Mercurial > hg > documentViewer
annotate documentViewer.py @ 528:f8a5f63eafc0
new viewMode=thumbs.
| author | casties |
|---|---|
| date | Fri, 13 Apr 2012 16:55:16 +0200 |
| parents | 3f375a048402 |
| children | 5c7433c2515c |
| 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 |
| 514 | 21 from SrvTxtUtils import getInt, utf8ify, getText, getHttpData, refreshingImageFileIndexHtml |
| 52 | 22 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
23 def serializeNode(node, encoding="utf-8"): |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
24 """returns a string containing node as XML""" |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
25 s = ET.tostring(node) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
26 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
27 # 4Suite: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
28 # stream = cStringIO.StringIO() |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
29 # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
30 # s = stream.getvalue() |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
31 # stream.close() |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
32 return s |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
33 |
| 387 | 34 def browserCheck(self): |
| 35 """check the browsers request to find out the browser type""" | |
| 36 bt = {} | |
| 37 ua = self.REQUEST.get_header("HTTP_USER_AGENT") | |
| 38 bt['ua'] = ua | |
| 39 bt['isIE'] = False | |
| 40 bt['isN4'] = False | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
41 bt['versFirefox']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
42 bt['versIE']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
43 bt['versSafariChrome']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
44 bt['versOpera']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
45 |
| 387 | 46 if string.find(ua, 'MSIE') > -1: |
| 47 bt['isIE'] = True | |
| 48 else: | |
| 49 bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
50 # Safari oder Chrome identification |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
51 try: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
52 nav = ua[string.find(ua, '('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
53 nav1=ua[string.find(ua,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
54 nav2=nav1[string.find(nav1,'('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
55 nav3=nav2[string.find(nav2,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
56 ie = string.split(nav, "; ")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
57 ie1 =string.split(nav1, " ")[2] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
58 ie2 =string.split(nav3, " ")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
59 ie3 =string.split(nav3, " ")[2] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
60 if string.find(ie3, "Safari") >-1: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
61 bt['versSafariChrome']=string.split(ie2, "/")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
62 except: pass |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
63 # IE identification |
| 387 | 64 try: |
| 65 nav = ua[string.find(ua, '('):] | |
| 66 ie = string.split(nav, "; ")[1] | |
| 67 if string.find(ie, "MSIE") > -1: | |
| 68 bt['versIE'] = string.split(ie, " ")[1] | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
69 except:pass |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
70 # Firefox identification |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
71 try: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
72 nav = ua[string.find(ua, '('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
73 nav1=ua[string.find(ua,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
74 if string.find(ie1, "Firefox") >-1: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
75 nav5= string.split(ie1, "/")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
76 logging.debug("FIREFOX: %s"%(nav5)) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
77 bt['versFirefox']=nav5[0:3] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
78 except:pass |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
79 #Opera identification |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
80 try: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
81 if string.find(ua,"Opera") >-1: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
82 nav = ua[string.find(ua, '('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
83 nav1=nav[string.find(nav,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
84 bt['versOpera']=string.split(nav1,"/")[2] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
85 except:pass |
| 387 | 86 |
| 87 bt['isMac'] = string.find(ua, 'Macintosh') > -1 | |
| 88 bt['isWin'] = string.find(ua, 'Windows') > -1 | |
| 89 bt['isIEWin'] = bt['isIE'] and bt['isWin'] | |
| 90 bt['isIEMac'] = bt['isIE'] and bt['isMac'] | |
| 91 bt['staticHTML'] = False | |
| 92 | |
| 93 return bt | |
| 234 | 94 |
| 464 | 95 def getParentPath(path, cnt=1): |
| 96 """returns pathname shortened by cnt""" | |
| 97 # make sure path doesn't end with / | |
| 98 path = path.rstrip('/') | |
| 99 # split by /, shorten, and reassemble | |
| 100 return '/'.join(path.split('/')[0:-cnt]) | |
| 101 | |
| 22 | 102 ## |
| 103 ## documentViewer class | |
| 104 ## | |
| 105 class documentViewer(Folder): | |
| 0 | 106 """document viewer""" |
| 107 meta_type="Document viewer" | |
| 108 | |
| 109 security=ClassSecurityInfo() | |
| 22 | 110 manage_options=Folder.manage_options+( |
