as default | |
| 508 | 301 viewLayer = "dict" |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
302 else: |
| 590 | 303 viewMode = "image" |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
304 |
| 474 | 305 elif viewMode == "text_dict": |
| 306 # legacy fix | |
| 307 viewMode = "text" | |
| 503 | 308 viewLayer = "dict" |
| 474 | 309 |
| 590 | 310 elif viewMode == 'images': |
| 311 # legacy fix | |
| 312 viewMode = 'image' | |
| 313 self.REQUEST['viewMode'] = 'image' | |
| 314 | |
| 543 | 315 # safe viewLayer in userinfo |
| 316 userinfo['viewLayer'] = viewLayer | |
| 548 | 317 |
| 543 | 318 # pageinfo: information about page (not cached) |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
319 pageinfo = self.getPageinfo(start=start, pn=pn, pf=pf, docinfo=docinfo, userinfo=userinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode) |
| 469 | 320 |
| 475 | 321 # get template /template/viewer_$viewMode |
| 322 pt = getattr(self.template, 'viewer_%s'%viewMode, None) | |
| 323 if pt is None: | |
| 324 logging.error("No template for viewMode=%s!"%viewMode) | |
| 325 # TODO: error page? | |
| 326 return "No template for viewMode=%s!"%viewMode | |
| 327 | |
| 455 | 328 # and execute with parameters |
| 471 | 329 return pt(docinfo=docinfo, pageinfo=pageinfo) |
| 0 | 330 |
| 525 | 331 def getAvailableLayers(self): |
| 332 """returns dict with list of available layers per viewMode""" | |
| 333 return self.availableLayers | |
| 334 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
335 def findDigilibUrl(self): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
336 """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
|
337 url = self.template.zogilib.getDLBaseUrl() |
| 624 | 338 return url |
| 480 | 339 |
| 340 def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None): | |
| 341 """returns URL to digilib Scaler with params""" | |
| 342 url = None | |
| 343 if docinfo is not None: | |
| 344 url = docinfo.get('imageURL', None) | |
| 345 | |
| 346 if url is None: | |
| 566 | 347 url = self.digilibScalerUrl |
| 480 | 348 if fn is None and docinfo is not None: |
| 349 fn = docinfo.get('imagePath','') | |
| 350 | |
| 351 url += "fn=%s"%fn | |
| 352 | |
| 353 if pn: | |
| 354 url += "&pn=%s"%pn | |
| 355 | |
| 356 url += "&dw=%s&dh=%s"%(dw,dh) | |
| 624 | 357 return sslifyUrl(url, self, force=True) |
| 126 | 358 |
| 359 def getDocumentViewerURL(self): | |
| 360 """returns the URL of this instance""" | |
| 361 return self.absolute_url() | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
362 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
363 def getStyle(self, idx, selected, style=""): |
| 480 | 364 """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
|
365 #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
|
366 if idx == selected: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
367 return style + 'sel' |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
368 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
369 return style |
| 74 | 370 |
| 478 | 371 def getParams(self, param=None, val=None, params=None, duplicates=None): |
| 469 | 372 """returns dict with URL parameters. |
| 373 | |
| 374 Takes URL parameters and additionally param=val or dict params. | |
| 375 Deletes key if value is None.""" | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
376 # copy existing request params |
| 469 | 377 newParams=self.REQUEST.form.copy() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
378 # change single param |
| 25 | 379 if param is not None: |
| 31 | 380 if val is None: |
| 469 | 381 if newParams.has_key(param): |
| 382 del newParams[param] | |
| 25 | 383 else: |
| 469 | 384 newParams[param] = str(val) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
385 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
386 # change more params |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
387 if params is not None: |
| 478 | 388 for (k, v) in params.items(): |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
389 if v is None: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
390 # val=None removes param |
| 469 | 391 if newParams.has_key(k): |
| 392 del newParams[k] | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
393 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
394 else: |
| 469 | 395 newParams[k] = v |
| 478 | 396 |
| 397 if duplicates: | |
| 398 # eliminate lists (coming from duplicate keys) | |
| 399 for (k,v) in newParams.items(): | |
| 400 if isinstance(v, list): | |
| 401 if duplicates == 'comma': | |
| 402 # make comma-separated list of non-empty entries | |
| 403 newParams[k] = ','.join([t for t in v if t]) | |
| 404 elif duplicates == 'first': | |
| 405 # take first non-empty entry | |
| 406 newParams[k] = [t for t in v if t][0] | |
| 407 | |
| 469 | 408 return newParams |
| 409 | |
| 478 | 410 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
| 469 | 411 """returns URL to documentviewer with parameter param set to val or from dict params""" |
| 478 | 412 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
|
413 # quote values and assemble into query string (not escaping '/') |
| 514 | 414 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
|
415 if baseUrl is None: |
| 469 | 416 baseUrl = self.getDocumentViewerURL() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
417 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
418 url = "%s?%s"%(baseUrl, ps) |
| 25 | 419 return url |
| 420 | |
| 478 | 421 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
| 68 | 422 """link to documentviewer with parameter param set to val""" |
| 478 | 423 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
|
424 |
| 526 | 425 |
| 426 def setAvailableLayers(self, newLayerString=None): | |
| 427 """sets availableLayers to newLayerString or tries to autodetect available layers. | |
