Mercurial > hg > documentViewer
annotate documentViewer.py @ 599:3b79ae4a23ca
normalize uri of annotated image.
| author | casties |
|---|---|
| date | Mon, 19 Nov 2012 17:15:13 +0100 |
| parents | da7daa783df4 |
| children | ef1d0a1fc9fa |
| 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 from Globals import package_home |
| 8 | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
9 import xml.etree.ElementTree as ET |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
10 |
|
489
55e3398e395e
more new templates. monkey-patch for App.ImageFile.
casties
parents:
488
diff
changeset
|
11 import os |
| 31 | 12 import sys |
| 0 | 13 import urllib |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
14 import logging |
| 61 | 15 import math |
| 46 | 16 import urlparse |
| 174 | 17 import re |
| 389 | 18 import string |
| 526 | 19 import json |
| 231 | 20 |
| 541 | 21 from Products.MetaDataProvider import MetaDataFolder |
| 22 | |
| 514 | 23 from SrvTxtUtils import getInt, utf8ify, getText, getHttpData, refreshingImageFileIndexHtml |
| 52 | 24 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
25 def serializeNode(node, encoding="utf-8"): |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
26 """returns a string containing node as XML""" |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
27 s = ET.tostring(node) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
28 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
29 # 4Suite: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
30 # stream = cStringIO.StringIO() |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
31 # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
32 # s = stream.getvalue() |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
33 # stream.close() |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
34 return s |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
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 |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
41 return node |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
42 |
| 464 | 43 def getParentPath(path, cnt=1): |
| 44 """returns pathname shortened by cnt""" | |
| 45 # make sure path doesn't end with / | |
| 46 path = path.rstrip('/') | |
| 47 # split by /, shorten, and reassemble | |
| 48 return '/'.join(path.split('/')[0:-cnt]) | |
| 49 | |
| 589 | 50 def getPnForPf(docinfo, pf, default=0): |
| 51 """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
|
52 if 'imgFileNames' in docinfo: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
53 pn = docinfo['imgFileNames'].get(pf, None) |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
54 if pn is None: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
55 # try to cut extension |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
56 xi = pf.rfind('.') |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
57 if xi > 0: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
58 pf = pf[:xi] |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
59 # try again, else return 0 |
| 589 | 60 pn = docinfo['imgFileNames'].get(pf, default) |
| 61 else: | |
| 62 # no extension | |
| 63 pn = default | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
64 |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
65 return pn |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
66 |
| 589 | 67 return default |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
68 |
| 591 | 69 def getPfForPn(docinfo, pn, default=None): |
| 70 """returns image file name for image number or default""" | |
| 71 if 'imgFileIndexes' in docinfo: | |
| 72 pn = docinfo['imgFileIndexes'].get(pn, default) | |
| 73 return pn | |
| 74 | |
| 75 return default | |
| 76 | |
| 585 | 77 |
| 22 | 78 ## |
| 79 ## documentViewer class | |
| 80 ## | |
| 81 class documentViewer(Folder): | |
| 0 | 82 """document viewer""" |
| 83 meta_type="Document viewer" | |
| 84 | |
| 85 security=ClassSecurityInfo() | |
| 22 | 86 manage_options=Folder.manage_options+( |
| 507 | 87 {'label':'Configuration','action':'changeDocumentViewerForm'}, |
| 0 | 88 ) |
| 463 | 89 |
| 90 metadataService = None | |
| 91 """MetaDataFolder instance""" | |
| 525 | 92 |
| 0 | 93 |
| 525 | 94 # |
| 22 | 95 # templates and forms |
| 525 | 96 # |
| 97 # viewMode templates | |
| 594 | 98 viewer_text = PageTemplateFile('zpt/viewer/viewer_text', globals()) |
| 99 viewer_xml = PageTemplateFile('zpt/viewer/viewer_xml', globals()) | |
| 100 viewer_image = PageTemplateFile('zpt/viewer/viewer_image', globals()) | |
| 101 viewer_index = PageTemplateFile('zpt/viewer/viewer_index', globals()) | |
| 102 viewer_thumbs = PageTemplateFile('zpt/viewer/viewer_thumbs', globals()) | |
| 103 viewer_indexonly = PageTemplateFile('zpt/viewer/viewer_indexonly', globals()) | |
| 546 | 104 # available layer types (annotator not default) |
| 105 builtinLayers = {'text': ['dict','search','gis'], | |
| 590 | 106 'xml': None, 'image': None, 'index': ['extended']} |
| 526 | 107 availableLayers = builtinLayers; |
| 525 | 108 # layer templates |
| 594 | 109 layer_text_dict = PageTemplateFile('zpt/viewer/layer_text_dict', globals()) |
| 110 layer_text_search = PageTemplateFile('zpt/viewer/layer_text_search', globals()) | |
| 111 layer_text_annotator = PageTemplateFile('zpt/viewer/layer_text_annotator', globals()) | |
| 112 layer_text_gis = PageTemplateFile('zpt/viewer/layer_text_gis', globals()) | |
| 113 layer_text_pundit = PageTemplateFile('zpt/viewer/layer_text_pundit', globals()) | |
| 114 layer_image_annotator = PageTemplateFile('zpt/viewer/layer_image_annotator', globals()) | |
| 115 layer_image_search = PageTemplateFile('zpt/viewer/layer_image_search', globals()) | |
| 116 layer_index_extended = PageTemplateFile('zpt/viewer/layer_index_extended', globals()) | |
| 525 | 117 # toc templates |
| 594 | 118 toc_thumbs = PageTemplateFile('zpt/viewer/toc_thumbs', globals()) |
| 119 toc_text = PageTemplateFile('zpt/viewer/toc_text', globals()) | |
| 120 toc_figures = PageTemplateFile('zpt/viewer/toc_figures', globals()) | |
| 121 toc_concordance = PageTemplateFile('zpt/viewer/toc_concordance', globals()) | |
| 122 toc_handwritten = PageTemplateFile('zpt/viewer/toc_handwritten', globals()) | |
| 123 toc_none = PageTemplateFile('zpt/viewer/toc_none', globals()) | |
| 525 | 124 # other templates |
| 594 | 125 common_template = PageTemplateFile('zpt/viewer/common_template', globals()) |
| 126 info_xml = PageTemplateFile('zpt/viewer/info_xml', globals()) | |
| 487 | 127 docuviewer_css = ImageFile('css/docuviewer.css',globals()) |
| 532 | 128 # make docuviewer_css refreshable for development |
|
490
6f116b86a226
more new template stuff. moved ImageFile index method to SrvTxtUtils
casties
parents:
489
diff
changeset
|
129 docuviewer_css.index_html = refreshingImageFileIndexHtml |
|
535
510bae2b593b
more fixes, e.g. IE support. first version of index page.