| 507 | 111 {'label':'Configuration','action':'changeDocumentViewerForm'}, |
| 0 | 112 ) |
| 463 | 113 |
| 114 metadataService = None | |
| 115 """MetaDataFolder instance""" | |
| 525 | 116 |
| 0 | 117 |
| 525 | 118 # |
| 22 | 119 # templates and forms |
| 525 | 120 # |
| 121 # viewMode templates | |
| 479 | 122 viewer_text = PageTemplateFile('zpt/viewer_text', globals()) |
| 503 | 123 viewer_xml = PageTemplateFile('zpt/viewer_xml', globals()) |
| 483 | 124 viewer_images = PageTemplateFile('zpt/viewer_images', globals()) |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
125 viewer_index = PageTemplateFile('zpt/viewer_index', globals()) |
| 528 | 126 viewer_thumbs = PageTemplateFile('zpt/viewer_thumbs', globals()) |
| 525 | 127 # available layer types |
| 526 | 128 builtinLayers = {'text': ['dict','search','gis','annotator'], |
| 129 'xml': None, 'images': None, 'index': None} | |
| 130 availableLayers = builtinLayers; | |
| 525 | 131 # layer templates |
| 526 | 132 layer_text_dict = PageTemplateFile('zpt/layer_text_dict', globals()) |
| 133 layer_text_search = PageTemplateFile('zpt/layer_text_search', globals()) | |
| 525 | 134 layer_text_annotator = PageTemplateFile('zpt/layer_text_annotator', globals()) |
| 135 layer_text_gis = PageTemplateFile('zpt/layer_text_gis', globals()) | |
| 136 # toc templates | |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
137 toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
138 toc_text = PageTemplateFile('zpt/toc_text', globals()) |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
139 toc_figures = PageTemplateFile('zpt/toc_figures', globals()) |
| 526 | 140 toc_concordance = PageTemplateFile('zpt/toc_concordance', globals()) |
| 491 | 141 toc_none = PageTemplateFile('zpt/toc_none', globals()) |
| 525 | 142 # other templates |
| 501 | 143 common_template = PageTemplateFile('zpt/common_template', globals()) |
| 57 | 144 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
| 487 | 145 docuviewer_css = ImageFile('css/docuviewer.css',globals()) |
|
489
55e3398e395e
more new templates. monkey-patch for App.ImageFile.
casties
parents:
488
diff
changeset
|
146 # make ImageFile better for development |
|
490
6f116b86a226
more new template stuff. moved ImageFile index method to SrvTxtUtils
casties
parents:
489
diff
changeset
|
147 docuviewer_css.index_html = refreshingImageFileIndexHtml |
| 501 | 148 jquery_js = ImageFile('js/jquery.js',globals()) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
149 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
150 |
| 95 | 151 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
| 0 | 152 """init document viewer""" |
| 153 self.id=id | |
| 154 self.title=title | |
| 25 | 155 self.thumbcols = thumbcols |
| 156 self.thumbrows = thumbrows | |
| 32 | 157 # authgroups is list of authorized groups (delimited by ,) |
| 158 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
|
159 # 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
|
160 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
161 templateFolder = Folder('template') |
| 498 | 162 self['template'] = templateFolder # Zope-2.12 style |
| 163 #self._setObject('template',templateFolder) # old style | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
164 try: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
165 import MpdlXmlTextServer |
| 132 | 166 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
| 498 | 167 templateFolder['fulltextclient'] = textServer |
| 168 #templateFolder._setObject('fulltextclient',textServer) | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
169 except Exception, e: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
170 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
| 463 | 171 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
172 try: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
173 from Products.zogiLib.zogiLib import zogiLib |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
174 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
| 498 | 175 templateFolder['zogilib'] = zogilib |
| 176 #templateFolder._setObject('zogilib',zogilib) | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
177 except Exception, e: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
178 logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
| 463 | 179 |
| 180 try: | |
| 181 # assume MetaDataFolder instance is called metadata | |
| 182 self.metadataService = getattr(self, 'metadata') | |
| 183 except Exception, e: | |
| 184 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 185 | |
| 477 | 186 if digilibBaseUrl is not None: |
| 187 self.digilibBaseUrl = digilibBaseUrl | |
| 188 | |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
189 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
190 # proxy text server methods to fulltextclient |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
191 def getTextPage(self, **args): |
| 498 | 192 """returns full text content of page""" |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
193 return self.template.fulltextclient.getTextPage(**args) |
| 22 | 194 |
| 508 | 195 def getSearchResults(self, **args): |
| 196 """loads list of search results and stores XML in docinfo""" | |
| 197 return self.template.fulltextclient.getSearchResults(**args) | |
| 198 | |
| 199 def getResultsPage(self, **args): | |
| 200 """returns one page of the search results""" | |
| 201 return self.template.fulltextclient.getResultsPage(**args) | |
| 202 | |
| 516 | 203 def getTextInfo(self, **args): |
| 204 """returns document info from the text server""" | |