| 428 assumes layer templates have the form layer_{m}_{l} for layer l in mode m. | |
| 429 newLayerString is parsed as JSON.""" | |
| 430 if newLayerString is not None: | |
| 431 try: | |
| 432 layers = json.loads(newLayerString) | |
| 590 | 433 if 'text' in layers and 'image' in layers: |
| 526 | 434 self.availableLayers = layers |
| 435 return | |
| 436 except: | |
| 437 pass | |
| 438 | |
| 439 logging.error("invalid layers=%s! autodetecting..."%repr(newLayerString)) | |
| 440 | |
| 441 # start with builtin layers | |
| 442 self.availableLayers = self.builtinLayers.copy() | |
| 443 # add layers from templates | |
| 444 for t in self.template: | |
| 445 if t.startswith('layer_'): | |
| 446 try: | |
| 447 (x, m, l) = t.split('_', 3) | |
| 448 if m not in self.availableLayers: | |
| 449 # mode m doesn't exist -> new list | |
| 450 self.availableLayers[m] = [l] | |
| 451 | |
| 452 else: | |
| 453 # m exists -> append | |
| 454 if l not in self.availableLayers[m]: | |
| 455 self.availableLayers[m].append() | |
| 456 | |
| 457 except: | |
| 458 pass | |
| 459 | |
| 460 def getAvailableLayersJson(self): | |
| 461 """returns available layers as JSON string.""" | |
| 462 return json.dumps(self.availableLayers) | |
| 463 | |
| 469 | 464 |
| 57 | 465 def getInfo_xml(self,url,mode): |
| 466 """returns info about the document as XML""" | |
| 467 if not self.digilibBaseUrl: | |
| 514 | 468 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 57 | 469 |
| 470 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 471 pt = getattr(self.template, 'info_xml') | |
| 472 return pt(docinfo=docinfo) | |
| 473 | |
| 528 | 474 def getAuthenticatedUser(self, anon=None): |
| 475 """returns the authenticated user object or None. (ignores Zopes anonymous user)""" | |
| 476 user = getSecurityManager().getUser() | |
| 477 if user is not None and user.getUserName() != "Anonymous User": | |
| 478 return user | |
| 479 else: | |
| 480 return anon | |
| 481 | |
| 35 | 482 def isAccessible(self, docinfo): |
| 32 | 483 """returns if access to the resource is granted""" |
| 484 access = docinfo.get('accessType', None) | |
| 167 | 485 logging.debug("documentViewer (accessOK) access type %s"%access) |
| 465 | 486 if access == 'free': |
| 167 | 487 logging.debug("documentViewer (accessOK) access is free") |
| 32 | 488 return True |
| 465 | 489 |
| 45 | 490 elif access is None or access in self.authgroups: |
| 35 | 491 # only local access -- only logged in users |
| 528 | 492 user = self.getAuthenticatedUser() |
| 167 | 493 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
| 528 | 494 return (user is not None) |
| 32 | 495 |
| 167 | 496 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
| 32 | 497 return False |
| 464 | 498 |
| 543 | 499 def getUserinfo(self): |
| 500 """returns userinfo object""" | |
| 501 logging.debug("getUserinfo") | |
| 502 userinfo = {} | |
| 503 # look for cached userinfo in session | |
| 504 if self.REQUEST.SESSION.has_key('userinfo'): | |
| 505 userinfo = self.REQUEST.SESSION['userinfo'] | |
| 506 # check if its still current? | |
| 507 else: | |
| 508 # store in session | |
| 509 self.REQUEST.SESSION['userinfo'] = userinfo | |
| 510 | |
| 511 return userinfo | |
| 512 | |
| 612 | 513 def getDocinfoJSON(self, mode, url, tocMode=None): |
| 514 """returns docinfo depending on mode""" | |
| 515 import json | |
| 516 | |
| 517 dc = self.getDocinfo( mode, url, tocMode) | |
| 518 | |
| 519 return json.dumps(dc) | |
| 520 | |
| 521 | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
522 def getDocinfo(self, mode, url, tocMode=None): |
| 464 | 523 """returns docinfo depending on mode""" |
| 524 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) | |
| 525 # look for cached docinfo in session | |
| 526 if self.REQUEST.SESSION.has_key('docinfo'): | |
| 527 docinfo = self.REQUEST.SESSION['docinfo'] | |
| 528 # check if its still current | |
| 529 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: | |
| 530 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
| 531 return docinfo | |
| 532 | |
| 533 # new docinfo | |
| 534 docinfo = {'mode': mode, 'url': url} | |
| 535 # add self url | |
| 536 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
|
625
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
537 docinfo['digilibBaseUrl'] = sslifyUrl(self.digilibBaseUrl, self, force=True) |
|
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
538 docinfo['digilibScalerUrl'] = sslifyUrl(self.digilibScalerUrl, self, force=True) |
|
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
539 docinfo['digilibViewerUrl'] = sslifyUrl(self.digilibViewerUrl, self, force=True) |
| 464 | 540 # get index.meta DOM |
| 541 docUrl = None | |
| 542 metaDom = None | |
| 543 if mode=="texttool": | |
| 544 # url points to document dir or index.meta | |
| 545 metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
|
631
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
546 removeINDEXMETA_NS(metaDom) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
547 |
| 464 | 548 if metaDom is None: |
| 549 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
|
550 |
|
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
551 docUrl = url.replace('/index.meta', '') |
|
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
552 if url.startswith('/mpiwg/online/'): |
|
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
553 docUrl = url.replace('/mpiwg/online/', '', 1) |
| 634 | 554 |
|
631
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
555 elif mode=="textpath": |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
556 #url points to an textfile |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
557 #index.meta optional |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
558 #assume index.meta in parent dir |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
559 docUrl = getParentPath(url) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