casties
parents:
532
diff
changeset
|
130 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
|
131 # make docuviewer_ie_css refreshable for development |
| 585 | 132 #docuviewer_ie_css.index_html = refreshingImageFileIndexHtml |
| 501 | 133 jquery_js = ImageFile('js/jquery.js',globals()) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
134 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
135 |
| 95 | 136 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
| 0 | 137 """init document viewer""" |
| 138 self.id=id | |
| 139 self.title=title | |
| 25 | 140 self.thumbcols = thumbcols |
| 141 self.thumbrows = thumbrows | |
| 32 | 142 # authgroups is list of authorized groups (delimited by ,) |
| 143 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
|
144 # 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
|
145 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
146 templateFolder = Folder('template') |
| 498 | 147 self['template'] = templateFolder # Zope-2.12 style |
| 148 #self._setObject('template',templateFolder) # old style | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
149 try: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
150 import MpdlXmlTextServer |
| 132 | 151 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
| 498 | 152 templateFolder['fulltextclient'] = textServer |
| 153 #templateFolder._setObject('fulltextclient',textServer) | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
154 except Exception, e: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
155 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
| 463 | 156 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
157 try: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
158 from Products.zogiLib.zogiLib import zogiLib |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
159 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
| 498 | 160 templateFolder['zogilib'] = zogilib |
| 161 #templateFolder._setObject('zogilib',zogilib) | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
162 except Exception, e: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
163 logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
| 463 | 164 |
| 165 try: | |
| 166 # assume MetaDataFolder instance is called metadata | |
| 167 self.metadataService = getattr(self, 'metadata') | |
| 168 except Exception, e: | |
| 169 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 170 | |
| 477 | 171 if digilibBaseUrl is not None: |
| 172 self.digilibBaseUrl = digilibBaseUrl | |
| 566 | 173 self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
| 174 self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' | |
| 477 | 175 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
176 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
177 # proxy text server methods to fulltextclient |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
178 def getTextPage(self, **args): |
| 498 | 179 """returns full text content of page""" |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
180 return self.template.fulltextclient.getTextPage(**args) |
| 22 | 181 |
| 508 | 182 def getSearchResults(self, **args): |
| 183 """loads list of search results and stores XML in docinfo""" | |
| 184 return self.template.fulltextclient.getSearchResults(**args) | |
| 185 | |
| 186 def getResultsPage(self, **args): | |
| 187 """returns one page of the search results""" | |
| 188 return self.template.fulltextclient.getResultsPage(**args) | |
| 189 | |
| 516 | 190 def getTextInfo(self, **args): |
| 191 """returns document info from the text server""" | |
| 192 return self.template.fulltextclient.getTextInfo(**args) | |
| 193 | |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
194 def getToc(self, **args): |
| 508 | 195 """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
|
196 return self.template.fulltextclient.getToc(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
197 |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
198 def getTocPage(self, **args): |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
199 """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
|
200 return self.template.fulltextclient.getTocPage(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
201 |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
202 def getRepositoryType(self, **args): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
203 """get repository type""" |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
204 return self.template.fulltextclient.getRepositoryType(**args) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
205 |
| 559 | 206 def getTextDownloadUrl(self, **args): |
| 207 """get list of gis places on one page""" | |
| 208 return self.template.fulltextclient.getTextDownloadUrl(**args) | |
| 209 | |
| 506 | 210 def getPlacesOnPage(self, **args): |
| 211 """get list of gis places on one page""" | |
| 212 return self.template.fulltextclient.getPlacesOnPage(**args) | |
| 307 | 213 |
| 548 | 214 # Thumb list for CoolIris Plugin |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
215 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
| 68 | 216 security.declareProtected('View','thumbs_rss') |
| 217 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
| 218 ''' | |
| 219 view it | |
| 220 @param mode: defines how to access the document behind url | |
| 221 @param url: url which contains display information | |
| 590 | 222 @param viewMode: image: display images, text: display text, default is auto (try text, else image) |
| 68 | 223 |
| 224 ''' | |
| 225 | |
| 226 if not hasattr(self, 'template'): | |
| 590 | 227 # this won't work |
| 228 logging.error("template folder missing!") | |
| 229 return "ERROR: template folder missing!" | |
| 230 | |
| 68 | 231 if not self.digilibBaseUrl: |
| 232 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 233 | |
| 234 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 338 | 235 #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
|
236 pageinfo = self.getPageinfo(start=start,pn=pn, docinfo=docinfo) |
| 331 | 237 ''' ZDES ''' |
| 68 | 238 pt = getattr(self.template, 'thumbs_main_rss') |
| 239 | |
| 240 if viewMode=="auto": # automodus gewaehlt | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
241 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
| 68 | 242 viewMode="text" |
| 243 else: | |
| 590 | 244 viewMode="image" |
| 68 | 245 |
| 246 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
| 465 | 247 |
| 68 | 248 |
| 22 | 249 security.declareProtected('View','index_html') |
| 589 | 250 def index_html(self, url, mode="texttool", viewMode="auto", viewLayer=None, tocMode=None, start=None, pn=None, pf=None): |
