Mercurial > hg > documentViewer
annotate documentViewer.py @ 622:bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
| author | casties |
|---|---|
| date | Fri, 12 Dec 2014 16:27:58 +0100 |
| parents | 54d3498a6e78 |
| children | 6012fe93f78c |
| 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 | |
| 514 | 19 from SrvTxtUtils import getInt, utf8ify, getText, getHttpData, refreshingImageFileIndexHtml |
| 52 | 20 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
21 |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
22 def getMDText(node): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
23 """returns the @text content from the MetaDataProvider metadata node""" |
| 617 | 24 |
| 25 | |
| 26 | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
27 if isinstance(node, dict): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
28 return node.get('@text', None) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
29 |
| 617 | 30 if isinstance(node,list): #more than one text file if there is an attribute don't choose it |
| 31 for nodeInList in node: | |
| 32 attr = nodeInList.get("@attr",None) | |
| 33 if attr is None: | |
| 34 return node.get('@text',None) | |
| 35 return None | |
| 36 | |
| 37 | |
| 38 | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
39 return node |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
40 |
| 464 | 41 def getParentPath(path, cnt=1): |
| 42 """returns pathname shortened by cnt""" | |
| 43 # make sure path doesn't end with / | |
| 44 path = path.rstrip('/') | |
| 45 # split by /, shorten, and reassemble | |
| 46 return '/'.join(path.split('/')[0:-cnt]) | |
| 47 | |
| 589 | 48 def getPnForPf(docinfo, pf, default=0): |
| 49 """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
|
50 if 'imgFileNames' in docinfo: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
51 pn = docinfo['imgFileNames'].get(pf, None) |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
52 if pn is None: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
53 # try to cut extension |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
54 xi = pf.rfind('.') |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
55 if xi > 0: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
56 pf = pf[:xi] |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
57 # try again, else return 0 |
| 589 | 58 pn = docinfo['imgFileNames'].get(pf, default) |
| 59 else: | |
| 60 # no extension | |
| 61 pn = default | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
62 |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
63 return pn |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
64 |
| 589 | 65 return default |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
66 |
| 591 | 67 def getPfForPn(docinfo, pn, default=None): |
| 68 """returns image file name for image number or default""" | |
| 69 if 'imgFileIndexes' in docinfo: | |
| 70 pn = docinfo['imgFileIndexes'].get(pn, default) | |
| 71 return pn | |
| 72 | |
| 73 return default | |
| 74 | |
| 585 | 75 |
| 22 | 76 ## |
| 77 ## documentViewer class | |
| 78 ## | |
| 79 class documentViewer(Folder): | |
| 0 | 80 """document viewer""" |
| 81 meta_type="Document viewer" | |
| 82 | |
| 83 security=ClassSecurityInfo() | |
| 22 | 84 manage_options=Folder.manage_options+( |
| 507 | 85 {'label':'Configuration','action':'changeDocumentViewerForm'}, |
| 0 | 86 ) |
| 463 | 87 |
| 88 metadataService = None | |
| 89 """MetaDataFolder instance""" | |
| 525 | 90 |
| 0 | 91 |
| 525 | 92 # |
| 22 | 93 # templates and forms |
| 525 | 94 # |
| 95 # viewMode templates | |
| 594 | 96 viewer_text = PageTemplateFile('zpt/viewer/viewer_text', globals()) |
|
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
97 viewer_hocr = PageTemplateFile('zpt/viewer/viewer_hocr', globals()) |
| 594 | 98 viewer_xml = PageTemplateFile('zpt/viewer/viewer_xml', globals()) |
| 99 viewer_image = PageTemplateFile('zpt/viewer/viewer_image', globals()) | |
| 100 viewer_index = PageTemplateFile('zpt/viewer/viewer_index', globals()) | |
| 101 viewer_thumbs = PageTemplateFile('zpt/viewer/viewer_thumbs', globals()) | |
| 102 viewer_indexonly = PageTemplateFile('zpt/viewer/viewer_indexonly', globals()) | |
| 546 | 103 # available layer types (annotator not default) |
| 104 builtinLayers = {'text': ['dict','search','gis'], | |
| 590 | 105 'xml': None, 'image': None, 'index': ['extended']} |
| 526 | 106 availableLayers = builtinLayers; |
| 525 | 107 # layer templates |
| 594 | 108 layer_text_dict = PageTemplateFile('zpt/viewer/layer_text_dict', globals()) |
| 109 layer_text_search = PageTemplateFile('zpt/viewer/layer_text_search', globals()) | |
| 110 layer_text_annotator = PageTemplateFile('zpt/viewer/layer_text_annotator', globals()) | |
| 111 layer_text_gis = PageTemplateFile('zpt/viewer/layer_text_gis', globals()) | |
| 112 layer_text_pundit = PageTemplateFile('zpt/viewer/layer_text_pundit', globals()) | |
| 113 layer_image_annotator = PageTemplateFile('zpt/viewer/layer_image_annotator', globals()) | |
| 114 layer_image_search = PageTemplateFile('zpt/viewer/layer_image_search', globals()) | |
| 115 layer_index_extended = PageTemplateFile('zpt/viewer/layer_index_extended', globals()) | |
| 525 | 116 # toc templates |
| 594 | 117 toc_thumbs = PageTemplateFile('zpt/viewer/toc_thumbs', globals()) |
| 118 toc_text = PageTemplateFile('zpt/viewer/toc_text', globals()) | |
| 119 toc_figures = PageTemplateFile('zpt/viewer/toc_figures', globals()) | |
| 120 toc_concordance = PageTemplateFile('zpt/viewer/toc_concordance', globals()) | |
| 609 | 121 toc_notes = PageTemplateFile('zpt/viewer/toc_notes', globals()) |
| 594 | 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: |
| 607 | 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""" |
|
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
180 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
181 return self.template.fulltextclient.getTextPage(**args) |
|
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
182 |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
183 |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
184 |
| 22 | 185 |
| 508 | 186 def getSearchResults(self, **args): |
| 187 """loads list of search results and stores XML in docinfo""" | |
| 188 return self.template.fulltextclient.getSearchResults(**args) | |
| 189 | |
| 190 def getResultsPage(self, **args): | |
| 191 """returns one page of the search results""" | |
| 192 return self.template.fulltextclient.getResultsPage(**args) | |
| 193 | |
| 516 | 194 def getTextInfo(self, **args): |
| 195 """returns document info from the text server""" | |
| 196 return self.template.fulltextclient.getTextInfo(**args) | |
| 197 | |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
198 def getToc(self, **args): |
| 508 | 199 """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
|
200 return self.template.fulltextclient.getToc(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
201 |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
202 def getTocPage(self, **args): |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