| 205 return self.template.fulltextclient.getTextInfo(**args) | |
| 206 | |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
207 def getToc(self, **args): |
| 508 | 208 """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
|
209 return self.template.fulltextclient.getToc(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
210 |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
211 def getTocPage(self, **args): |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
212 """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
|
213 return self.template.fulltextclient.getTocPage(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
214 |
| 506 | 215 def getPlacesOnPage(self, **args): |
| 216 """get list of gis places on one page""" | |
| 217 return self.template.fulltextclient.getPlacesOnPage(**args) | |
| 307 | 218 |
| 498 | 219 #WTF? |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
220 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
| 68 | 221 security.declareProtected('View','thumbs_rss') |
| 222 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
| 223 ''' | |
| 224 view it | |
| 225 @param mode: defines how to access the document behind url | |
| 226 @param url: url which contains display information | |
| 227 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
| 228 | |
| 229 ''' | |
| 167 | 230 logging.debug("HHHHHHHHHHHHHH:load the rss") |
| 458 | 231 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| 68 | 232 |
| 233 if not hasattr(self, 'template'): | |
| 234 # create template folder if it doesn't exist | |
| 235 self.manage_addFolder('template') | |
| 236 | |
| 237 if not self.digilibBaseUrl: | |
| 238 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 239 | |
| 240 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 338 | 241 #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
| 345 | 242 pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) |
| 331 | 243 ''' ZDES ''' |
| 68 | 244 pt = getattr(self.template, 'thumbs_main_rss') |
| 245 | |
| 246 if viewMode=="auto": # automodus gewaehlt | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
247 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
| 68 | 248 viewMode="text" |
| 249 else: | |
| 250 viewMode="images" | |
| 251 | |
| 252 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
| 465 | 253 |
| 68 | 254 |
| 22 | 255 security.declareProtected('View','index_html') |
| 503 | 256 def index_html(self,url,mode="texttool",viewMode="auto",viewLayer=None,tocMode="thumbs",start=1,pn=1): |
| 464 | 257 """ |
| 471 | 258 view page |
| 259 @param url: url which contains display information | |
| 57 | 260 @param mode: defines how to access the document behind url |
| 503 | 261 @param viewMode: 'images': display images, 'text': display text, 'xml': display xml, default is 'auto' |
| 262 @param viewLayer: sub-type of viewMode, e.g. 'dict' for viewMode='text' | |
| 99 | 263 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
| 464 | 264 """ |
| 0 | 265 |
| 503 | 266 logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewLayer=%s start=%s pn=%s"%(mode,url,viewMode,viewLayer,start,pn)) |
| 22 | 267 |
| 268 if not hasattr(self, 'template'): | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
269 # this won't work |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
270 logging.error("template folder missing!") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
271 return "ERROR: template folder missing!" |
| 22 | 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 |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
276 docinfo = self.getDocinfo(mode=mode,url=url,tocMode=tocMode) |
| 97 | 277 |
| 471 | 278 # auto viewMode: text if there is a text else images |
| 455 | 279 if viewMode=="auto": |
| 280 if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): | |
| 471 | 281 viewMode = "text" |
| 508 | 282 if viewLayer is None: |
| 283 viewLayer = "dict" | |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
284 else: |
| 471 | 285 viewMode = "images" |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
286 |
| 474 | 287 elif viewMode == "text_dict": |
| 288 # legacy fix | |
| 289 viewMode = "text" | |
| 503 | 290 viewLayer = "dict" |
| 474 | 291 |
| 503 | 292 pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode) |
| 469 | 293 |
| 475 | 294 # get template /template/viewer_$viewMode |
| 295 pt = getattr(self.template, 'viewer_%s'%viewMode, None) | |
| 296 if pt is None: | |
| 297 logging.error("No template for viewMode=%s!"%viewMode) | |
| 298 # TODO: error page? | |
| 299 return "No template for viewMode=%s!"%viewMode | |
| 300 | |
| 455 | 301 # and execute with parameters |
| 471 | 302 return pt(docinfo=docinfo, pageinfo=pageinfo) |
| 0 | 303 |
| 506 | 304 #WTF? |
| 74 | 305 def generateMarks(self,mk): |
| 306 ret="" | |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
307 if mk is None: |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
308 return "" |
| 134 | 309 if not isinstance(mk, list): |
| 132 | 310 mk=[mk] |
| 74 | 311 for m in mk: |
|
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
312 ret+="mk=%s"%m |
| 74 | 313 return ret |
| 389 | 314 |
| 315 | |
| 525 | 316 def getAvailableLayers(self): |
| 317 """returns dict with list of available layers per viewMode""" | |
| 318 return self.availableLayers | |
| 319 | |
| 387 | 320 def getBrowser(self): |
| 321 """getBrowser the version of browser """ | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
322 bt = browserCheck(self) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