| 464 | 251 """ |
| 543 | 252 show page |
| 471 | 253 @param url: url which contains display information |
| 57 | 254 @param mode: defines how to access the document behind url |
| 590 | 255 @param viewMode: 'image': display images, 'text': display text, 'xml': display xml, default is 'auto' |
| 543 | 256 @param viewLayer: sub-type of viewMode, e.g. layer 'dict' for viewMode='text' |
| 99 | 257 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
| 464 | 258 """ |
| 0 | 259 |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
260 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 | 261 |
| 262 if not hasattr(self, 'template'): | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
263 # this won't work |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
264 logging.error("template folder missing!") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
265 return "ERROR: template folder missing!" |
| 22 | 266 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
267 if not getattr(self, 'digilibBaseUrl', None): |
| 132 | 268 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 22 | 269 |
| 548 | 270 # mode=filepath should not have toc-thumbs |
| 271 if tocMode is None: | |
| 272 if mode == "filepath": | |
| 273 tocMode = "none" | |
| 274 else: | |
| 275 tocMode = "thumbs" | |
| 276 | |
| 543 | 277 # docinfo: information about document (cached) |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
278 docinfo = self.getDocinfo(mode=mode,url=url,tocMode=tocMode) |
| 97 | 279 |
| 543 | 280 # userinfo: user settings (cached) |
| 281 userinfo = self.getUserinfo() | |
| 282 | |
| 471 | 283 # auto viewMode: text if there is a text else images |
| 455 | 284 if viewMode=="auto": |
| 530 | 285 if docinfo.get('textURLPath', None): |
| 286 # docinfo.get('textURL', None) not implemented yet | |
| 471 | 287 viewMode = "text" |
| 543 | 288 if viewLayer is None and 'viewLayer' not in userinfo: |
| 289 # use layer dict as default | |
| 508 | 290 viewLayer = "dict" |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
291 else: |
| 590 | 292 viewMode = "image" |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
293 |
| 474 | 294 elif viewMode == "text_dict": |
| 295 # legacy fix | |
| 296 viewMode = "text" | |
| 503 | 297 viewLayer = "dict" |
| 474 | 298 |
| 590 | 299 elif viewMode == 'images': |
| 300 # legacy fix | |
| 301 viewMode = 'image' | |
| 302 self.REQUEST['viewMode'] = 'image' | |
| 303 | |
| 543 | 304 # safe viewLayer in userinfo |
| 305 userinfo['viewLayer'] = viewLayer | |
| 548 | 306 |
| 543 | 307 # pageinfo: information about page (not cached) |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
308 pageinfo = self.getPageinfo(start=start, pn=pn, pf=pf, docinfo=docinfo, userinfo=userinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode) |
| 469 | 309 |
| 475 | 310 # get template /template/viewer_$viewMode |
| 311 pt = getattr(self.template, 'viewer_%s'%viewMode, None) | |
| 312 if pt is None: | |
| 313 logging.error("No template for viewMode=%s!"%viewMode) | |
| 314 # TODO: error page? | |
| 315 return "No template for viewMode=%s!"%viewMode | |
| 316 | |
| 455 | 317 # and execute with parameters |
| 471 | 318 return pt(docinfo=docinfo, pageinfo=pageinfo) |
| 0 | 319 |
| 525 | 320 def getAvailableLayers(self): |
| 321 """returns dict with list of available layers per viewMode""" | |
| 322 return self.availableLayers | |
| 323 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
324 def findDigilibUrl(self): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
325 """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
|
326 url = self.template.zogilib.getDLBaseUrl() |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
327 return url |
| 480 | 328 |
| 329 def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None): | |
| 330 """returns URL to digilib Scaler with params""" | |
| 331 url = None | |
| 332 if docinfo is not None: | |
| 333 url = docinfo.get('imageURL', None) | |
| 334 | |
| 335 if url is None: | |
| 566 | 336 url = self.digilibScalerUrl |
| 480 | 337 if fn is None and docinfo is not None: |
| 338 fn = docinfo.get('imagePath','') | |
| 339 | |
| 340 url += "fn=%s"%fn | |
| 341 | |
| 342 if pn: | |
| 343 url += "&pn=%s"%pn | |
| 344 | |
| 345 url += "&dw=%s&dh=%s"%(dw,dh) | |
| 346 return url | |
| 126 | 347 |
| 348 def getDocumentViewerURL(self): | |
| 349 """returns the URL of this instance""" | |
| 350 return self.absolute_url() | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
351 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
352 def getStyle(self, idx, selected, style=""): |
| 480 | 353 """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
|
354 #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
|
355 if idx == selected: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
356 return style + 'sel' |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
357 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
358 return style |
| 74 | 359 |
| 478 | 360 def getParams(self, param=None, val=None, params=None, duplicates=None): |
| 469 | 361 """returns dict with URL parameters. |
| 362 | |
| 363 Takes URL parameters and additionally param=val or dict params. | |
| 364 Deletes key if value is None.""" | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
365 # copy existing request params |
| 469 | 366 newParams=self.REQUEST.form.copy() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
367 # change single param |
| 25 | 368 if param is not None: |
| 31 | 369 if val is None: |
| 469 | 370 if newParams.has_key(param): |
| 371 del newParams[param] | |
| 25 | 372 else: |
| 469 | 373 newParams[param] = str(val) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
374 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
375 # change more params |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
376 if params is not None: |
| 478 | 377 for (k, v) in params.items(): |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
378 if v is None: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
379 # val=None removes param |
| 469 | 380 if newParams.has_key(k): |
| 381 del newParams[k] | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
382 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
383 else: |
| 469 | 384 newParams[k] = v |
| 478 | 385 |
| 386 if duplicates: | |
| 387 # eliminate lists (coming from duplicate keys) | |
| 388 for (k,v) in newParams.items(): | |
| 389 if isinstance(v, list): | |
| 390 if duplicates == 'comma': | |
| 391 # make comma-separated list of non-empty entries | |