203 """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
|
204 return self.template.fulltextclient.getTocPage(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
205 |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
206 def getRepositoryType(self, **args): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
207 """get repository type""" |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
208 return self.template.fulltextclient.getRepositoryType(**args) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
209 |
| 559 | 210 def getTextDownloadUrl(self, **args): |
| 610 | 211 """get URL to download the full text""" |
| 559 | 212 return self.template.fulltextclient.getTextDownloadUrl(**args) |
| 213 | |
| 506 | 214 def getPlacesOnPage(self, **args): |
| 215 """get list of gis places on one page""" | |
| 216 return self.template.fulltextclient.getPlacesOnPage(**args) | |
| 307 | 217 |
| 548 | 218 # Thumb list for CoolIris Plugin |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
219 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
| 68 | 220 security.declareProtected('View','thumbs_rss') |
| 221 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
| 222 ''' | |
| 223 view it | |
| 224 @param mode: defines how to access the document behind url | |
| 225 @param url: url which contains display information | |
| 590 | 226 @param viewMode: image: display images, text: display text, default is auto (try text, else image) |
| 68 | 227 |
| 228 ''' | |
| 229 | |
| 230 if not hasattr(self, 'template'): | |
| 590 | 231 # this won't work |
| 232 logging.error("template folder missing!") | |
| 233 return "ERROR: template folder missing!" | |
| 234 | |
| 68 | 235 if not self.digilibBaseUrl: |
| 236 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 237 | |
| 238 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 338 | 239 #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
|
240 pageinfo = self.getPageinfo(start=start,pn=pn, docinfo=docinfo) |
| 331 | 241 ''' ZDES ''' |
| 68 | 242 pt = getattr(self.template, 'thumbs_main_rss') |
| 243 | |
| 244 if viewMode=="auto": # automodus gewaehlt | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
245 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
| 68 | 246 viewMode="text" |
| 247 else: | |
| 590 | 248 viewMode="image" |
| 68 | 249 |
| 250 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
| 465 | 251 |
| 68 | 252 |
| 22 | 253 security.declareProtected('View','index_html') |
| 589 | 254 def index_html(self, url, mode="texttool", viewMode="auto", viewLayer=None, tocMode=None, start=None, pn=None, pf=None): |
| 464 | 255 """ |
| 543 | 256 show page |
| 471 | 257 @param url: url which contains display information |
| 57 | 258 @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
|
259 @param viewMode: 'image': display images, 'text': display text, 'xml': display xml, default is 'auto', 'hocr' : hocr format |
| 543 | 260 @param viewLayer: sub-type of viewMode, e.g. layer 'dict' for viewMode='text' |
| 99 | 261 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
| 464 | 262 """ |
| 0 | 263 |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
264 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 | 265 |
| 266 if not hasattr(self, 'template'): | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
267 # this won't work |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
268 logging.error("template folder missing!") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
269 return "ERROR: template folder missing!" |
| 617 | 270 |
| 271 | |
| 272 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
273 if not getattr(self, 'digilibBaseUrl', None): |
| 132 | 274 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 22 | 275 |
| 548 | 276 # mode=filepath should not have toc-thumbs |
| 277 if tocMode is None: | |
| 278 if mode == "filepath": | |
| 279 tocMode = "none" | |
| 280 else: | |
| 281 tocMode = "thumbs" | |
| 282 | |
| 543 | 283 # docinfo: information about document (cached) |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
284 docinfo = self.getDocinfo(mode=mode,url=url,tocMode=tocMode) |
| 97 | 285 |
| 543 | 286 # userinfo: user settings (cached) |
| 287 userinfo = self.getUserinfo() | |
| 288 | |
| 471 | 289 # auto viewMode: text if there is a text else images |
| 455 | 290 if viewMode=="auto": |
| 530 | 291 if docinfo.get('textURLPath', None): |
| 292 # docinfo.get('textURL', None) not implemented yet | |
| 471 | 293 viewMode = "text" |
| 543 | 294 if viewLayer is None and 'viewLayer' not in userinfo: |
| 295 # use layer dict as default | |
| 508 | 296 viewLayer = "dict" |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
297 else: |
| 590 | 298 viewMode = "image" |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
299 |
| 474 | 300 elif viewMode == "text_dict": |
| 301 # legacy fix | |
| 302 viewMode = "text" | |
| 503 | 303 viewLayer = "dict" |
| 474 | 304 |
| 590 | 305 elif viewMode == 'images': |
| 306 # legacy fix | |
| 307 viewMode = 'image' | |
| 308 self.REQUEST['viewMode'] = 'image' | |
|
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
309 |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
310 |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
311 |
| 590 | 312 |
| 543 | 313 # safe viewLayer in userinfo |
| 314 userinfo['viewLayer'] = viewLayer | |
| 548 | 315 |
| 543 | 316 # pageinfo: information about page (not cached) |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
317 pageinfo = self.getPageinfo(start=start, pn=pn, pf=pf, docinfo=docinfo, userinfo=userinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode) |
| 469 | 318 |
| 475 | 319 # get template /template/viewer_$viewMode |
| 320 pt = getattr(self.template, 'viewer_%s'%viewMode, None) | |
| 321 if pt is None: | |
| 322 logging.error("No template for viewMode=%s!"%viewMode) | |
| 323 # TODO: error page? | |
| 324 return "No template for viewMode=%s!"%viewMode | |
| 325 | |
| 455 | 326 # and execute with parameters |
| 471 | 327 return pt(docinfo=docinfo, pageinfo=pageinfo) |
| 0 | 328 |
| 525 | 329 def getAvailableLayers(self): |
| 330 """returns dict with list of available layers per viewMode""" | |
| 331 return self.availableLayers | |
| 332 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
333 def findDigilibUrl(self): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
334 """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
|
335 url = self.template.zogilib.getDLBaseUrl() |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
336 return url |
| 480 | 337 |
| 338 def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None): | |
| 339 """returns URL to digilib Scaler with params""" | |
| 340 url = None | |
| 341 if docinfo is not None: | |
| 342 url = docinfo.get('imageURL', None) | |
| 343 | |
| 344 if url is None: | |
| 566 | 345 url = self.digilibScalerUrl |
| 480 | 346 if fn is None and docinfo is not None: |
| 347 fn = docinfo.get('imagePath','') | |
| 348 | |
| 349 url += "fn=%s"%fn | |
| 350 | |
| 351 if pn: | |
| 352 url += "&pn=%s"%pn | |
| 353 | |
| 354 url += "&dw=%s&dh=%s"%(dw,dh) | |