323 logging.debug("BROWSER VERSION: %s"%(bt)) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
324 return bt |
| 387 | 325 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
326 def findDigilibUrl(self): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
327 """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
|
328 url = self.template.zogilib.getDLBaseUrl() |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
329 return url |
| 480 | 330 |
| 331 def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None): | |
| 332 """returns URL to digilib Scaler with params""" | |
| 333 url = None | |
| 334 if docinfo is not None: | |
| 335 url = docinfo.get('imageURL', None) | |
| 336 | |
| 337 if url is None: | |
| 338 url = "%s/servlet/Scaler?"%self.digilibBaseUrl | |
| 339 if fn is None and docinfo is not None: | |
| 340 fn = docinfo.get('imagePath','') | |
| 341 | |
| 342 url += "fn=%s"%fn | |
| 343 | |
| 344 if pn: | |
| 345 url += "&pn=%s"%pn | |
| 346 | |
| 347 url += "&dw=%s&dh=%s"%(dw,dh) | |
| 348 return url | |
| 126 | 349 |
| 350 def getDocumentViewerURL(self): | |
| 351 """returns the URL of this instance""" | |
| 352 return self.absolute_url() | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
353 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
354 def getStyle(self, idx, selected, style=""): |
| 480 | 355 """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
|
356 #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
|
357 if idx == selected: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
358 return style + 'sel' |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
359 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
360 return style |
| 74 | 361 |
| 478 | 362 def getParams(self, param=None, val=None, params=None, duplicates=None): |
| 469 | 363 """returns dict with URL parameters. |
| 364 | |
| 365 Takes URL parameters and additionally param=val or dict params. | |
| 366 Deletes key if value is None.""" | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
367 # copy existing request params |
| 469 | 368 newParams=self.REQUEST.form.copy() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
369 # change single param |
| 25 | 370 if param is not None: |
| 31 | 371 if val is None: |
| 469 | 372 if newParams.has_key(param): |
| 373 del newParams[param] | |
| 25 | 374 else: |
| 469 | 375 newParams[param] = str(val) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
376 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
377 # change more params |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
378 if params is not None: |
| 478 | 379 for (k, v) in params.items(): |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
380 if v is None: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
381 # val=None removes param |
| 469 | 382 if newParams.has_key(k): |
| 383 del newParams[k] | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
384 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
385 else: |
| 469 | 386 newParams[k] = v |
| 478 | 387 |
| 388 if duplicates: | |
| 389 # eliminate lists (coming from duplicate keys) | |
| 390 for (k,v) in newParams.items(): | |
| 391 if isinstance(v, list): | |
| 392 if duplicates == 'comma': | |
| 393 # make comma-separated list of non-empty entries | |
| 394 newParams[k] = ','.join([t for t in v if t]) | |
| 395 elif duplicates == 'first': | |
| 396 # take first non-empty entry | |
| 397 newParams[k] = [t for t in v if t][0] | |
| 398 | |
| 469 | 399 return newParams |
| 400 | |
| 478 | 401 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
| 469 | 402 """returns URL to documentviewer with parameter param set to val or from dict params""" |
| 478 | 403 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
|
404 # quote values and assemble into query string (not escaping '/') |
| 514 | 405 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
|
406 if baseUrl is None: |
| 469 | 407 baseUrl = self.getDocumentViewerURL() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
408 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
409 url = "%s?%s"%(baseUrl, ps) |
| 25 | 410 return url |
| 411 | |
| 478 | 412 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
| 68 | 413 """link to documentviewer with parameter param set to val""" |
| 478 | 414 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
|
415 |
| 526 | 416 |
| 417 def setAvailableLayers(self, newLayerString=None): | |
| 418 """sets availableLayers to newLayerString or tries to autodetect available layers. | |
| 419 assumes layer templates have the form layer_{m}_{l} for layer l in mode m. | |
| 420 newLayerString is parsed as JSON.""" | |
| 421 if newLayerString is not None: | |
| 422 try: | |
| 423 layers = json.loads(newLayerString) | |
| 424 if 'text' in layers and 'images' in layers: | |
| 425 self.availableLayers = layers | |
| 426 return | |
| 427 except: | |
| 428 pass | |
| 429 | |
| 430 logging.error("invalid layers=%s! autodetecting..."%repr(newLayerString)) | |
| 431 | |
| 432 # start with builtin layers | |
| 433 self.availableLayers = self.builtinLayers.copy() | |
| 434 # add layers from templates | |
| 435 for t in self.template: | |
| 436 if t.startswith('layer_'): | |
| 437 try: | |
| 438 (x, m, l) = t.split('_', 3) | |
| 439 if m not in self.availableLayers: | |
| 440 # mode m doesn't exist -> new list | |
| 441 self.availableLayers[m] = [l] | |
| 442 | |
| 443 else: | |
| 444 # m exists -> append | |
| 445 if l not in self.availableLayers[m]: | |
| 446 self.availableLayers[m].append() | |
| 447 | |
| 448 except: | |