| 392 newParams[k] = ','.join([t for t in v if t]) | |
| 393 elif duplicates == 'first': | |
| 394 # take first non-empty entry | |
| 395 newParams[k] = [t for t in v if t][0] | |
| 396 | |
| 469 | 397 return newParams |
| 398 | |
| 478 | 399 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
| 469 | 400 """returns URL to documentviewer with parameter param set to val or from dict params""" |
| 478 | 401 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
|
402 # quote values and assemble into query string (not escaping '/') |
| 514 | 403 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
|
404 if baseUrl is None: |
| 469 | 405 baseUrl = self.getDocumentViewerURL() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
406 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
407 url = "%s?%s"%(baseUrl, ps) |
| 25 | 408 return url |
| 409 | |
| 478 | 410 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
| 68 | 411 """link to documentviewer with parameter param set to val""" |
| 478 | 412 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
|
413 |
| 526 | 414 |
| 415 def setAvailableLayers(self, newLayerString=None): | |
| 416 """sets availableLayers to newLayerString or tries to autodetect available layers. | |
| 417 assumes layer templates have the form layer_{m}_{l} for layer l in mode m. | |
| 418 newLayerString is parsed as JSON.""" | |
| 419 if newLayerString is not None: | |
| 420 try: | |
| 421 layers = json.loads(newLayerString) | |
| 590 | 422 if 'text' in layers and 'image' in layers: |
| 526 | 423 self.availableLayers = layers |
| 424 return | |
| 425 except: | |
| 426 pass | |
| 427 | |
| 428 logging.error("invalid layers=%s! autodetecting..."%repr(newLayerString)) | |
| 429 | |
| 430 # start with builtin layers | |
| 431 self.availableLayers = self.builtinLayers.copy() | |
| 432 # add layers from templates | |
| 433 for t in self.template: | |
| 434 if t.startswith('layer_'): | |
| 435 try: | |
| 436 (x, m, l) = t.split('_', 3) | |
| 437 if m not in self.availableLayers: | |
| 438 # mode m doesn't exist -> new list | |
| 439 self.availableLayers[m] = [l] | |
| 440 | |
| 441 else: | |
| 442 # m exists -> append | |
| 443 if l not in self.availableLayers[m]: | |
| 444 self.availableLayers[m].append() | |
| 445 | |
| 446 except: | |
| 447 pass | |
| 448 | |
| 449 def getAvailableLayersJson(self): | |
| 450 """returns available layers as JSON string.""" | |
| 451 return json.dumps(self.availableLayers) | |
| 452 | |
| 469 | 453 |
| 57 | 454 def getInfo_xml(self,url,mode): |
| 455 """returns info about the document as XML""" | |
| 456 if not self.digilibBaseUrl: | |
| 514 | 457 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 57 | 458 |
| 459 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 460 pt = getattr(self.template, 'info_xml') | |
| 461 return pt(docinfo=docinfo) | |
| 462 | |
| 528 | 463 def getAuthenticatedUser(self, anon=None): |
| 464 """returns the authenticated user object or None. (ignores Zopes anonymous user)""" | |
| 465 user = getSecurityManager().getUser() | |
| 466 if user is not None and user.getUserName() != "Anonymous User": | |
| 467 return user | |
| 468 else: | |
| 469 return anon | |
| 470 | |
| 35 | 471 def isAccessible(self, docinfo): |
| 32 | 472 """returns if access to the resource is granted""" |
| 473 access = docinfo.get('accessType', None) | |
| 167 | 474 logging.debug("documentViewer (accessOK) access type %s"%access) |
| 465 | 475 if access == 'free': |
| 167 | 476 logging.debug("documentViewer (accessOK) access is free") |
| 32 | 477 return True |
| 465 | 478 |
| 45 | 479 elif access is None or access in self.authgroups: |
| 35 | 480 # only local access -- only logged in users |
| 528 | 481 user = self.getAuthenticatedUser() |
| 167 | 482 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
| 528 | 483 return (user is not None) |
| 32 | 484 |
| 167 | 485 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
| 32 | 486 return False |
| 464 | 487 |
| 543 | 488 def getUserinfo(self): |
| 489 """returns userinfo object""" | |
| 490 logging.debug("getUserinfo") | |
| 491 userinfo = {} | |
| 492 # look for cached userinfo in session | |
| 493 if self.REQUEST.SESSION.has_key('userinfo'): | |
| 494 userinfo = self.REQUEST.SESSION['userinfo'] | |
| 495 # check if its still current? | |
| 496 else: | |
| 497 # store in session | |
| 498 self.REQUEST.SESSION['userinfo'] = userinfo | |
| 499 | |
| 500 return userinfo | |
| 501 | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
502 def getDocinfo(self, mode, url, tocMode=None): |
| 464 | 503 """returns docinfo depending on mode""" |
| 504 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) | |
| 505 # look for cached docinfo in session | |
| 506 if self.REQUEST.SESSION.has_key('docinfo'): | |
| 507 docinfo = self.REQUEST.SESSION['docinfo'] | |
| 508 # check if its still current | |
| 509 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: | |
| 510 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
| 511 return docinfo | |
| 512 | |
| 513 # new docinfo | |
| 514 docinfo = {'mode': mode, 'url': url} | |
| 515 # add self url | |
| 516 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
| 477 | 517 docinfo['digilibBaseUrl'] = self.digilibBaseUrl |
| 566 | 518 docinfo['digilibScalerUrl'] = self.digilibScalerUrl |
| 519 docinfo['digilibViewerUrl'] = self.digilibViewerUrl | |
| 464 | 520 # get index.meta DOM |
| 521 docUrl = None | |
| 522 metaDom = None | |
| 523 if mode=="texttool": | |
| 524 # url points to document dir or index.meta | |
| 525 metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
| 526 if metaDom is None: | |
| 527 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
|
528 |
|
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
529 docUrl = url.replace('/index.meta', '') |
|
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
530 if url.startswith('/mpiwg/online/'): |
|
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
531 docUrl = url.replace('/mpiwg/online/', '', 1) |
| 464 | 532 |
| 533 elif mode=="imagepath": | |
| 534 # url points to folder with images, index.meta optional | |
| 535 # asssume index.meta in parent dir | |
| 536 docUrl = getParentPath(url) | |
| 537 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 599 | 538 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
| 464 | 539 |
| 540 elif mode=="filepath": | |
| 541 # url points to image file, index.meta optional | |
| 566 | 542 docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, url) |
| 548 | 543 docinfo['numPages'] = 1 |
| 464 | 544 # asssume index.meta is two path segments up |