| 355 return url | |
| 126 | 356 |
| 357 def getDocumentViewerURL(self): | |
| 358 """returns the URL of this instance""" | |
| 359 return self.absolute_url() | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
360 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
361 def getStyle(self, idx, selected, style=""): |
| 480 | 362 """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
|
363 #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
|
364 if idx == selected: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
365 return style + 'sel' |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
366 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
367 return style |
| 74 | 368 |
| 478 | 369 def getParams(self, param=None, val=None, params=None, duplicates=None): |
| 469 | 370 """returns dict with URL parameters. |
| 371 | |
| 372 Takes URL parameters and additionally param=val or dict params. | |
| 373 Deletes key if value is None.""" | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
374 # copy existing request params |
| 469 | 375 newParams=self.REQUEST.form.copy() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
376 # change single param |
| 25 | 377 if param is not None: |
| 31 | 378 if val is None: |
| 469 | 379 if newParams.has_key(param): |
| 380 del newParams[param] | |
| 25 | 381 else: |
| 469 | 382 newParams[param] = str(val) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
383 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
384 # change more params |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
385 if params is not None: |
| 478 | 386 for (k, v) in params.items(): |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
387 if v is None: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
388 # val=None removes param |
| 469 | 389 if newParams.has_key(k): |
| 390 del newParams[k] | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
391 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
392 else: |
| 469 | 393 newParams[k] = v |
| 478 | 394 |
| 395 if duplicates: | |
| 396 # eliminate lists (coming from duplicate keys) | |
| 397 for (k,v) in newParams.items(): | |
| 398 if isinstance(v, list): | |
| 399 if duplicates == 'comma': | |
| 400 # make comma-separated list of non-empty entries | |
| 401 newParams[k] = ','.join([t for t in v if t]) | |
| 402 elif duplicates == 'first': | |
| 403 # take first non-empty entry | |
| 404 newParams[k] = [t for t in v if t][0] | |
| 405 | |
| 469 | 406 return newParams |
| 407 | |
| 478 | 408 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
| 469 | 409 """returns URL to documentviewer with parameter param set to val or from dict params""" |
| 478 | 410 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
|
411 # quote values and assemble into query string (not escaping '/') |
| 514 | 412 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
|
413 if baseUrl is None: |
| 469 | 414 baseUrl = self.getDocumentViewerURL() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
415 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
416 url = "%s?%s"%(baseUrl, ps) |
| 25 | 417 return url |
| 418 | |
| 478 | 419 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
| 68 | 420 """link to documentviewer with parameter param set to val""" |
| 478 | 421 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
|
422 |
| 526 | 423 |
| 424 def setAvailableLayers(self, newLayerString=None): | |
| 425 """sets availableLayers to newLayerString or tries to autodetect available layers. | |
| 426 assumes layer templates have the form layer_{m}_{l} for layer l in mode m. | |
| 427 newLayerString is parsed as JSON.""" | |
| 428 if newLayerString is not None: | |
| 429 try: | |
| 430 layers = json.loads(newLayerString) | |
| 590 | 431 if 'text' in layers and 'image' in layers: |
| 526 | 432 self.availableLayers = layers |
| 433 return | |
| 434 except: | |
| 435 pass | |
| 436 | |
| 437 logging.error("invalid layers=%s! autodetecting..."%repr(newLayerString)) | |
| 438 | |
| 439 # start with builtin layers | |
| 440 self.availableLayers = self.builtinLayers.copy() | |
| 441 # add layers from templates | |
| 442 for t in self.template: | |
| 443 if t.startswith('layer_'): | |
| 444 try: | |
| 445 (x, m, l) = t.split('_', 3) | |
| 446 if m not in self.availableLayers: | |
| 447 # mode m doesn't exist -> new list | |
| 448 self.availableLayers[m] = [l] | |
| 449 | |
| 450 else: | |
| 451 # m exists -> append | |
| 452 if l not in self.availableLayers[m]: | |
| 453 self.availableLayers[m].append() | |
| 454 | |
| 455 except: | |
| 456 pass | |
| 457 | |
| 458 def getAvailableLayersJson(self): | |
| 459 """returns available layers as JSON string.""" | |
| 460 return json.dumps(self.availableLayers) | |
| 461 | |
| 469 | 462 |
| 57 | 463 def getInfo_xml(self,url,mode): |
| 464 """returns info about the document as XML""" | |
| 465 if not self.digilibBaseUrl: | |
| 514 | 466 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 57 | 467 |
| 468 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 469 pt = getattr(self.template, 'info_xml') | |
| 470 return pt(docinfo=docinfo) | |
| 471 | |
| 528 | 472 def getAuthenticatedUser(self, anon=None): |
| 473 """returns the authenticated user object or None. (ignores Zopes anonymous user)""" | |
| 474 user = getSecurityManager().getUser() | |
| 475 if user is not None and user.getUserName() != "Anonymous User": | |
| 476 return user | |
| 477 else: | |
| 478 return anon | |
| 479 | |
| 35 | 480 def isAccessible(self, docinfo): |
| 32 | 481 """returns if access to the resource is granted""" |
| 482 access = docinfo.get('accessType', None) | |
| 167 | 483 logging.debug("documentViewer (accessOK) access type %s"%access) |
| 465 | 484 if access == 'free': |
| 167 | 485 logging.debug("documentViewer (accessOK) access is free") |
| 32 | 486 return True |
| 465 | 487 |
| 45 | 488 elif access is None or access in self.authgroups: |
| 35 | 489 # only local access -- only logged in users |
| 528 | 490 user = self.getAuthenticatedUser() |
| 167 | 491 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
| 528 | 492 return (user is not None) |
| 32 | 493 |
| 167 | 494 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
| 32 | 495 return False |
| 464 | 496 |
| 543 | 497 def getUserinfo(self): |
| 498 """returns userinfo object""" | |
| 499 logging.debug("getUserinfo") | |
| 500 userinfo = {} | |
| 501 # look for cached userinfo in session | |
| 502 if self.REQUEST.SESSION.has_key('userinfo'): | |
| 503 userinfo = self.REQUEST.SESSION['userinfo'] | |
| 504 # check if its still current? | |
| 505 else: | |
| 506 # store in session | |
| 507 self.REQUEST.SESSION['userinfo'] = userinfo | |
| 508 | |
| 509 return userinfo | |
| 510 | |
| 612 | 511 def getDocinfoJSON(self, mode, url, tocMode=None): |
| 512 """returns docinfo depending on mode""" | |
| 513 import json | |
| 514 | |
| 515 dc = self.getDocinfo( mode, url, tocMode) | |
| 516 | |
| 517 return json.dumps(dc) | |
| 518 | |
| 519 | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