560 docinfo['viewmode'] = "text" |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
561 |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
562 try: |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
563 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
564 removeINDEXMETA_NS(metaDom) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
565 |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
566 except: |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
567 metaDom = None |
| 634 | 568 |
|
631
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
569 #metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
570 #docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
571 docinfo['textURLPath'] = url.replace('/mpiwg/online', '', 1) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
572 docinfo['textURL'] = url |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
573 if docinfo.get("creator", None) is None: |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
574 docinfo['creator'] = "" |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
575 |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
576 if docinfo.get("title", None) is None: |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
577 docinfo['title'] = "" |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
578 |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
579 if docinfo.get("documentPath", None) is None: |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
580 docinfo['documentPath'] = url.replace('/mpiwg/online', '', 1) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
581 docinfo['documentPath'] = url.replace('/pages', '', 1) |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
582 |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
583 docinfo['numPages'] = 1 |
| 464 | 584 |
| 585 elif mode=="imagepath": | |
| 586 # url points to folder with images, index.meta optional | |
| 587 # asssume index.meta in parent dir | |
| 634 | 588 docUrl = getParentPath(url) |
| 464 | 589 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
| 599 | 590 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
|
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
591 |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
592 elif mode=="hocr": |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
593 # url points to folder with images, index.meta optional |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
594 # asssume index.meta in parent dir |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
595 docUrl = getParentPath(url) |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
596 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
597 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
598 docinfo['textURLPath'] = url.replace('/mpiwg/online', '', 1) |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
599 if docinfo.get("creator", None) is None: |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
600 docinfo['creator'] = "" |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
601 |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
602 if docinfo.get("title", None) is None: |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
603 docinfo['title'] = "" |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
604 |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
605 if docinfo.get("documentPath", None) is None: |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
606 docinfo['documentPath'] = url.replace('/mpiwg/online', '', 1) |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
607 docinfo['documentPath'] = url.replace('/pages', '', 1) |
| 464 | 608 |
| 609 elif mode=="filepath": | |
| 610 # url points to image file, index.meta optional | |
| 566 | 611 docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, url) |
| 548 | 612 docinfo['numPages'] = 1 |
| 464 | 613 # asssume index.meta is two path segments up |
| 614 docUrl = getParentPath(url, 2) | |
| 615 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 616 | |
| 617 else: | |
| 618 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
| 619 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
| 620 | |
| 621 docinfo['documentUrl'] = docUrl | |
| 622 # process index.meta contents | |
|
631
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
623 |
|
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
624 if metaDom is not None and (metaDom.tag == 'resource' or metaDom.tag == "{%s}resource"%INDEXMETA_NS): |
| 464 | 625 # document directory name and path |
| 608 | 626 resource = self.metadataService.getResourceData(dom=metaDom, recursive=1) |
| 464 | 627 if resource: |
| 628 docinfo = self.getDocinfoFromResource(docinfo, resource) | |
|
631
0c3aab828864
remove index meta ns
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
629
diff
changeset
|
629 |
| 464 | 630 # texttool info |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
631 texttool = self.metadataService.getTexttoolData(dom=metaDom, recursive=1, all=True) |
| 464 | 632 if texttool: |
| 633 docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
| 568 | 634 # document info from full text server |
| 516 | 635 if docinfo.get('textURLPath', None): |
| 565 | 636 docinfo = self.getTextInfo(mode=None, docinfo=docinfo) |
| 568 | 637 # include list of pages TODO: do we need this always? |
| 638 docinfo = self.getTextInfo(mode='pages', docinfo=docinfo) | |
| 464 | 639 |
| 640 # bib info | |
| 641 bib = self.metadataService.getBibData(dom=metaDom) | |
| 642 if bib: | |
| 548 | 643 # save extended version as 'bibx' TODO: ugly |
| 541 | 644 bibx = self.metadataService.getBibData(dom=metaDom, all=True, recursive=1) |
| 645 if len(bibx) == 1: | |
| 646 # unwrap list if possible | |
| 647 bibx = bibx[0] | |
| 648 | |
| 649 docinfo['bibx'] = bibx | |
| 650 docinfo = self.getDocinfoFromBib(docinfo, bib, bibx) | |
| 465 | 651 else: |