| 545 docUrl = getParentPath(url, 2) | |
| 546 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 547 | |
| 548 else: | |
| 549 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
| 550 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
| 551 | |
| 552 docinfo['documentUrl'] = docUrl | |
| 553 # process index.meta contents | |
| 473 | 554 if metaDom is not None and metaDom.tag == 'resource': |
| 464 | 555 # document directory name and path |
| 556 resource = self.metadataService.getResourceData(dom=metaDom) | |
| 557 if resource: | |
| 558 docinfo = self.getDocinfoFromResource(docinfo, resource) | |
| 559 | |
| 560 # texttool info | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
561 texttool = self.metadataService.getTexttoolData(dom=metaDom, recursive=1, all=True) |
| 464 | 562 if texttool: |
| 563 docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
| 568 | 564 # document info from full text server |
| 516 | 565 if docinfo.get('textURLPath', None): |
| 565 | 566 docinfo = self.getTextInfo(mode=None, docinfo=docinfo) |
| 568 | 567 # include list of pages TODO: do we need this always? |
| 568 docinfo = self.getTextInfo(mode='pages', docinfo=docinfo) | |
| 464 | 569 |
| 570 # bib info | |
| 571 bib = self.metadataService.getBibData(dom=metaDom) | |
| 572 if bib: | |
| 548 | 573 # save extended version as 'bibx' TODO: ugly |
| 541 | 574 bibx = self.metadataService.getBibData(dom=metaDom, all=True, recursive=1) |
| 575 if len(bibx) == 1: | |
| 576 # unwrap list if possible | |
| 577 bibx = bibx[0] | |
| 578 | |
| 579 docinfo['bibx'] = bibx | |
| 580 docinfo = self.getDocinfoFromBib(docinfo, bib, bibx) | |
| 465 | 581 else: |
| 582 # no bib - try info.xml | |
| 583 docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) | |
| 464 | 584 |
| 585 # auth info | |
| 586 access = self.metadataService.getAccessData(dom=metaDom) | |
| 587 if access: | |
| 588 docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 589 | |
| 466 | 590 # attribution info |
| 591 attribution = self.metadataService.getAttributionData(dom=metaDom) | |
| 592 if attribution: | |
| 593 logging.debug("getDocinfo: attribution=%s"%repr(attribution)) | |
| 594 docinfo['attribution'] = attribution | |
| 595 | |
| 596 # copyright info | |
| 597 copyright = self.metadataService.getCopyrightData(dom=metaDom) | |
| 598 if copyright: | |
| 599 logging.debug("getDocinfo: copyright=%s"%repr(copyright)) | |
| 600 docinfo['copyright'] = copyright | |
| 538 | 601 |
| 602 # DRI (permanent ID) | |
| 581 | 603 dri = self.metadataService.getDRI(dom=metaDom, type='mpiwg') |
| 538 | 604 if dri: |
| 605 docinfo['DRI'] = dri | |
| 466 | 606 |
| 578 | 607 # (presentation) context |
| 608 ctx = self.metadataService.getContextData(dom=metaDom, all=True) | |
| 609 if ctx: | |
| 610 logging.debug("getcontext: ctx=%s"%repr(ctx)) | |
| 611 docinfo['presentationContext'] = ctx | |
| 612 | |
| 464 | 613 # image path |
| 614 if mode != 'texttool': | |
| 532 | 615 # override image path from texttool with url parameter TODO: how about mode=auto? |
| 599 | 616 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
| 464 | 617 |
| 548 | 618 # check numPages |
| 619 if docinfo.get('numPages', 0) == 0: | |
| 620 # number of images from digilib | |
| 621 if docinfo.get('imagePath', None): | |
| 599 | 622 imgpath = docinfo['imagePath'].replace('/mpiwg/online', '', 1) |
|
580
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
623 logging.debug("imgpath=%s"%imgpath) |
| 566 | 624 docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, imgpath) |
| 562 | 625 docinfo = self.getDocinfoFromDigilib(docinfo, imgpath) |
| 548 | 626 else: |
| 627 # imagePath still missing? try "./pageimg" | |
| 628 imgPath = os.path.join(docUrl, 'pageimg') | |
| 629 docinfo = self.getDocinfoFromDigilib(docinfo, imgPath) | |
| 630 if docinfo.get('numPages', 0) > 0: | |
| 631 # there are pages | |
| 632 docinfo['imagePath'] = imgPath | |
| 566 | 633 docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, docinfo['imagePath']) |
| 464 | 634 |
| 516 | 635 # check numPages |
| 636 if docinfo.get('numPages', 0) == 0: | |
| 637 if docinfo.get('numTextPages', 0) > 0: | |
| 638 # replace with numTextPages (text-only?) | |
| 639 docinfo['numPages'] = docinfo['numTextPages'] | |
| 640 | |
| 599 | 641 # normalize path |
| 642 if 'imagePath' in docinfo and not docinfo['imagePath'].startswith('/'): | |
| 643 docinfo['imagePath'] = '/' + docinfo['imagePath'] | |
| 644 | |
| 464 | 645 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
| 646 # store in session | |
| 647 self.REQUEST.SESSION['docinfo'] = docinfo | |
| 648 return docinfo | |
| 649 | |
| 516 | 650 |
| 464 | 651 def getDocinfoFromResource(self, docinfo, resource): |
| 652 """reads contents of resource element into docinfo""" | |
| 653 docName = resource.get('name', None) | |
| 654 docinfo['documentName'] = docName | |
| 655 docPath = resource.get('archive-path', None) | |
| 656 if docPath: | |
| 657 # clean up document path | |
| 658 if docPath[0] != '/': | |
| 659 docPath = '/' + docPath | |
| 660 | |
| 661 if docName and (not docPath.endswith(docName)): | |
| 662 docPath += "/" + docName | |
| 663 | |
| 664 else: | |
| 665 # use docUrl as docPath | |
| 666 docUrl = docinfo['documentURL'] | |
| 667 if not docUrl.startswith('http:'): | |
| 668 docPath = docUrl | |
| 465 | 669 if docPath: |
| 670 # fix URLs starting with /mpiwg/online | |
| 671 docPath = docPath.replace('/mpiwg/online', '', 1) | |
| 672 | |
| 464 | 673 docinfo['documentPath'] = docPath |
| 674 return docinfo | |
| 675 | |
| 676 def getDocinfoFromTexttool(self, docinfo, texttool): | |
| 677 """reads contents of texttool element into docinfo""" | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
678 logging.debug("texttool=%s"%repr(texttool)) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
679 # unpack list if necessary |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
680 if isinstance(texttool, list): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
681 texttool = texttool[0] |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
682 |
| 464 | 683 # image dir |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
684 imageDir = getMDText(texttool.get('image', None)) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
685 docPath = getMDText(docinfo.get('documentPath', None)) |
| 464 | 686 if imageDir and docPath: |
| 687 imageDir = os.path.join(docPath, imageDir) | |
| 688 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
| 689 docinfo['imagePath'] = imageDir | |
| 690 | |