520 def getDocinfo(self, mode, url, tocMode=None): |
| 464 | 521 """returns docinfo depending on mode""" |
| 522 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) | |
| 523 # look for cached docinfo in session | |
| 524 if self.REQUEST.SESSION.has_key('docinfo'): | |
| 525 docinfo = self.REQUEST.SESSION['docinfo'] | |
| 526 # check if its still current | |
| 527 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: | |
| 528 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
| 529 return docinfo | |
| 530 | |
| 531 # new docinfo | |
| 532 docinfo = {'mode': mode, 'url': url} | |
| 533 # add self url | |
| 534 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
| 477 | 535 docinfo['digilibBaseUrl'] = self.digilibBaseUrl |
| 566 | 536 docinfo['digilibScalerUrl'] = self.digilibScalerUrl |
| 537 docinfo['digilibViewerUrl'] = self.digilibViewerUrl | |
| 464 | 538 # get index.meta DOM |
| 539 docUrl = None | |
| 540 metaDom = None | |
| 541 if mode=="texttool": | |
| 542 # url points to document dir or index.meta | |
| 543 metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
| 544 if metaDom is None: | |
| 545 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
|
546 |
|
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
547 docUrl = url.replace('/index.meta', '') |
|
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
548 if url.startswith('/mpiwg/online/'): |
|
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
549 docUrl = url.replace('/mpiwg/online/', '', 1) |
| 464 | 550 |
| 551 elif mode=="imagepath": | |
| 552 # url points to folder with images, index.meta optional | |
| 553 # asssume index.meta in parent dir | |
| 554 docUrl = getParentPath(url) | |
| 555 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 599 | 556 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
|
615
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
557 |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
558 elif mode=="hocr": |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
559 # url points to folder with images, index.meta optional |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
560 # asssume index.meta in parent dir |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
561 docUrl = getParentPath(url) |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
562 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
563 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
564 docinfo['textURLPath'] = url.replace('/mpiwg/online', '', 1) |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
565 if docinfo.get("creator", None) is None: |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
566 docinfo['creator'] = "" |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
567 |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
568 if docinfo.get("title", None) is None: |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
569 docinfo['title'] = "" |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
570 |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
571 if docinfo.get("documentPath", None) is None: |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
572 docinfo['documentPath'] = url.replace('/mpiwg/online', '', 1) |
|
d6eca930a534
hocr viewer eingebaut
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
613
diff
changeset
|
573 docinfo['documentPath'] = url.replace('/pages', '', 1) |
| 464 | 574 |
| 575 elif mode=="filepath": | |
| 576 # url points to image file, index.meta optional | |
| 566 | 577 docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, url) |
| 548 | 578 docinfo['numPages'] = 1 |
| 464 | 579 # asssume index.meta is two path segments up |
| 580 docUrl = getParentPath(url, 2) | |
| 581 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 582 | |
| 583 else: | |
| 584 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
| 585 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
| 586 | |
| 587 docinfo['documentUrl'] = docUrl | |
| 588 # process index.meta contents | |
| 473 | 589 if metaDom is not None and metaDom.tag == 'resource': |
| 464 | 590 # document directory name and path |
| 608 | 591 resource = self.metadataService.getResourceData(dom=metaDom, recursive=1) |
| 464 | 592 if resource: |
| 593 docinfo = self.getDocinfoFromResource(docinfo, resource) | |
| 594 | |
| 595 # texttool info | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
596 texttool = self.metadataService.getTexttoolData(dom=metaDom, recursive=1, all=True) |
| 464 | 597 if texttool: |
| 598 docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
| 568 | 599 # document info from full text server |
| 516 | 600 if docinfo.get('textURLPath', None): |
| 565 | 601 docinfo = self.getTextInfo(mode=None, docinfo=docinfo) |
| 568 | 602 # include list of pages TODO: do we need this always? |
| 603 docinfo = self.getTextInfo(mode='pages', docinfo=docinfo) | |
| 464 | 604 |
| 605 # bib info | |
| 606 bib = self.metadataService.getBibData(dom=metaDom) | |
| 607 if bib: | |
| 548 | 608 # save extended version as 'bibx' TODO: ugly |
| 541 | 609 bibx = self.metadataService.getBibData(dom=metaDom, all=True, recursive=1) |
| 610 if len(bibx) == 1: | |
| 611 # unwrap list if possible | |
| 612 bibx = bibx[0] | |
| 613 | |
| 614 docinfo['bibx'] = bibx | |
| 615 docinfo = self.getDocinfoFromBib(docinfo, bib, bibx) | |
| 465 | 616 else: |
| 617 # no bib - try info.xml | |
| 618 docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) | |
| 464 | 619 |
| 620 # auth info | |
| 621 access = self.metadataService.getAccessData(dom=metaDom) | |
| 622 if access: | |
| 623 docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 624 | |
| 466 | 625 # attribution info |
| 626 attribution = self.metadataService.getAttributionData(dom=metaDom) | |
| 627 if attribution: | |
| 628 logging.debug("getDocinfo: attribution=%s"%repr(attribution)) | |
| 629 docinfo['attribution'] = attribution | |
| 630 | |
| 631 # copyright info | |
| 632 copyright = self.metadataService.getCopyrightData(dom=metaDom) | |
| 633 if copyright: | |
| 634 logging.debug("getDocinfo: copyright=%s"%repr(copyright)) | |
| 635 docinfo['copyright'] = copyright | |
| 538 | 636 |
| 637 # DRI (permanent ID) | |
| 581 | 638 dri = self.metadataService.getDRI(dom=metaDom, type='mpiwg') |
| 538 | 639 if dri: |
| 640 docinfo['DRI'] = dri | |
| 466 | 641 |
| 578 | 642 # (presentation) context |
| 643 ctx = self.metadataService.getContextData(dom=metaDom, all=True) | |
| 644 if ctx: | |
| 645 logging.debug("getcontext: ctx=%s"%repr(ctx)) | |
| 646 docinfo['presentationContext'] = ctx | |
| 647 | |
| 464 | 648 # image path |
| 649 if mode != 'texttool': | |
| 532 | 650 # override image path from texttool with url parameter TODO: how about mode=auto? |
| 599 | 651 docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1) |
| 464 | 652 |
| 548 | 653 # check numPages |
| 654 if docinfo.get('numPages', 0) == 0: | |
| 655 # number of images from digilib | |
| 656 if docinfo.get('imagePath', None): | |
| 599 | 657 imgpath = docinfo['imagePath'].replace('/mpiwg/online', '', 1) |
|
580
0806cb9061c1
fixed another bug when url starts with /mpiwg/online/