| 652 # no bib - try info.xml | |
| 653 docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) | |
| 464 | 654 |
| 655 # auth info | |
| 656 access = self.metadataService.getAccessData(dom=metaDom) | |
| 657 if access: | |
| 658 docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 659 | |
| 466 | 660 # attribution info |
| 661 attribution = self.metadataService.getAttributionData(dom=metaDom) | |
| 662 if attribution: | |
| 663 logging.debug("getDocinfo: attribution=%s"%repr(attribution)) | |
| 664 docinfo['attribution'] = attribution | |
| 665 | |
| 666 # copyright info | |
| 667 copyright = self.metadataService.getCopyrightData(dom=metaDom) | |
| 668 if copyright: | |
| 669 logging.debug("getDocinfo: copyright=%s"%repr(copyright)) | |
| 670 docinfo['copyright'] = copyright | |
| 538 | 671 |
| 672 # DRI (permanent ID) | |
| 581 | 673 dri = self.metadataService.getDRI(dom=metaDom, type='mpiwg') |
| 538 | 674 if dri: |
| 675 docinfo['DRI'] = dri | |
| 466 | 676 |
| 578 | 677 # (presentation) context |
| 678 ctx = self.metadataService.getContextData(dom=metaDom, all=True) | |
| 679 if ctx: | |
| 680 logging.debug("getcontext: ctx=%s"%repr(ctx)) | |
| 681 docinfo['presentationContext'] = ctx | |
| 682 | |
| 464 | 683 # image path |
| 684 if mode != 'texttool': | |
| 532 | 685 # override image path from texttool with url parameter TODO: how about mode=auto? |
| 599 | 686 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
| 464 | 687 |
| 548 | 688 # check numPages |
| 689 if docinfo.get('numPages', 0) == 0: | |
| 690 # number of images from digilib | |
| 691 if docinfo.get('imagePath', None): | |
| 599 | 692 imgpath = docinfo['imagePath'].replace('/mpiwg/online', '', 1) |
|
580
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
693 logging.debug("imgpath=%s"%imgpath) |
|
625
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
694 docinfo['imageURL'] = sslifyUrl("%s?fn=%s"%(self.digilibScalerUrl, imgpath), self, force=True) |
| 562 | 695 docinfo = self.getDocinfoFromDigilib(docinfo, imgpath) |
| 548 | 696 else: |
| 697 # imagePath still missing? try "./pageimg" | |
| 698 imgPath = os.path.join(docUrl, 'pageimg') | |
| 699 docinfo = self.getDocinfoFromDigilib(docinfo, imgPath) | |
| 700 if docinfo.get('numPages', 0) > 0: | |
| 701 # there are pages | |
| 702 docinfo['imagePath'] = imgPath | |
|
625
80a3b1fa5705
more move sslification to only client-visible urls.
casties
parents:
624
diff
changeset
|
703 docinfo['imageURL'] = sslifyUrl("%s?fn=%s"%(self.digilibScalerUrl, docinfo['imagePath']), self, force=True) |
| 464 | 704 |
| 516 | 705 # check numPages |
| 706 if docinfo.get('numPages', 0) == 0: | |
| 707 if docinfo.get('numTextPages', 0) > 0: | |
| 708 # replace with numTextPages (text-only?) | |
| 709 docinfo['numPages'] = docinfo['numTextPages'] | |
| 607 | 710 |
| 711 # min and max page no | |
| 712 docinfo['minPageNo'] = docinfo.get('minPageNo', 1) | |
| 713 docinfo['maxPageNo'] = docinfo.get('maxPageNo', docinfo['numPages']) | |
| 516 | 714 |
| 608 | 715 # part-of information |
| 716 partOfPath = docinfo.get('partOfPath', None) | |
| 717 if partOfPath is not None: | |
| 718 partOfDom = self.metadataService.getDomFromPathOrUrl(partOfPath) | |
| 719 if partOfDom is not None: | |
| 720 docinfo['partOfLabel'] = self.metadataService.getBibFormattedLabel(dom=partOfDom) | |
| 721 docinfo['partOfUrl'] = "%s?url=%s"%(self.getDocumentViewerURL(), partOfPath) | |
| 722 logging.debug("partOfLabel=%s partOfUrl=%s"%(docinfo['partOfLabel'],docinfo['partOfUrl'])) | |
| 723 | |
| 599 | 724 # normalize path |
| 725 if 'imagePath' in docinfo and not docinfo['imagePath'].startswith('/'): | |
| 726 docinfo['imagePath'] = '/' + docinfo['imagePath'] | |
| 727 | |
| 464 | 728 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
| 729 # store in session | |
| 730 self.REQUEST.SESSION['docinfo'] = docinfo | |
| 731 return docinfo | |
| 732 | |
| 516 | 733 |
| 464 | 734 def getDocinfoFromResource(self, docinfo, resource): |
| 735 """reads contents of resource element into docinfo""" | |
| 608 | 736 logging.debug("getDocinfoFromResource: resource=%s"%(repr(resource))) |
| 737 docName = getMDText(resource.get('name', None)) | |
| 464 | 738 docinfo['documentName'] = docName |
| 608 | 739 docPath = getMDText(resource.get('archive-path', None)) |
| 464 | 740 if docPath: |
| 741 # clean up document path | |
| 742 if docPath[0] != '/': | |
| 743 docPath = '/' + docPath | |
| 744 | |
| 745 if docName and (not docPath.endswith(docName)): | |
| 746 docPath += "/" + docName | |
| 747 | |
| 748 else: | |
| 749 # use docUrl as docPath | |
| 750 docUrl = docinfo['documentURL'] | |
| 751 if not docUrl.startswith('http:'): | |
| 752 docPath = docUrl | |
| 608 | 753 |
| 465 | 754 if docPath: |
| 755 # fix URLs starting with /mpiwg/online | |
| 756 docPath = docPath.replace('/mpiwg/online', '', 1) | |
| 757 | |
| 464 | 758 docinfo['documentPath'] = docPath |
| 608 | 759 |
| 760 # is this part-of? | |
| 761 partOf = resource.get('is-part-of', None) | |
| 762 if partOf is not None: | |
| 763 partOf = getMDText(partOf.get('archive-path', None)) | |
| 764 if partOf is not None: | |
| 765 docinfo['partOfPath'] = partOf.strip() | |
| 766 | |
| 464 | 767 return docinfo |
| 768 | |
| 769 def getDocinfoFromTexttool(self, docinfo, texttool): | |
| 770 """reads contents of texttool element into docinfo""" | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
771 logging.debug("texttool=%s"%repr(texttool)) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
772 # unpack list if necessary |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
773 if isinstance(texttool, list): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
774 texttool = texttool[0] |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
775 |
| 464 | 776 # image dir |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