| 691 # old style text URL | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
692 textUrl = getMDText(texttool.get('text', None)) |
| 464 | 693 if textUrl and docPath: |
| 694 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
| 695 textUrl = os.path.join(docPath, textUrl) | |
| 696 | |
| 697 docinfo['textURL'] = textUrl | |
| 698 | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
699 # 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
|
700 textUrlNode = texttool.get('text-url-path', None) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
701 if not isinstance(textUrlNode, list): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
702 textUrlNode = [textUrlNode] |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
703 |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
704 for tun in textUrlNode: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
705 textUrl = getMDText(tun) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
706 if textUrl: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
707 textUrlAtts = tun.get('@attr') |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
708 if (textUrlAtts and 'repository' in textUrlAtts): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
709 textRepo = textUrlAtts['repository'] |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
710 # use matching repository |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
711 if self.getRepositoryType() == textRepo: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
712 docinfo['textURLPath'] = textUrl |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
713 docinfo['textURLRepository'] = textRepo |
| 564 | 714 break |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
715 |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
716 else: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
717 # no repo attribute - use always |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
718 docinfo['textURLPath'] = textUrl |
| 468 | 719 |
| 720 # page flow | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
721 docinfo['pageFlow'] = getMDText(texttool.get('page-flow', 'ltr')) |
| 468 | 722 |
| 723 # odd pages are left | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
724 docinfo['oddPage'] = getMDText(texttool.get('odd-scan-position', 'left')) |
| 468 | 725 |
| 541 | 726 # number of title page (default 1) |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
727 docinfo['titlePage'] = getMDText(texttool.get('title-scan-no', 1)) |
| 464 | 728 |
| 729 # old presentation stuff | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
730 presentation = getMDText(texttool.get('presentation', None)) |
| 464 | 731 if presentation and docPath: |
| 465 | 732 if presentation.startswith('http:'): |
| 733 docinfo['presentationUrl'] = presentation | |
| 734 else: | |
| 735 docinfo['presentationUrl'] = os.path.join(docPath, presentation) | |
| 468 | 736 |
| 464 | 737 return docinfo |
| 738 | |
| 541 | 739 def getDocinfoFromBib(self, docinfo, bib, bibx=None): |
| 464 | 740 """reads contents of bib element into docinfo""" |
| 465 | 741 logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
| 464 | 742 # put all raw bib fields in dict "bib" |
| 743 docinfo['bib'] = bib | |
| 744 bibtype = bib.get('@type', None) | |
| 745 docinfo['bibType'] = bibtype | |
| 746 # also store DC metadata for convenience | |
| 747 dc = self.metadataService.getDCMappedData(bib) | |
|
536
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
748 docinfo['creator'] = dc.get('creator','') |
|
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
749 docinfo['title'] = dc.get('title','') |
|
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
750 docinfo['date'] = dc.get('date','') |
| 464 | 751 return docinfo |
| 752 | |
| 753 def getDocinfoFromAccess(self, docinfo, acc): | |
| 754 """reads contents of access element into docinfo""" | |
| 755 #TODO: also read resource type | |
| 465 | 756 logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
| 464 | 757 try: |
| 465 | 758 acctype = acc['@attr']['type'] |
| 464 | 759 if acctype: |
| 760 access=acctype | |
| 761 if access in ['group', 'institution']: | |
| 762 access = acc['name'].lower() | |
| 763 | |
| 764 docinfo['accessType'] = access | |
| 765 | |
| 766 except: | |
| 767 pass | |
| 768 | |
| 769 return docinfo | |
| 770 | |
| 771 def getDocinfoFromDigilib(self, docinfo, path): | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
772 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?fn="+path |
| 464 | 773 # fetch data |
| 774 txt = getHttpData(infoUrl) | |
| 775 if not txt: | |
| 776 logging.error("Unable to get dir-info from %s"%(infoUrl)) | |
| 777 return docinfo | |
| 778 | |
| 779 dom = ET.fromstring(txt) | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
780 dir = dom |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
781 # save size |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
782 size = dir.findtext('size') |
| 464 | 783 logging.debug("getDocinfoFromDigilib: size=%s"%size) |
| 784 if size: | |
| 785 docinfo['numPages'] = int(size) | |
| 786 else: | |
| 787 docinfo['numPages'] = 0 | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
788 return docinfo |
| 464 | 789 |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
790 # save list of image names and numbers |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
791 imgNames = {} |
| 591 | 792 imgIndexes = {} |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
793 for f in dir: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
794 fn = f.findtext('name') |
| 591 | 795 pn = getInt(f.findtext('index')) |
| 796 imgNames[fn] = pn | |
| 797 imgIndexes[pn] = fn | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
798 |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
799 docinfo['imgFileNames'] = imgNames |
| 591 | 800 docinfo['imgFileIndexes'] = imgIndexes |
| 464 | 801 return docinfo |
| 802 | |
| 803 | |
| 465 | 804 def getDocinfoFromPresentationInfoXml(self,docinfo): |
| 805 """gets DC-like bibliographical information from the presentation entry in texttools""" | |
| 806 url = docinfo.get('presentationUrl', None) | |
| 807 if not url: | |
| 808 logging.error("getDocinfoFromPresentation: no URL!") | |
| 809 return docinfo | |
| 810 | |
| 811 dom = None | |
| 812 metaUrl = None | |
| 813 if url.startswith("http://"): | |
| 814 # real URL | |
| 815 metaUrl = url | |
| 816 else: | |
| 817 # online path | |
| 818 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 819 metaUrl=server+url | |
| 820 | |
| 821 txt=getHttpData(metaUrl) | |
| 822 if txt is None: | |
| 823 logging.error("Unable to read info.xml from %s"%(url)) | |