casties
parents:
578
diff
changeset
|
658 logging.debug("imgpath=%s"%imgpath) |
| 566 | 659 docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, imgpath) |
| 562 | 660 docinfo = self.getDocinfoFromDigilib(docinfo, imgpath) |
| 548 | 661 else: |
| 662 # imagePath still missing? try "./pageimg" | |
| 663 imgPath = os.path.join(docUrl, 'pageimg') | |
| 664 docinfo = self.getDocinfoFromDigilib(docinfo, imgPath) | |
| 665 if docinfo.get('numPages', 0) > 0: | |
| 666 # there are pages | |
| 667 docinfo['imagePath'] = imgPath | |
| 566 | 668 docinfo['imageURL'] = "%s?fn=%s"%(self.digilibScalerUrl, docinfo['imagePath']) |
| 464 | 669 |
| 516 | 670 # check numPages |
| 671 if docinfo.get('numPages', 0) == 0: | |
| 672 if docinfo.get('numTextPages', 0) > 0: | |
| 673 # replace with numTextPages (text-only?) | |
| 674 docinfo['numPages'] = docinfo['numTextPages'] | |
| 607 | 675 |
| 676 # min and max page no | |
| 677 docinfo['minPageNo'] = docinfo.get('minPageNo', 1) | |
| 678 docinfo['maxPageNo'] = docinfo.get('maxPageNo', docinfo['numPages']) | |
| 516 | 679 |
| 608 | 680 # part-of information |
| 681 partOfPath = docinfo.get('partOfPath', None) | |
| 682 if partOfPath is not None: | |
| 683 partOfDom = self.metadataService.getDomFromPathOrUrl(partOfPath) | |
| 684 if partOfDom is not None: | |
| 685 docinfo['partOfLabel'] = self.metadataService.getBibFormattedLabel(dom=partOfDom) | |
| 686 docinfo['partOfUrl'] = "%s?url=%s"%(self.getDocumentViewerURL(), partOfPath) | |
| 687 logging.debug("partOfLabel=%s partOfUrl=%s"%(docinfo['partOfLabel'],docinfo['partOfUrl'])) | |
| 688 | |
| 599 | 689 # normalize path |
| 690 if 'imagePath' in docinfo and not docinfo['imagePath'].startswith('/'): | |
| 691 docinfo['imagePath'] = '/' + docinfo['imagePath'] | |
| 692 | |
| 464 | 693 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
| 694 # store in session | |
| 695 self.REQUEST.SESSION['docinfo'] = docinfo | |
| 696 return docinfo | |
| 697 | |
| 516 | 698 |
| 464 | 699 def getDocinfoFromResource(self, docinfo, resource): |
| 700 """reads contents of resource element into docinfo""" | |
| 608 | 701 logging.debug("getDocinfoFromResource: resource=%s"%(repr(resource))) |
| 702 docName = getMDText(resource.get('name', None)) | |
| 464 | 703 docinfo['documentName'] = docName |
| 608 | 704 docPath = getMDText(resource.get('archive-path', None)) |
| 464 | 705 if docPath: |
| 706 # clean up document path | |
| 707 if docPath[0] != '/': | |
| 708 docPath = '/' + docPath | |
| 709 | |
| 710 if docName and (not docPath.endswith(docName)): | |
| 711 docPath += "/" + docName | |
| 712 | |
| 713 else: | |
| 714 # use docUrl as docPath | |
| 715 docUrl = docinfo['documentURL'] | |
| 716 if not docUrl.startswith('http:'): | |
| 717 docPath = docUrl | |
| 608 | 718 |
| 465 | 719 if docPath: |
| 720 # fix URLs starting with /mpiwg/online | |
| 721 docPath = docPath.replace('/mpiwg/online', '', 1) | |
| 722 | |
| 464 | 723 docinfo['documentPath'] = docPath |
| 608 | 724 |
| 725 # is this part-of? | |
| 726 partOf = resource.get('is-part-of', None) | |
| 727 if partOf is not None: | |
| 728 partOf = getMDText(partOf.get('archive-path', None)) | |
| 729 if partOf is not None: | |
| 730 docinfo['partOfPath'] = partOf.strip() | |
| 731 | |
| 464 | 732 return docinfo |
| 733 | |
| 734 def getDocinfoFromTexttool(self, docinfo, texttool): | |
| 735 """reads contents of texttool element into docinfo""" | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
736 logging.debug("texttool=%s"%repr(texttool)) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
737 # unpack list if necessary |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
738 if isinstance(texttool, list): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
739 texttool = texttool[0] |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
740 |
| 464 | 741 # image dir |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
742 imageDir = getMDText(texttool.get('image', None)) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
743 docPath = getMDText(docinfo.get('documentPath', None)) |
| 607 | 744 if imageDir: |
| 745 if imageDir.startswith('/'): | |
| 746 # absolute path | |
| 747 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
| 748 docinfo['imagePath'] = imageDir | |
| 749 | |
| 750 elif docPath: | |
| 751 # relative path | |
| 752 imageDir = os.path.join(docPath, imageDir) | |
| 753 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
| 754 docinfo['imagePath'] = imageDir | |
| 755 | |
| 756 # start and end page (for subdocuments of other documents) | |
| 757 imgStartNo = getMDText(texttool.get('image-start-no', None)) | |
| 758 minPageNo = getInt(imgStartNo, 1) | |
| 759 docinfo['minPageNo'] = minPageNo | |
| 760 | |
| 761 imgEndNo = getMDText(texttool.get('image-end-no', None)) | |
| 762 if imgEndNo: | |
| 763 docinfo['maxPageNo'] = getInt(imgEndNo) | |
| 464 | 764 |
| 765 # old style text URL | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
766 textUrl = getMDText(texttool.get('text', None)) |
| 617 | 767 |
| 768 | |
| 769 | |
| 770 | |
| 464 | 771 if textUrl and docPath: |
| 772 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
| 773 textUrl = os.path.join(docPath, textUrl) | |
| 774 | |
| 775 docinfo['textURL'] = textUrl | |
| 776 | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
777 # 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
|
778 textUrlNode = texttool.get('text-url-path', None) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
779 if not isinstance(textUrlNode, list): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
780 textUrlNode = [textUrlNode] |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
781 |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
782 for tun in textUrlNode: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
783 textUrl = getMDText(tun) |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
784 if textUrl: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
785 textUrlAtts = tun.get('@attr') |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
786 if (textUrlAtts and 'repository' in textUrlAtts): |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
787 textRepo = textUrlAtts['repository'] |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
788 # use matching repository |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
789 if self.getRepositoryType() == textRepo: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
790 docinfo['textURLPath'] = textUrl |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
791 docinfo['textURLRepository'] = textRepo |
| 564 | 792 break |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
793 |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
794 else: |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
795 # no repo attribute - use always |
|
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
796 docinfo['textURLPath'] = textUrl |
| 468 | 797 |
| 798 # page flow | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
799 docinfo['pageFlow'] = getMDText(texttool.get('page-flow', 'ltr')) |