777 imageDir = getMDText(texttool.get('image', None)) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
778 docPath = getMDText(docinfo.get('documentPath', None)) |
| 607 | 779 if imageDir: |
| 780 if imageDir.startswith('/'): | |
| 781 # absolute path | |
| 782 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
| 783 docinfo['imagePath'] = imageDir | |
| 784 | |
| 785 elif docPath: | |
| 786 # relative path | |
| 787 imageDir = os.path.join(docPath, imageDir) | |
| 788 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
| 789 docinfo['imagePath'] = imageDir | |
| 790 | |
| 791 # start and end page (for subdocuments of other documents) | |
| 792 imgStartNo = getMDText(texttool.get('image-start-no', None)) | |
| 793 minPageNo = getInt(imgStartNo, 1) | |
| 794 docinfo['minPageNo'] = minPageNo | |
| 795 | |
| 796 imgEndNo = getMDText(texttool.get('image-end-no', None)) | |
| 797 if imgEndNo: | |
| 798 docinfo['maxPageNo'] = getInt(imgEndNo) | |
| 464 | 799 |
| 800 # old style text URL | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
801 textUrl = getMDText(texttool.get('text', None)) |
| 617 | 802 |
| 464 | 803 if textUrl and docPath: |
| 804 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
| 805 textUrl = os.path.join(docPath, textUrl) | |
| 806 | |
| 807 docinfo['textURL'] = textUrl | |
| 808 | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
809 # 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
|
810 textUrlNode = texttool.get('text-url-path', None) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
811 if not isinstance(textUrlNode, list): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
812 textUrlNode = [textUrlNode] |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
813 |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
814 for tun in textUrlNode: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
815 textUrl = getMDText(tun) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
816 if textUrl: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
817 textUrlAtts = tun.get('@attr') |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
818 if (textUrlAtts and 'repository' in textUrlAtts): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
819 textRepo = textUrlAtts['repository'] |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
820 # use matching repository |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
821 if self.getRepositoryType() == textRepo: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
822 docinfo['textURLPath'] = textUrl |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
823 docinfo['textURLRepository'] = textRepo |
| 564 | 824 break |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
825 |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
826 else: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
827 # no repo attribute - use always |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
828 docinfo['textURLPath'] = textUrl |
| 468 | 829 |
| 830 # page flow | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
831 docinfo['pageFlow'] = getMDText(texttool.get('page-flow', 'ltr')) |
| 468 | 832 |
| 833 # odd pages are left | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
834 docinfo['oddPage'] = getMDText(texttool.get('odd-scan-position', 'left')) |
| 468 | 835 |
| 541 | 836 # number of title page (default 1) |
| 607 | 837 docinfo['titlePage'] = getMDText(texttool.get('title-scan-no', minPageNo)) |
| 464 | 838 |
| 839 # old presentation stuff | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
840 presentation = getMDText(texttool.get('presentation', None)) |
| 464 | 841 if presentation and docPath: |
| 465 | 842 if presentation.startswith('http:'): |
| 843 docinfo['presentationUrl'] = presentation | |
| 844 else: | |
| 845 docinfo['presentationUrl'] = os.path.join(docPath, presentation) | |
| 602 | 846 |
| 847 # make sure we have at least fake DC data | |
| 848 if 'creator' not in docinfo: | |
| 849 docinfo['creator'] = '[no author found]' | |
| 850 | |
| 851 if 'title' not in docinfo: | |
| 852 docinfo['title'] = '[no title found]' | |
| 853 | |
| 854 if 'date' not in docinfo: | |
| 855 docinfo['date'] = '[no date found]' | |
| 468 | 856 |
| 464 | 857 return docinfo |
| 858 | |
| 541 | 859 def getDocinfoFromBib(self, docinfo, bib, bibx=None): |
| 464 | 860 """reads contents of bib element into docinfo""" |
| 465 | 861 logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
| 464 | 862 # put all raw bib fields in dict "bib" |
| 863 docinfo['bib'] = bib | |
| 864 bibtype = bib.get('@type', None) | |
| 865 docinfo['bibType'] = bibtype | |
| 866 # also store DC metadata for convenience | |
| 867 dc = self.metadataService.getDCMappedData(bib) | |
|
536
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
868 docinfo['creator'] = dc.get('creator','') |
|
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
869 docinfo['title'] = dc.get('title','') |
|
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
870 docinfo['date'] = dc.get('date','') |
| 464 | 871 return docinfo |
| 872 | |
| 873 def getDocinfoFromAccess(self, docinfo, acc): | |
| 874 """reads contents of access element into docinfo""" | |
| 875 #TODO: also read resource type | |
| 465 | 876 logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
| 464 | 877 try: |
| 465 | 878 acctype = acc['@attr']['type'] |
| 464 | 879 if acctype: |
| 880 access=acctype | |
| 881 if access in ['group', 'institution']: | |
| 882 access = acc['name'].lower() | |
| 883 | |
| 884 docinfo['accessType'] = access | |
| 885 | |
| 886 except: | |
| 887 pass | |
| 888 | |
| 889 return docinfo | |
| 890 | |
| 891 def getDocinfoFromDigilib(self, docinfo, path): | |
| 635 | 892 infoUrl=self.digilibBaseUrl+"/api/dirInfo-xml.jsp?fn="+path |
| 464 | 893 # fetch data |
| 894 txt = getHttpData(infoUrl) | |
| 895 if not txt: | |
| 896 logging.error("Unable to get dir-info from %s"%(infoUrl)) | |