| 449 pass | |
| 450 | |
| 451 def getAvailableLayersJson(self): | |
| 452 """returns available layers as JSON string.""" | |
| 453 return json.dumps(self.availableLayers) | |
| 454 | |
| 469 | 455 |
| 57 | 456 def getInfo_xml(self,url,mode): |
| 457 """returns info about the document as XML""" | |
| 458 if not self.digilibBaseUrl: | |
| 514 | 459 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 57 | 460 |
| 461 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 462 pt = getattr(self.template, 'info_xml') | |
| 463 return pt(docinfo=docinfo) | |
| 464 | |
| 528 | 465 def getAuthenticatedUser(self, anon=None): |
| 466 """returns the authenticated user object or None. (ignores Zopes anonymous user)""" | |
| 467 user = getSecurityManager().getUser() | |
| 468 if user is not None and user.getUserName() != "Anonymous User": | |
| 469 return user | |
| 470 else: | |
| 471 return anon | |
| 472 | |
| 35 | 473 def isAccessible(self, docinfo): |
| 32 | 474 """returns if access to the resource is granted""" |
| 475 access = docinfo.get('accessType', None) | |
| 167 | 476 logging.debug("documentViewer (accessOK) access type %s"%access) |
| 465 | 477 if access == 'free': |
| 167 | 478 logging.debug("documentViewer (accessOK) access is free") |
| 32 | 479 return True |
| 465 | 480 |
| 45 | 481 elif access is None or access in self.authgroups: |
| 35 | 482 # only local access -- only logged in users |
| 528 | 483 user = self.getAuthenticatedUser() |
| 167 | 484 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
| 528 | 485 return (user is not None) |
| 32 | 486 |
| 167 | 487 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
| 32 | 488 return False |
| 464 | 489 |
| 490 | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
491 def getDocinfo(self, mode, url, tocMode=None): |
| 464 | 492 """returns docinfo depending on mode""" |
| 493 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) | |
| 494 # look for cached docinfo in session | |
| 495 if self.REQUEST.SESSION.has_key('docinfo'): | |
| 496 docinfo = self.REQUEST.SESSION['docinfo'] | |
| 497 # check if its still current | |
| 498 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: | |
| 499 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
| 500 return docinfo | |
| 501 | |
| 502 # new docinfo | |
| 503 docinfo = {'mode': mode, 'url': url} | |
| 504 # add self url | |
| 505 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
| 477 | 506 docinfo['digilibBaseUrl'] = self.digilibBaseUrl |
| 464 | 507 # get index.meta DOM |
| 508 docUrl = None | |
| 509 metaDom = None | |
| 510 if mode=="texttool": | |
| 511 # url points to document dir or index.meta | |
| 512 metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
| 513 docUrl = url.replace('/index.meta', '') | |
| 514 if metaDom is None: | |
| 515 raise IOError("Unable to find index.meta for mode=texttool!") | |
| 516 | |
| 517 elif mode=="imagepath": | |
| 518 # url points to folder with images, index.meta optional | |
| 519 # asssume index.meta in parent dir | |
| 520 docUrl = getParentPath(url) | |
| 521 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 522 | |
| 523 elif mode=="filepath": | |
| 524 # url points to image file, index.meta optional | |
| 525 # asssume index.meta is two path segments up | |
| 526 docUrl = getParentPath(url, 2) | |
| 527 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 528 | |
| 529 else: | |
| 530 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
| 531 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
| 532 | |
| 533 docinfo['documentUrl'] = docUrl | |
| 534 # process index.meta contents | |
| 473 | 535 if metaDom is not None and metaDom.tag == 'resource': |
| 464 | 536 # document directory name and path |
| 537 resource = self.metadataService.getResourceData(dom=metaDom) | |
| 538 if resource: | |
| 539 docinfo = self.getDocinfoFromResource(docinfo, resource) | |
| 540 | |
| 541 # texttool info | |
| 542 texttool = self.metadataService.getTexttoolData(dom=metaDom) | |
| 543 if texttool: | |
| 544 docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
545 # document info (including toc) from full text |
| 516 | 546 if docinfo.get('textURLPath', None): |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
547 docinfo = self.getTextInfo(mode=tocMode, docinfo=docinfo) |
| 464 | 548 |
| 549 # bib info | |
| 550 bib = self.metadataService.getBibData(dom=metaDom) | |
| 551 if bib: | |
| 552 docinfo = self.getDocinfoFromBib(docinfo, bib) | |
| 465 | 553 else: |
| 554 # no bib - try info.xml | |
| 555 docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) | |
| 464 | 556 |
| 557 # auth info | |
| 558 access = self.metadataService.getAccessData(dom=metaDom) | |
| 559 if access: | |
| 560 docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 561 | |
| 466 | 562 # attribution info |
| 563 attribution = self.metadataService.getAttributionData(dom=metaDom) | |
| 564 if attribution: | |
| 565 logging.debug("getDocinfo: attribution=%s"%repr(attribution)) | |
| 566 docinfo['attribution'] = attribution | |
| 567 #docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 568 | |
| 569 # copyright info | |
| 570 copyright = self.metadataService.getCopyrightData(dom=metaDom) | |
| 571 if copyright: | |
| 572 logging.debug("getDocinfo: copyright=%s"%repr(copyright)) | |
| 573 docinfo['copyright'] = copyright | |
| 574 #docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 575 | |
| 464 | 576 # image path |
| 577 if mode != 'texttool': | |
| 516 | 578 # override image path from texttool with url TODO: how about mode=auto? |