| 468 | 800 |
| 801 # odd pages are left | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
802 docinfo['oddPage'] = getMDText(texttool.get('odd-scan-position', 'left')) |
| 468 | 803 |
| 541 | 804 # number of title page (default 1) |
| 607 | 805 docinfo['titlePage'] = getMDText(texttool.get('title-scan-no', minPageNo)) |
| 464 | 806 |
| 807 # old presentation stuff | |
|
561
9255acc4518d
CLOSED - # 256: display texts from different backends (sandbox)
casties
parents:
560
diff
changeset
|
808 presentation = getMDText(texttool.get('presentation', None)) |
| 464 | 809 if presentation and docPath: |
| 465 | 810 if presentation.startswith('http:'): |
| 811 docinfo['presentationUrl'] = presentation | |
| 812 else: | |
| 813 docinfo['presentationUrl'] = os.path.join(docPath, presentation) | |
| 602 | 814 |
| 815 # make sure we have at least fake DC data | |
| 816 if 'creator' not in docinfo: | |
| 817 docinfo['creator'] = '[no author found]' | |
| 818 | |
| 819 if 'title' not in docinfo: | |
| 820 docinfo['title'] = '[no title found]' | |
| 821 | |
| 822 if 'date' not in docinfo: | |
| 823 docinfo['date'] = '[no date found]' | |
| 468 | 824 |
| 464 | 825 return docinfo |
| 826 | |
| 541 | 827 def getDocinfoFromBib(self, docinfo, bib, bibx=None): |
| 464 | 828 """reads contents of bib element into docinfo""" |
| 465 | 829 logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
| 464 | 830 # put all raw bib fields in dict "bib" |
| 831 docinfo['bib'] = bib | |
| 832 bibtype = bib.get('@type', None) | |
| 833 docinfo['bibType'] = bibtype | |
| 834 # also store DC metadata for convenience | |
| 835 dc = self.metadataService.getDCMappedData(bib) | |
|
536
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
836 docinfo['creator'] = dc.get('creator','') |
|
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
837 docinfo['title'] = dc.get('title','') |
|
abd36d4d97b8
new version of index page. improvements for digilib page and thumbnail overview.
casties
parents:
535
diff
changeset
|
838 docinfo['date'] = dc.get('date','') |
| 464 | 839 return docinfo |
| 840 | |
| 841 def getDocinfoFromAccess(self, docinfo, acc): | |
| 842 """reads contents of access element into docinfo""" | |
| 843 #TODO: also read resource type | |
| 465 | 844 logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
| 464 | 845 try: |
| 465 | 846 acctype = acc['@attr']['type'] |
| 464 | 847 if acctype: |
| 848 access=acctype | |
| 849 if access in ['group', 'institution']: | |
| 850 access = acc['name'].lower() | |
| 851 | |
| 852 docinfo['accessType'] = access | |
| 853 | |
| 854 except: | |
| 855 pass | |
| 856 | |
| 857 return docinfo | |
| 858 | |
| 859 def getDocinfoFromDigilib(self, docinfo, path): | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
860 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?fn="+path |
| 464 | 861 # fetch data |
| 862 txt = getHttpData(infoUrl) | |
| 863 if not txt: | |
| 864 logging.error("Unable to get dir-info from %s"%(infoUrl)) | |
| 865 return docinfo | |
| 866 | |
| 867 dom = ET.fromstring(txt) | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
868 dir = dom |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
869 # save size |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
870 size = dir.findtext('size') |
| 464 | 871 logging.debug("getDocinfoFromDigilib: size=%s"%size) |
| 872 if size: | |
| 873 docinfo['numPages'] = int(size) | |
| 874 else: | |
| 875 docinfo['numPages'] = 0 | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
876 return docinfo |
| 464 | 877 |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
878 # save list of image names and numbers |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
879 imgNames = {} |
| 591 | 880 imgIndexes = {} |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
881 for f in dir: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
882 fn = f.findtext('name') |
| 591 | 883 pn = getInt(f.findtext('index')) |
| 884 imgNames[fn] = pn | |
| 885 imgIndexes[pn] = fn | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
886 |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
887 docinfo['imgFileNames'] = imgNames |
| 591 | 888 docinfo['imgFileIndexes'] = imgIndexes |
| 464 | 889 return docinfo |
| 890 | |
| 891 | |
| 465 | 892 def getDocinfoFromPresentationInfoXml(self,docinfo): |
| 893 """gets DC-like bibliographical information from the presentation entry in texttools""" | |
| 894 url = docinfo.get('presentationUrl', None) | |
| 895 if not url: | |
| 896 logging.error("getDocinfoFromPresentation: no URL!") | |
| 897 return docinfo | |
| 898 | |
| 899 dom = None | |
| 900 metaUrl = None | |
| 901 if url.startswith("http://"): | |
| 902 # real URL | |
| 903 metaUrl = url | |
| 904 else: | |
| 905 # online path | |
| 906 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 907 metaUrl=server+url | |
| 908 | |
| 909 txt=getHttpData(metaUrl) | |
| 910 if txt is None: | |
| 911 logging.error("Unable to read info.xml from %s"%(url)) | |
| 912 return docinfo | |
| 913 | |
| 914 dom = ET.fromstring(txt) | |
| 915 docinfo['creator']=getText(dom.find(".//author")) | |
| 916 docinfo['title']=getText(dom.find(".//title")) | |
| 917 docinfo['date']=getText(dom.find(".//date")) | |
| 918 return docinfo | |
| 919 | |
| 920 | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
921 def getPageinfo(self, pn=None, pf=None, start=None, rows=None, cols=None, docinfo=None, userinfo=None, viewMode=None, viewLayer=None, tocMode=None): |
| 22 | 922 """returns pageinfo with the given parameters""" |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
923 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 | 924 pageinfo = {} |
| 471 | 925 pageinfo['viewMode'] = viewMode |
| 508 | 926 # split viewLayer if necessary |
| 927 if isinstance(viewLayer,basestring): | |
| 928 viewLayer = viewLayer.split(',') | |
| 929 | |
| 930 if isinstance(viewLayer, list): | |
| 931 logging.debug("getPageinfo: viewLayer is list:%s"%viewLayer) | |
| 932 # save (unique) list in viewLayers | |
| 933 seen = set() | |
| 934 viewLayers = [l for l in viewLayer if l and l not in seen and not seen.add(l)] | |
| 935 pageinfo['viewLayers'] = viewLayers | |
| 936 # stringify viewLayer | |
| 937 viewLayer = ','.join(viewLayers) | |
| 938 else: | |
| 939 #create list | |
| 940 pageinfo['viewLayers'] = [viewLayer] | |
| 941 | |
| 503 | 942 pageinfo['viewLayer'] = viewLayer |
| 471 | 943 pageinfo['tocMode'] = tocMode |
| 944 | |
| 607 | 945 minPageNo = docinfo.get('minPageNo', 1) |
| 946 | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
947 # pf takes precedence over pn |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
948 if pf: |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
949 pageinfo['pf'] = pf |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
950 pn = getPnForPf(docinfo, pf) |
| 589 | 951 # replace pf in request params (used for creating new URLs) |
| 952 self.REQUEST.form.pop('pf', None) | |
| 953 self.REQUEST.form['pn'] = pn | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
954 else: |
| 607 | 955 pn = getInt(pn, minPageNo) |