| 897 return docinfo | |
| 898 | |
| 899 dom = ET.fromstring(txt) | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
900 dir = dom |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
901 # save size |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
902 size = dir.findtext('size') |
| 464 | 903 logging.debug("getDocinfoFromDigilib: size=%s"%size) |
| 904 if size: | |
| 905 docinfo['numPages'] = int(size) | |
| 906 else: | |
| 907 docinfo['numPages'] = 0 | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
908 return docinfo |
| 464 | 909 |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
910 # save list of image names and numbers |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
911 imgNames = {} |
| 591 | 912 imgIndexes = {} |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
913 for f in dir: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
914 fn = f.findtext('name') |
| 591 | 915 pn = getInt(f.findtext('index')) |
| 916 imgNames[fn] = pn | |
| 917 imgIndexes[pn] = fn | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
918 |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
919 docinfo['imgFileNames'] = imgNames |
| 591 | 920 docinfo['imgFileIndexes'] = imgIndexes |
| 464 | 921 return docinfo |
| 922 | |
| 923 | |
| 465 | 924 def getDocinfoFromPresentationInfoXml(self,docinfo): |
| 925 """gets DC-like bibliographical information from the presentation entry in texttools""" | |
| 926 url = docinfo.get('presentationUrl', None) | |
| 927 if not url: | |
| 928 logging.error("getDocinfoFromPresentation: no URL!") | |
| 929 return docinfo | |
| 930 | |
| 931 dom = None | |
| 932 metaUrl = None | |
| 933 if url.startswith("http://"): | |
| 934 # real URL | |
| 935 metaUrl = url | |
| 936 else: | |
| 937 # online path | |
| 938 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 939 metaUrl=server+url | |
| 940 | |
| 941 txt=getHttpData(metaUrl) | |
| 942 if txt is None: | |
| 943 logging.error("Unable to read info.xml from %s"%(url)) | |
| 944 return docinfo | |
| 945 | |
| 946 dom = ET.fromstring(txt) | |
| 947 docinfo['creator']=getText(dom.find(".//author")) | |
| 948 docinfo['title']=getText(dom.find(".//title")) | |
| 949 docinfo['date']=getText(dom.find(".//date")) | |
| 950 return docinfo | |
| 951 | |
| 952 | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
953 def getPageinfo(self, pn=None, pf=None, start=None, rows=None, cols=None, docinfo=None, userinfo=None, viewMode=None, viewLayer=None, tocMode=None): |
| 22 | 954 """returns pageinfo with the given parameters""" |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
955 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 | 956 pageinfo = {} |
| 471 | 957 pageinfo['viewMode'] = viewMode |
| 508 | 958 # split viewLayer if necessary |
| 959 if isinstance(viewLayer,basestring): | |
| 960 viewLayer = viewLayer.split(',') | |
| 961 | |
| 962 if isinstance(viewLayer, list): | |
| 963 logging.debug("getPageinfo: viewLayer is list:%s"%viewLayer) | |
| 964 # save (unique) list in viewLayers | |
| 965 seen = set() | |
| 966 viewLayers = [l for l in viewLayer if l and l not in seen and not seen.add(l)] | |
| 967 pageinfo['viewLayers'] = viewLayers | |
| 968 # stringify viewLayer | |
| 969 viewLayer = ','.join(viewLayers) | |
| 970 else: | |
| 971 #create list | |
| 972 pageinfo['viewLayers'] = [viewLayer] | |
| 973 | |
| 503 | 974 pageinfo['viewLayer'] = viewLayer |
| 471 | 975 pageinfo['tocMode'] = tocMode |
| 976 | |
| 607 | 977 minPageNo = docinfo.get('minPageNo', 1) |
| 978 | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
979 # pf takes precedence over pn |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
980 if pf: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
981 pageinfo['pf'] = pf |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
982 pn = getPnForPf(docinfo, pf) |
| 589 | 983 # replace pf in request params (used for creating new URLs) |
| 984 self.REQUEST.form.pop('pf', None) | |
| 985 self.REQUEST.form['pn'] = pn | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
986 else: |
| 607 | 987 pn = getInt(pn, minPageNo) |
| 591 | 988 pf = getPfForPn(docinfo, pn) |
| 989 pageinfo['pf'] = pf | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
990 |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
991 pageinfo['pn'] = pn |
| 25 | 992 rows = int(rows or self.thumbrows) |
| 993 pageinfo['rows'] = rows | |
| 994 cols = int(cols or self.thumbcols) | |
| 995 pageinfo['cols'] = cols | |
| 996 grpsize = cols * rows | |
| 997 pageinfo['groupsize'] = grpsize | |
| 607 | 998 # if start is empty use one around pn |
| 999 grouppn = math.ceil(float(pn)/float(grpsize))*grpsize-(grpsize-1) | |
| 1000 # but not smaller than minPageNo | |
| 1001 start = getInt(start, max(grouppn, minPageNo)) | |
| 22 | 1002 pageinfo['start'] = start |
| 511 | 1003 # get number of pages |
| 607 | 1004 numPages = int(docinfo.get('numPages', 0)) |
| 1005 if numPages == 0: | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
1006 # try numTextPages |
| 607 | 1007 numPages = docinfo.get('numTextPages', 0) |
| 1008 if numPages != 0: | |
| 1009 docinfo['numPages'] = numPages | |
| 1010 | |
| 1011 maxPageNo = docinfo.get('maxPageNo', numPages) | |
| 1012 logging.debug("minPageNo=%s maxPageNo=%s start=%s numPages=%s"%(minPageNo,maxPageNo,start,numPages)) | |
| 1013 np = maxPageNo | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
1014 |
| 511 | 1015 # cache table of contents |
| 1016 pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) | |
| 469 | 1017 pageinfo['numgroups'] = int(np / grpsize) |
| 1018 if np % grpsize > 0: | |
| 1019 pageinfo['numgroups'] += 1 | |
| 476 | 1020 |
| 1021 pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' | |
| 1022 oddScanLeft = docinfo.get('oddPage', 'left') != 'right' | |
| 1023 # add zeroth page for two columns | |
| 1024 pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) | |