| 465 | 579 docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1) |
| 464 | 580 |
| 581 # number of images from digilib | |
| 582 if docinfo.get('imagePath', None): | |
| 583 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath'] | |
| 584 docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath']) | |
| 585 | |
| 516 | 586 # check numPages |
| 587 if docinfo.get('numPages', 0) == 0: | |
| 588 if docinfo.get('numTextPages', 0) > 0: | |
| 589 # replace with numTextPages (text-only?) | |
| 590 docinfo['numPages'] = docinfo['numTextPages'] | |
| 591 | |
| 464 | 592 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
| 593 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) | |
| 594 # store in session | |
| 595 self.REQUEST.SESSION['docinfo'] = docinfo | |
| 596 return docinfo | |
| 597 | |
| 516 | 598 |
| 464 | 599 def getDocinfoFromResource(self, docinfo, resource): |
| 600 """reads contents of resource element into docinfo""" | |
| 601 docName = resource.get('name', None) | |
| 602 docinfo['documentName'] = docName | |
| 603 docPath = resource.get('archive-path', None) | |
| 604 if docPath: | |
| 605 # clean up document path | |
| 606 if docPath[0] != '/': | |
| 607 docPath = '/' + docPath | |
| 608 | |
| 609 if docName and (not docPath.endswith(docName)): | |
| 610 docPath += "/" + docName | |
| 611 | |
| 612 else: | |
| 613 # use docUrl as docPath | |
| 614 docUrl = docinfo['documentURL'] | |
| 615 if not docUrl.startswith('http:'): | |
| 616 docPath = docUrl | |
| 465 | 617 if docPath: |
| 618 # fix URLs starting with /mpiwg/online | |
| 619 docPath = docPath.replace('/mpiwg/online', '', 1) | |
| 620 | |
| 464 | 621 docinfo['documentPath'] = docPath |
| 622 return docinfo | |
| 623 | |
| 624 def getDocinfoFromTexttool(self, docinfo, texttool): | |
| 625 """reads contents of texttool element into docinfo""" | |
| 626 # image dir | |
| 627 imageDir = texttool.get('image', None) | |
| 628 docPath = docinfo.get('documentPath', None) | |
| 629 if imageDir and docPath: | |
| 630 #print "image: ", imageDir, " archivepath: ", archivePath | |
| 631 imageDir = os.path.join(docPath, imageDir) | |
| 632 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
| 633 docinfo['imagePath'] = imageDir | |
| 634 | |
| 635 # old style text URL | |
| 636 textUrl = texttool.get('text', None) | |
| 637 if textUrl and docPath: | |
| 638 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
| 639 textUrl = os.path.join(docPath, textUrl) | |
| 640 | |
| 641 docinfo['textURL'] = textUrl | |
| 642 | |
| 643 # new style text-url-path | |
| 644 textUrl = texttool.get('text-url-path', None) | |
| 645 if textUrl: | |
| 646 docinfo['textURLPath'] = textUrl | |
| 468 | 647 |
| 648 # page flow | |
| 649 docinfo['pageFlow'] = texttool.get('page-flow', 'ltr') | |
| 650 | |
| 651 # odd pages are left | |
| 476 | 652 docinfo['oddPage'] = texttool.get('odd-scan-position', 'left') |
| 468 | 653 |
| 469 | 654 # number of title page (0: not defined) |
| 468 | 655 docinfo['titlePage'] = texttool.get('title-scan-no', 0) |
| 464 | 656 |
| 657 # old presentation stuff | |
| 658 presentation = texttool.get('presentation', None) | |
| 659 if presentation and docPath: | |
| 465 | 660 if presentation.startswith('http:'): |
| 661 docinfo['presentationUrl'] = presentation | |
| 662 else: | |
| 663 docinfo['presentationUrl'] = os.path.join(docPath, presentation) | |
| 464 | 664 |
| 468 | 665 |
| 464 | 666 return docinfo |
| 667 | |
| 668 def getDocinfoFromBib(self, docinfo, bib): | |
| 669 """reads contents of bib element into docinfo""" | |
| 465 | 670 logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
| 464 | 671 # put all raw bib fields in dict "bib" |
| 672 docinfo['bib'] = bib | |
| 673 bibtype = bib.get('@type', None) | |
| 674 docinfo['bibType'] = bibtype | |
| 675 # also store DC metadata for convenience | |
| 676 dc = self.metadataService.getDCMappedData(bib) | |
| 677 docinfo['creator'] = dc.get('creator',None) | |
| 678 docinfo['title'] = dc.get('title',None) | |
| 679 docinfo['date'] = dc.get('date',None) | |
| 680 return docinfo | |
| 681 | |
| 682 def getDocinfoFromAccess(self, docinfo, acc): | |
| 683 """reads contents of access element into docinfo""" | |
| 684 #TODO: also read resource type | |
| 465 | 685 logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
| 464 | 686 try: |
| 465 | 687 acctype = acc['@attr']['type'] |
| 464 | 688 if acctype: |
| 689 access=acctype | |
| 690 if access in ['group', 'institution']: | |
| 691 access = acc['name'].lower() | |
| 692 | |
| 693 docinfo['accessType'] = access | |
| 694 | |
| 695 except: | |
| 696 pass | |
| 697 | |
| 698 return docinfo | |
| 699 | |
| 700 def getDocinfoFromDigilib(self, docinfo, path): | |
| 701 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path | |
| 702 # fetch data | |
| 703 txt = getHttpData(infoUrl) | |
| 704 if not txt: | |
| 705 logging.error("Unable to get dir-info from %s"%(infoUrl)) | |
| 706 return docinfo | |
| 707 | |
| 708 dom = ET.fromstring(txt) | |
| 709 size = getText(dom.find("size")) | |
| 710 logging.debug("getDocinfoFromDigilib: size=%s"%size) | |
| 711 if size: | |
| 712 docinfo['numPages'] = int(size) | |
| 713 else: | |
| 714 docinfo['numPages'] = 0 | |
| 715 | |
| 716 # TODO: produce and keep list of image names and numbers | |
| 717 return docinfo | |
| 718 | |
| 719 | |
| 465 | 720 def getDocinfoFromPresentationInfoXml(self,docinfo): |
| 721 """gets DC-like bibliographical information from the presentation entry in texttools""" | |
| 722 url = docinfo.get('presentationUrl', None) | |