| 591 | 956 pf = getPfForPn(docinfo, pn) |
| 957 pageinfo['pf'] = pf | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
958 |
|
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
959 pageinfo['pn'] = pn |
| 25 | 960 rows = int(rows or self.thumbrows) |
| 961 pageinfo['rows'] = rows | |
| 962 cols = int(cols or self.thumbcols) | |
| 963 pageinfo['cols'] = cols | |
| 964 grpsize = cols * rows | |
| 965 pageinfo['groupsize'] = grpsize | |
| 607 | 966 # if start is empty use one around pn |
| 967 grouppn = math.ceil(float(pn)/float(grpsize))*grpsize-(grpsize-1) | |
| 968 # but not smaller than minPageNo | |
| 969 start = getInt(start, max(grouppn, minPageNo)) | |
| 22 | 970 pageinfo['start'] = start |
| 511 | 971 # get number of pages |
| 607 | 972 numPages = int(docinfo.get('numPages', 0)) |
| 973 if numPages == 0: | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
974 # try numTextPages |
| 607 | 975 numPages = docinfo.get('numTextPages', 0) |
| 976 if numPages != 0: | |
| 977 docinfo['numPages'] = numPages | |
| 978 | |
| 979 maxPageNo = docinfo.get('maxPageNo', numPages) | |
| 980 logging.debug("minPageNo=%s maxPageNo=%s start=%s numPages=%s"%(minPageNo,maxPageNo,start,numPages)) | |
| 981 np = maxPageNo | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
982 |
| 511 | 983 # cache table of contents |
| 984 pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) | |
| 469 | 985 pageinfo['numgroups'] = int(np / grpsize) |
| 986 if np % grpsize > 0: | |
| 987 pageinfo['numgroups'] += 1 | |
| 476 | 988 |
| 989 pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' | |
| 990 oddScanLeft = docinfo.get('oddPage', 'left') != 'right' | |
| 991 # add zeroth page for two columns | |
| 992 pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) | |
| 993 pageinfo['pageZero'] = pageZero | |
| 607 | 994 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=minPageNo, maxIdx=np) |
| 516 | 995 # more page parameters |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
996 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
| 516 | 997 if docinfo.get('pageNumbers'): |
| 998 # get original page numbers | |
|
587
6000c7e24d8a
new parameter "pf" to specify image file name. (still some issues)
casties
parents:
585
diff
changeset
|
999 pageNumber = docinfo['pageNumbers'].get(pn, None) |
| 516 | 1000 if pageNumber is not None: |
| 1001 pageinfo['pageNumberOrig'] = pageNumber['no'] | |
| 1002 pageinfo['pageNumberOrigNorm'] = pageNumber['non'] | |
| 158 | 1003 |
| 511 | 1004 # cache search results |
| 1005 query = self.REQUEST.get('query',None) | |
| 1006 pageinfo['query'] = query | |
| 591 | 1007 if query and viewMode == 'text': |
| 1008 pageinfo['resultPageSize'] = getInt(self.REQUEST.get('resultPageSize', 10)) | |
| 511 | 1009 queryType = self.REQUEST.get('queryType', 'fulltextMorph') |
| 1010 pageinfo['queryType'] = queryType | |
| 1011 pageinfo['resultStart'] = getInt(self.REQUEST.get('resultStart', '1')) | |
| 1012 self.getSearchResults(mode=queryType, query=query, pageinfo=pageinfo, docinfo=docinfo) | |
| 1013 | |
| 1014 # highlighting | |
| 1015 highlightQuery = self.REQUEST.get('highlightQuery', None) | |
| 1016 if highlightQuery: | |
| 1017 pageinfo['highlightQuery'] = highlightQuery | |
| 1018 pageinfo['highlightElement'] = self.REQUEST.get('highlightElement', '') | |
| 1019 pageinfo['highlightElementPos'] = self.REQUEST.get('highlightElementPos', '') | |
| 460 | 1020 |
| 22 | 1021 return pageinfo |
| 460 | 1022 |
| 463 | 1023 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1024 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
|
1025 """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
|
1026 |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1027 :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
|
1028 :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
|
1029 :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
|
1030 :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
|
1031 :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
|
1032 :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
|
1033 :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
|
1034 :returns: dict with |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1035 first: first page index |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1036 last: last page index |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1037 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
|
1038 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
|
1039 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
|
1040 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
|
1041 """ |
| 607 | 1042 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
|
1043 batch = {} |
| 480 | 1044 grpsize = rows * cols |
| 476 | 1045 if maxIdx == 0: |
| 480 | 1046 maxIdx = start + grpsize |
| 476 | 1047 |
| 607 | 1048 np = maxIdx - minIdx + 1 |
|
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1049 if pageZero: |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1050 # 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
|
1051 np += 1 |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1052 |
| 607 | 1053 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
|
1054 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1055 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1056 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1057 if pageZero: |
| 607 | 1058 ofs = minIdx - 1 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1059 else: |
| 607 | 1060 ofs = minIdx |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1061 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1062 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1063 s = i * grpsize + ofs |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1064 e = min((i + 1) * grpsize + ofs - 1, maxIdx) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1065 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1066 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1067 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1068 |
|
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1069 # list of pages for current screen |
| 476 | 1070 pages = [] |
| 607 | 1071 if pageZero and start == minIdx: |
| 476 | 1072 # correct beginning |
| 607 | 1073 idx = minIdx - 1 |
| 476 | 1074 else: |
| 1075 idx = start | |
| 1076 | |
| 1077 for r in range(rows): | |
| 1078 row = [] | |
| 1079 for c in range(cols): | |
| 1080 if idx < minIdx or idx > maxIdx: | |
| 1081 page = {'idx':None} | |
| 1082 else: | |
| 1083 page = {'idx':idx} | |
| 1084 | |
| 1085 idx += 1 | |
| 1086 if pageFlowLtr: | |
| 1087 row.append(page) | |
| 1088 else: | |
| 1089 row.insert(0, page) | |
| 1090 | |
| 1091 pages.append(row) | |
| 1092 | |
| 607 | 1093 if start > minIdx: |
| 1094 batch['prevStart'] = max(start - grpsize, minIdx) | |
| 480 | 1095 else: |
| 1096 batch['prevStart'] = None | |
| 1097 | |
| 526 | 1098 if start + grpsize <= maxIdx: |
|