| 1025 pageinfo['pageZero'] = pageZero | |
| 607 | 1026 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=minPageNo, maxIdx=np) |
| 516 | 1027 # more page parameters |
| 629 | 1028 #pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
| 1029 #becuase it is buggy this currently disabled and set to orig. | |
| 1030 pageinfo['characterNormalization'] = 'orig' | |
| 516 | 1031 if docinfo.get('pageNumbers'): |
| 1032 # get original page numbers | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
1033 pageNumber = docinfo['pageNumbers'].get(pn, None) |
| 516 | 1034 if pageNumber is not None: |
| 1035 pageinfo['pageNumberOrig'] = pageNumber['no'] | |
| 1036 pageinfo['pageNumberOrigNorm'] = pageNumber['non'] | |
| 158 | 1037 |
| 511 | 1038 # cache search results |
| 1039 query = self.REQUEST.get('query',None) | |
| 1040 pageinfo['query'] = query | |
| 591 | 1041 if query and viewMode == 'text': |
| 1042 pageinfo['resultPageSize'] = getInt(self.REQUEST.get('resultPageSize', 10)) | |
| 511 | 1043 queryType = self.REQUEST.get('queryType', 'fulltextMorph') |
| 1044 pageinfo['queryType'] = queryType | |
| 1045 pageinfo['resultStart'] = getInt(self.REQUEST.get('resultStart', '1')) | |
| 1046 self.getSearchResults(mode=queryType, query=query, pageinfo=pageinfo, docinfo=docinfo) | |
| 1047 | |
| 1048 # highlighting | |
| 1049 highlightQuery = self.REQUEST.get('highlightQuery', None) | |
| 1050 if highlightQuery: | |
| 1051 pageinfo['highlightQuery'] = highlightQuery | |
| 1052 pageinfo['highlightElement'] = self.REQUEST.get('highlightElement', '') | |
| 1053 pageinfo['highlightElementPos'] = self.REQUEST.get('highlightElementPos', '') | |
| 460 | 1054 |
| 22 | 1055 return pageinfo |
| 460 | 1056 |
| 463 | 1057 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1058 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
|
1059 """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
|
1060 |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1061 :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
|
1062 :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
|
1063 :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
|
1064 :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
|
1065 :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
|
1066 :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
|
1067 :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
|
1068 :returns: dict with |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1069 first: first page index |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1070 last: last page index |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1071 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
|
1072 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
|
1073 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
|
1074 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
|
1075 """ |
| 607 | 1076 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
|
1077 batch = {} |
| 480 | 1078 grpsize = rows * cols |
| 476 | 1079 if maxIdx == 0: |
| 480 | 1080 maxIdx = start + grpsize |
| 476 | 1081 |
| 607 | 1082 np = maxIdx - minIdx + 1 |
|
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1083 if pageZero: |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1084 # 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
|
1085 np += 1 |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1086 |
| 607 | 1087 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
|
1088 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1089 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1090 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1091 if pageZero: |
| 607 | 1092 ofs = minIdx - 1 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1093 else: |
| 607 | 1094 ofs = minIdx |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1095 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1096 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1097 s = i * grpsize + ofs |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1098 e = min((i + 1) * grpsize + ofs - 1, maxIdx) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1099 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1100 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1101 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1102 |
|
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1103 # list of pages for current screen |
| 476 | 1104 pages = [] |
| 607 | 1105 if pageZero and start == minIdx: |
| 476 | 1106 # correct beginning |
| 607 | 1107 idx = minIdx - 1 |
| 476 | 1108 else: |
| 1109 idx = start | |
| 1110 | |
| 1111 for r in range(rows): | |
| 1112 row = [] | |
| 1113 for c in range(cols): | |
| 1114 if idx < minIdx or idx > maxIdx: | |
| 1115 page = {'idx':None} | |
| 1116 else: | |
| 1117 page = {'idx':idx} | |
| 1118 | |
| 1119 idx += 1 | |
| 1120 if pageFlowLtr: | |
| 1121 row.append(page) | |
| 1122 else: | |
| 1123 row.insert(0, page) | |
| 1124 | |
| 1125 pages.append(row) | |
| 1126 | |
| 607 | 1127 if start > minIdx: |
| 1128 batch['prevStart'] = max(start - grpsize, minIdx) | |
| 480 | 1129 else: |
| 1130 batch['prevStart'] = None | |
| 1131 | |
| 526 | 1132 if start + grpsize <= maxIdx: |
|
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1133 if pageZero and start == minIdx: |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1134 # correct nextStart for pageZero |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1135 batch['nextStart'] = grpsize |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1136 else: |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1137 batch['nextStart'] = start + grpsize |
| 480 | 1138 else: |
| 1139 batch['nextStart'] = None | |
| 1140 | |
| 1141 batch['pages'] = pages | |
| 571 | 1142 batch['first'] = minIdx |
| 1143 batch['last'] = maxIdx | |
|