| 723 if not url: | |
| 724 logging.error("getDocinfoFromPresentation: no URL!") | |
| 725 return docinfo | |
| 726 | |
| 727 dom = None | |
| 728 metaUrl = None | |
| 729 if url.startswith("http://"): | |
| 730 # real URL | |
| 731 metaUrl = url | |
| 732 else: | |
| 733 # online path | |
| 734 | |
| 735 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 736 metaUrl=server+url | |
| 737 | |
| 738 txt=getHttpData(metaUrl) | |
| 739 if txt is None: | |
| 740 logging.error("Unable to read info.xml from %s"%(url)) | |
| 741 return docinfo | |
| 742 | |
| 743 dom = ET.fromstring(txt) | |
| 744 docinfo['creator']=getText(dom.find(".//author")) | |
| 745 docinfo['title']=getText(dom.find(".//title")) | |
| 746 docinfo['date']=getText(dom.find(".//date")) | |
| 747 return docinfo | |
| 748 | |
| 749 | |
| 503 | 750 def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewLayer=None, tocMode=None): |
| 22 | 751 """returns pageinfo with the given parameters""" |
| 503 | 752 logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewLayer=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewLayer,tocMode)) |
| 22 | 753 pageinfo = {} |
| 471 | 754 pageinfo['viewMode'] = viewMode |
| 508 | 755 # split viewLayer if necessary |
| 756 if isinstance(viewLayer,basestring): | |
| 757 viewLayer = viewLayer.split(',') | |
| 758 | |
| 759 if isinstance(viewLayer, list): | |
| 760 logging.debug("getPageinfo: viewLayer is list:%s"%viewLayer) | |
| 761 # save (unique) list in viewLayers | |
| 762 seen = set() | |
| 763 viewLayers = [l for l in viewLayer if l and l not in seen and not seen.add(l)] | |
| 764 pageinfo['viewLayers'] = viewLayers | |
| 765 # stringify viewLayer | |
| 766 viewLayer = ','.join(viewLayers) | |
| 767 else: | |
| 768 #create list | |
| 769 pageinfo['viewLayers'] = [viewLayer] | |
| 770 | |
| 503 | 771 pageinfo['viewLayer'] = viewLayer |
| 471 | 772 pageinfo['tocMode'] = tocMode |
| 773 | |
| 516 | 774 # TODO: unify current and pn! |
| 25 | 775 current = getInt(current) |
| 776 pageinfo['current'] = current | |
| 480 | 777 pageinfo['pn'] = current |
| 25 | 778 rows = int(rows or self.thumbrows) |
| 779 pageinfo['rows'] = rows | |
| 780 cols = int(cols or self.thumbcols) | |
| 781 pageinfo['cols'] = cols | |
| 782 grpsize = cols * rows | |
| 783 pageinfo['groupsize'] = grpsize | |
| 476 | 784 # is start is empty use one around current |
| 61 | 785 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
| 786 # int(current / grpsize) * grpsize +1)) | |
| 22 | 787 pageinfo['start'] = start |
| 511 | 788 # get number of pages |
| 469 | 789 np = int(docinfo.get('numPages', 0)) |
| 790 if np == 0: | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
791 # try numTextPages |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
792 np = docinfo.get('numTextPages', 0) |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
793 if np != 0: |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
794 docinfo['numPages'] = np |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
795 |
| 511 | 796 # cache table of contents |
| 797 pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) | |
| 469 | 798 pageinfo['numgroups'] = int(np / grpsize) |
| 799 if np % grpsize > 0: | |
| 800 pageinfo['numgroups'] += 1 | |
| 476 | 801 |
| 802 pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' | |
| 803 oddScanLeft = docinfo.get('oddPage', 'left') != 'right' | |
| 804 # add zeroth page for two columns | |
| 805 pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) | |
| 806 pageinfo['pageZero'] = pageZero | |
| 480 | 807 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np) |
| 516 | 808 # more page parameters |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
809 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
| 516 | 810 if docinfo.get('pageNumbers'): |
| 811 # get original page numbers | |
| 812 pageNumber = docinfo['pageNumbers'].get(current, None) | |
| 813 if pageNumber is not None: | |
| 814 pageinfo['pageNumberOrig'] = pageNumber['no'] | |
| 815 pageinfo['pageNumberOrigNorm'] = pageNumber['non'] | |
| 158 | 816 |
| 511 | 817 # cache search results |
| 818 pageinfo['resultPageSize'] = getInt(self.REQUEST.get('resultPageSize', 10)) | |
| 819 query = self.REQUEST.get('query',None) | |
| 820 pageinfo['query'] = query | |
| 821 if query: | |
| 822 queryType = self.REQUEST.get('queryType', 'fulltextMorph') | |
| 823 pageinfo['queryType'] = queryType | |
| 824 pageinfo['resultStart'] = getInt(self.REQUEST.get('resultStart', '1')) | |
| 825 self.getSearchResults(mode=queryType, query=query, pageinfo=pageinfo, docinfo=docinfo) | |
| 826 | |
| 827 # highlighting | |
| 828 highlightQuery = self.REQUEST.get('highlightQuery', None) | |
| 829 if highlightQuery: | |
| 830 pageinfo['highlightQuery'] = highlightQuery | |
| 831 pageinfo['highlightElement'] = self.REQUEST.get('highlightElement', '') | |
| 832 pageinfo['highlightElementPos'] = self.REQUEST.get('highlightElementPos', '') | |
| 460 | 833 |
| 22 | 834 return pageinfo |
| 460 | 835 |
| 463 | 836 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
837 def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0): |
| 480 | 838 """returns dict with array of page informations for one screenfull of thumbnails""" |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
839 batch = {} |
| 480 | 840 grpsize = rows * cols |
| 476 | 841 if maxIdx == 0: |
| 480 | 842 maxIdx = start + grpsize |
| 476 | 843 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
844 nb = int(math.ceil(maxIdx / float(grpsize))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