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1099 if pageZero and start == minIdx: |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1100 # correct nextStart for pageZero |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1101 batch['nextStart'] = grpsize |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1102 else: |
|
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1103 batch['nextStart'] = start + grpsize |
| 480 | 1104 else: |
| 1105 batch['nextStart'] = None | |
| 1106 | |
| 1107 batch['pages'] = pages | |
| 571 | 1108 batch['first'] = minIdx |
| 1109 batch['last'] = maxIdx | |
|
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1110 logging.debug("batch: %s"%repr(batch)) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1111 return batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1112 |
|
613
c57d80a649ea
CLOSED - # 281: List of thumbnails verschluckt Seite, wenn odd-scan-position gesetzt ist
casties
parents:
612
diff
changeset
|
1113 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1114 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
|
1115 """returns dict with information for one screenfull of data.""" |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1116 batch = {} |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1117 if end == 0: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1118 end = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1119 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1120 nb = int(math.ceil(end / float(size))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1121 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1122 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1123 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1124 s = i * size + 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1125 e = min((i + 1) * size, end) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1126 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1127 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1128 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1129 # list of elements in this batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1130 this = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1131 j = 0 |
| 526 | 1132 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
|
1133 if data: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1134 if fullData: |
| 526 | 1135 d = data.get(i, None) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1136 else: |
| 526 | 1137 d = data.get(j, None) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1138 j += 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1139 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1140 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1141 d = i+1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1142 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1143 this.append(d) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1144 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1145 batch['this'] = this |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1146 if start > 1: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1147 batch['prevStart'] = max(start - size, 1) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1148 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1149 batch['prevStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1150 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1151 if start + size < end: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1152 batch['nextStart'] = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1153 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1154 batch['nextStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
1155 |
| 571 | 1156 batch['first'] = start |
| 1157 batch['last'] = end | |
| 480 | 1158 return batch |
| 476 | 1159 |
| 1160 | |
| 546 | 1161 def getAnnotatorGroupsForUser(self, user, annotationServerUrl="http://tuxserve03.mpiwg-berlin.mpg.de/AnnotationManager"): |
| 1162 """returns list of groups {name:*, id:*} on the annotation server for the user""" | |
| 1163 groups = [] | |
|
622
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1164 if annotationServerUrl.startswith('//'): |
|
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1165 # add matching http(s) from our URL |
|
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1166 myUrl = self.REQUEST['URL'] |
|
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1167 logging.debug("my URL: %s"%myUrl) |
|
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1168 if myUrl.startswith('https:'): |
|
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1169 annotationServerUrl = "https:%s"%annotationServerUrl |
|
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1170 else: |
|
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1171 annotationServerUrl = "http:%s"%annotationServerUrl |
|
bc68ca0d2c0a
make annotationServerUrl work with protocol-relative URL (//).
casties
parents:
618
diff
changeset
|
1172 |
| 546 | 1173 groupsUrl = "%s/annotator/groups?user=%s"%(annotationServerUrl,user) |
| 1174 data = getHttpData(url=groupsUrl, noExceptions=True) | |
| 1175 if data: | |
| 1176 res = json.loads(data) | |
| 1177 rows = res.get('rows', None) | |
| 1178 if rows is None: | |
| 1179 return groups | |
| 1180 for r in rows: | |
| 1181 groups.append({'id': r.get('id', None), 'name': r.get('name', None), 'uri': r.get('uri', None)}) | |
| 1182 | |
| 1183 return groups | |
| 1184 | |
| 1185 | |
| 463 | 1186 security.declareProtected('View management screens','changeDocumentViewerForm') |
| 1187 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 22 | 1188 |
| 526 | 1189 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',availableLayers=None,RESPONSE=None): |
| 22 | 1190 """init document viewer""" |
| 1191 self.title=title | |
| 1192 self.digilibBaseUrl = digilibBaseUrl | |
| 566 | 1193 self.digilibScalerUrl = digilibBaseUrl + '/servlet/Scaler' |
| 1194 self.digilibViewerUrl = digilibBaseUrl + '/jquery/digilib.html' | |
| 25 | 1195 self.thumbrows = thumbrows |
| 1196 self.thumbcols = thumbcols | |
| 32 | 1197 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| 463 | 1198 try: |
| 1199 # assume MetaDataFolder instance is called metadata | |
| 1200 self.metadataService = getattr(self, 'metadata') | |
| 1201 except Exception, e: | |
| 1202 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 526 | 1203 |
| 1204 self.setAvailableLayers(availableLayers) | |
| 463 | 1205 |
| 22 | 1206 if RESPONSE is not None: |
| 1207 RESPONSE.redirect('manage_main') | |
| 0 | 1208 |
| 1209 def manage_AddDocumentViewerForm(self): | |
| 1210 """add the viewer form""" | |
| 22 | 1211 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| 0 | 1212 return pt() |
| 1213 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1214 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
| 0 | 1215 """add the viewer""" |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1216 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
| 0 | 1217 self._setObject(id,newObj) |
| 1218 | |
| 1219 if RESPONSE is not None: | |
| 1220 RESPONSE.redirect('manage_main') |