| 824 return docinfo | |
| 825 | |
| 826 dom = ET.fromstring(txt) | |
| 827 docinfo['creator']=getText(dom.find(".//author")) | |
| 828 docinfo['title']=getText(dom.find(".//title")) | |
| 829 docinfo['date']=getText(dom.find(".//date")) | |
| 830 return docinfo | |
| 831 | |
| 832 | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
833 def getPageinfo(self, pn=None, pf=None, start=None, rows=None, cols=None, docinfo=None, userinfo=None, viewMode=None, viewLayer=None, tocMode=None): |
| 22 | 834 """returns pageinfo with the given parameters""" |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
835 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 | 836 pageinfo = {} |
| 471 | 837 pageinfo['viewMode'] = viewMode |
| 508 | 838 # split viewLayer if necessary |
| 839 if isinstance(viewLayer,basestring): | |
| 840 viewLayer = viewLayer.split(',') | |
| 841 | |
| 842 if isinstance(viewLayer, list): | |
| 843 logging.debug("getPageinfo: viewLayer is list:%s"%viewLayer) | |
| 844 # save (unique) list in viewLayers | |
| 845 seen = set() | |
| 846 viewLayers = [l for l in viewLayer if l and l not in seen and not seen.add(l)] | |
| 847 pageinfo['viewLayers'] = viewLayers | |
| 848 # stringify viewLayer | |
| 849 viewLayer = ','.join(viewLayers) | |
| 850 else: | |
| 851 #create list | |
| 852 pageinfo['viewLayers'] = [viewLayer] | |
| 853 | |
| 503 | 854 pageinfo['viewLayer'] = viewLayer |
| 471 | 855 pageinfo['tocMode'] = tocMode |
| 856 | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
857 # pf takes precedence over pn |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
858 if pf: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
859 pageinfo['pf'] = pf |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
860 pn = getPnForPf(docinfo, pf) |
| 589 | 861 # replace pf in request params (used for creating new URLs) |
| 862 self.REQUEST.form.pop('pf', None) | |
| 863 self.REQUEST.form['pn'] = pn | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
864 else: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
865 pn = getInt(pn, 1) |
| 591 | 866 pf = getPfForPn(docinfo, pn) |
| 867 pageinfo['pf'] = pf | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
868 |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
869 pageinfo['pn'] = pn |
| 25 | 870 rows = int(rows or self.thumbrows) |
| 871 pageinfo['rows'] = rows | |
| 872 cols = int(cols or self.thumbcols) | |
| 873 pageinfo['cols'] = cols | |
| 874 grpsize = cols * rows | |
| 875 pageinfo['groupsize'] = grpsize | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
876 # is start is empty use one around pn |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
877 start = getInt(start, default=(math.ceil(float(pn)/float(grpsize))*grpsize-(grpsize-1))) |
| 61 | 878 # int(current / grpsize) * grpsize +1)) |
| 22 | 879 pageinfo['start'] = start |
| 511 | 880 # get number of pages |
| 469 | 881 np = int(docinfo.get('numPages', 0)) |
| 882 if np == 0: | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
883 # try numTextPages |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
884 np = docinfo.get('numTextPages', 0) |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
885 if np != 0: |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
886 docinfo['numPages'] = np |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
887 |
| 511 | 888 # cache table of contents |
| 889 pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) | |
| 469 | 890 pageinfo['numgroups'] = int(np / grpsize) |
| 891 if np % grpsize > 0: | |
| 892 pageinfo['numgroups'] += 1 | |
| 476 | 893 |
| 894 pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' | |
| 895 oddScanLeft = docinfo.get('oddPage', 'left') != 'right' | |
| 896 # add zeroth page for two columns | |
| 897 pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) | |
| 898 pageinfo['pageZero'] = pageZero | |
| 480 | 899 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np) |
| 516 | 900 # more page parameters |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
901 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
| 516 | 902 if docinfo.get('pageNumbers'): |
| 903 # get original page numbers | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
904 pageNumber = docinfo['pageNumbers'].get(pn, None) |
| 516 | 905 if pageNumber is not None: |
| 906 pageinfo['pageNumberOrig'] = pageNumber['no'] | |
| 907 pageinfo['pageNumberOrigNorm'] = pageNumber['non'] | |
| 158 | 908 |
| 511 | 909 # cache search results |
| 910 query = self.REQUEST.get('query',None) | |
| 911 pageinfo['query'] = query | |
| 591 | 912 if query and viewMode == 'text': |
| 913 pageinfo['resultPageSize'] = getInt(self.REQUEST.get('resultPageSize', 10)) | |
| 511 | 914 queryType = self.REQUEST.get('queryType', 'fulltextMorph') |
| 915 pageinfo['queryType'] = queryType | |
| 916 pageinfo['resultStart'] = getInt(self.REQUEST.get('resultStart', '1')) | |
| 917 self.getSearchResults(mode=queryType, query=query, pageinfo=pageinfo, docinfo=docinfo) | |
| 918 | |
| 919 # highlighting | |
| 920 highlightQuery = self.REQUEST.get('highlightQuery', None) | |
| 921 if highlightQuery: | |
| 922 pageinfo['highlightQuery'] = highlightQuery | |
| 923 pageinfo['highlightElement'] = self.REQUEST.get('highlightElement', '') | |
| 924 pageinfo['highlightElementPos'] = self.REQUEST.get('highlightElementPos', '') | |
| 460 | 925 |
| 22 | 926 return pageinfo |
| 460 | 927 |
| 463 | 928 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
929 def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0): |
| 591 | 930 """returns dict with array of page information for one screenfull of thumbnails""" |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
931 batch = {} |
| 480 | 932 grpsize = rows * cols |
| 476 | 933 if maxIdx == 0: |
| 480 | 934 maxIdx = start + grpsize |
| 476 | 935 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
936 nb = int(math.ceil(maxIdx / float(grpsize))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
937 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
938 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
939 if pageZero: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
940 ofs = 0 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
941 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
942 ofs = 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
943 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
944 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
945 s = i * grpsize + ofs |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