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1144 logging.debug("batch: %s"%repr(batch)) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1145 return batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1146 |
|
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1147 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1148 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
|
1149 """returns dict with information for one screenfull of data.""" |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1150 batch = {} |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1151 if end == 0: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1152 end = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1153 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1154 nb = int(math.ceil(end / float(size))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1155 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1156 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1157 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1158 s = i * size + 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1159 e = min((i + 1) * size, end) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1160 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1161 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1162 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1163 # list of elements in this batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1164 this = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1165 j = 0 |
| 526 | 1166 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
|
1167 if data: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1168 if fullData: |
| 526 | 1169 d = data.get(i, None) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1170 else: |
| 526 | 1171 d = data.get(j, None) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1172 j += 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1173 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1174 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1175 d = i+1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1176 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1177 this.append(d) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1178 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1179 batch['this'] = this |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1180 if start > 1: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1181 batch['prevStart'] = max(start - size, 1) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1182 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1183 batch['prevStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1184 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1185 if start + size < end: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1186 batch['nextStart'] = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1187 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1188 batch['nextStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1189 |
| 571 | 1190 batch['first'] = start |
| 1191 batch['last'] = end | |
| 480 | 1192 return batch |
| 476 | 1193 |
| 1194 | |
| 546 | 1195 def getAnnotatorGroupsForUser(self, user, annotationServerUrl="http://tuxserve03.mpiwg-berlin.mpg.de/AnnotationManager"): |
| 1196 """returns list of groups {name:*, id:*} on the annotation server for the user""" | |
| 1197 groups = [] | |
| 623 | 1198 # add matching http(s) from our URL |
| 1199 annotationServerUrl = sslifyUrl(annotationServerUrl, self) | |
|
622
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1200 |
| 546 | 1201 groupsUrl = "%s/annotator/groups?user=%s"%(annotationServerUrl,user) |
| 1202 data = getHttpData(url=groupsUrl, noExceptions=True) | |
| 1203 if data: | |
| 1204 res = json.loads(data) | |
| 1205 rows = res.get('rows', None) | |
| 1206 if rows is None: | |
| 1207 return groups | |
| 1208 for r in rows: | |
| 1209 groups.append({'id': r.get('id', None), 'name': r.get('name', None), 'uri': r.get('uri', None)}) | |
| 1210 | |
| 1211 return groups | |
| 1212 | |
| 626 | 1213 def sslifyUrl(self, url, **args): |
| 1214 """returns URL with http or https""" | |
| 1215 return sslifyUrl(url, **args) | |
| 546 | 1216 |
| 463 | 1217 security.declareProtected('View management screens','changeDocumentViewerForm') |
| 1218 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 22 | 1219 |
| 526 | 1220 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',availableLayers=None,RESPONSE=None): |
| 22 | 1221 """init document viewer""" |
| 1222 self.title=title | |
| 1223 self.digilibBaseUrl = digilibBaseUrl | |
| 566 | 1224 self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
| 1225 self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' | |
| 25 | 1226 self.thumbrows = thumbrows |
| 1227 self.thumbcols = thumbcols | |
| 32 | 1228 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| 463 | 1229 try: |
| 1230 # assume MetaDataFolder instance is called metadata | |
| 1231 self.metadataService = getattr(self, 'metadata') | |
| 1232 except Exception, e: | |
| 1233 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 526 | 1234 |
| 1235 self.setAvailableLayers(availableLayers) | |
| 463 | 1236 |
| 22 | 1237 if RESPONSE is not None: |
| 1238 RESPONSE.redirect('manage_main') | |
| 623 | 1239 |
| 0 | 1240 |
| 1241 def manage_AddDocumentViewerForm(self): | |
| 1242 """add the viewer form""" | |
| 22 | 1243 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| 0 | 1244 return pt() |
| 1245 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1246 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
| 0 | 1247 """add the viewer""" |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1248 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
| 0 | 1249 self._setObject(id,newObj) |
| 1250 | |
| 1251 if RESPONSE is not None: | |
| 1252 RESPONSE.redirect('manage_main') |