946 e = min((i + 1) * grpsize + ofs - 1, maxIdx) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
947 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
948 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
949 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
950 |
| 476 | 951 pages = [] |
| 952 if pageZero and start == 1: | |
| 953 # correct beginning | |
| 954 idx = 0 | |
| 955 else: | |
| 956 idx = start | |
| 957 | |
| 958 for r in range(rows): | |
| 959 row = [] | |
| 960 for c in range(cols): | |
| 961 if idx < minIdx or idx > maxIdx: | |
| 962 page = {'idx':None} | |
| 963 else: | |
| 964 page = {'idx':idx} | |
| 965 | |
| 966 idx += 1 | |
| 967 if pageFlowLtr: | |
| 968 row.append(page) | |
| 969 else: | |
| 970 row.insert(0, page) | |
| 971 | |
| 972 pages.append(row) | |
| 973 | |
| 480 | 974 if start > 1: |
| 975 batch['prevStart'] = max(start - grpsize, 1) | |
| 976 else: | |
| 977 batch['prevStart'] = None | |
| 978 | |
| 526 | 979 if start + grpsize <= maxIdx: |
| 480 | 980 batch['nextStart'] = start + grpsize |
| 981 else: | |
| 982 batch['nextStart'] = None | |
| 983 | |
| 984 batch['pages'] = pages | |
| 571 | 985 batch['first'] = minIdx |
| 986 batch['last'] = maxIdx | |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
987 return batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
988 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
989 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
|
990 """returns dict with information for one screenfull of data.""" |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
991 batch = {} |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
992 if end == 0: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
993 end = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
994 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
995 nb = int(math.ceil(end / float(size))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
996 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
997 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
998 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
999 s = i * size + 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1000 e = min((i + 1) * size, end) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1001 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1002 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1003 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1004 # list of elements in this batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1005 this = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1006 j = 0 |
| 526 | 1007 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
|
1008 if data: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1009 if fullData: |
| 526 | 1010 d = data.get(i, None) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1011 else: |
| 526 | 1012 d = data.get(j, None) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1013 j += 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1014 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1015 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1016 d = i+1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1017 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1018 this.append(d) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1019 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1020 batch['this'] = this |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1021 if start > 1: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1022 batch['prevStart'] = max(start - size, 1) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1023 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1024 batch['prevStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1025 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1026 if start + size < end: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1027 batch['nextStart'] = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1028 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1029 batch['nextStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1030 |
| 571 | 1031 batch['first'] = start |
| 1032 batch['last'] = end | |
| 480 | 1033 return batch |
| 476 | 1034 |
| 1035 | |
| 546 | 1036 def getAnnotatorGroupsForUser(self, user, annotationServerUrl="http://tuxserve03.mpiwg-berlin.mpg.de/AnnotationManager"): |
| 1037 """returns list of groups {name:*, id:*} on the annotation server for the user""" | |
| 1038 groups = [] | |
| 1039 groupsUrl = "%s/annotator/groups?user=%s"%(annotationServerUrl,user) | |
| 1040 data = getHttpData(url=groupsUrl, noExceptions=True) | |
| 1041 if data: | |
| 1042 res = json.loads(data) | |
| 1043 rows = res.get('rows', None) | |
| 1044 if rows is None: | |
| 1045 return groups | |
| 1046 for r in rows: | |
| 1047 groups.append({'id': r.get('id', None), 'name': r.get('name', None), 'uri': r.get('uri', None)}) | |
| 1048 | |
| 1049 return groups | |
| 1050 | |
| 1051 | |
| 463 | 1052 security.declareProtected('View management screens','changeDocumentViewerForm') |
| 1053 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 22 | 1054 |
| 526 | 1055 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',availableLayers=None,RESPONSE=None): |
| 22 | 1056 """init document viewer""" |
| 1057 self.title=title | |
| 1058 self.digilibBaseUrl = digilibBaseUrl | |
| 566 | 1059 self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
| 1060 self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' | |
| 25 | 1061 self.thumbrows = thumbrows |
| 1062 self.thumbcols = thumbcols | |
| 32 | 1063 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| 463 | 1064 try: |
| 1065 # assume MetaDataFolder instance is called metadata | |
| 1066 self.metadataService = getattr(self, 'metadata') | |
| 1067 except Exception, e: | |
| 1068 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 526 | 1069 |
| 1070 self.setAvailableLayers(availableLayers) | |
| 463 | 1071 |
| 22 | 1072 if RESPONSE is not None: |
| 1073 RESPONSE.redirect('manage_main') | |
| 0 | 1074 |
| 1075 def manage_AddDocumentViewerForm(self): | |
| 1076 """add the viewer form""" | |
| 22 | 1077 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| 0 | 1078 return pt() |
| 1079 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1080 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
| 0 | 1081 """add the viewer""" |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1082 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
| 0 | 1083 self._setObject(id,newObj) |
| 1084 | |
| 1085 if RESPONSE is not None: | |
| 1086 RESPONSE.redirect('manage_main') |