845 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
846 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
847 if pageZero: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
848 ofs = 0 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
849 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
850 ofs = 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
851 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
852 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
853 s = i * grpsize + ofs |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
854 e = min((i + 1) * grpsize + ofs - 1, maxIdx) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
855 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
856 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
857 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
858 |
| 476 | 859 pages = [] |
| 860 if pageZero and start == 1: | |
| 861 # correct beginning | |
| 862 idx = 0 | |
| 863 else: | |
| 864 idx = start | |
| 865 | |
| 866 for r in range(rows): | |
| 867 row = [] | |
| 868 for c in range(cols): | |
| 869 if idx < minIdx or idx > maxIdx: | |
| 870 page = {'idx':None} | |
| 871 else: | |
| 872 page = {'idx':idx} | |
| 873 | |
| 874 idx += 1 | |
| 875 if pageFlowLtr: | |
| 876 row.append(page) | |
| 877 else: | |
| 878 row.insert(0, page) | |
| 879 | |
| 880 pages.append(row) | |
| 881 | |
| 480 | 882 if start > 1: |
| 883 batch['prevStart'] = max(start - grpsize, 1) | |
| 884 else: | |
| 885 batch['prevStart'] = None | |
| 886 | |
| 526 | 887 if start + grpsize <= maxIdx: |
| 480 | 888 batch['nextStart'] = start + grpsize |
| 889 else: | |
| 890 batch['nextStart'] = None | |
| 891 | |
| 892 batch['pages'] = pages | |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
893 return batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
894 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
895 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
|
896 """returns dict with information for one screenfull of data.""" |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
897 batch = {} |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
898 if end == 0: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
899 end = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
900 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
901 nb = int(math.ceil(end / float(size))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
902 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
903 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
904 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
905 s = i * size + 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
906 e = min((i + 1) * size, end) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
907 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
908 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
909 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
910 # list of elements in this batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
911 this = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
912 j = 0 |
| 526 | 913 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
|
914 if data: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
915 if fullData: |
| 526 | 916 d = data.get(i, None) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
917 else: |
| 526 | 918 d = data.get(j, None) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
919 j += 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
920 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
921 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
922 d = i+1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
923 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
924 this.append(d) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
925 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
926 batch['this'] = this |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
927 if start > 1: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
928 batch['prevStart'] = max(start - size, 1) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
929 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
930 batch['prevStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
931 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
932 if start + size < end: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
933 batch['nextStart'] = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
934 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
935 batch['nextStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
936 |
| 526 | 937 logging.debug("getBatch start=%s size=%s end=%s batch=%s"%(start,size,end,repr(batch))) |
| 480 | 938 return batch |
| 476 | 939 |
| 940 | |
| 463 | 941 security.declareProtected('View management screens','changeDocumentViewerForm') |
| 942 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 22 | 943 |
| 526 | 944 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',availableLayers=None,RESPONSE=None): |
| 22 | 945 """init document viewer""" |
| 946 self.title=title | |
| 947 self.digilibBaseUrl = digilibBaseUrl | |
| 25 | 948 self.thumbrows = thumbrows |
| 949 self.thumbcols = thumbcols | |
| 32 | 950 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| 463 | 951 try: |
| 952 # assume MetaDataFolder instance is called metadata | |
| 953 self.metadataService = getattr(self, 'metadata') | |
| 954 except Exception, e: | |
| 955 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 526 | 956 |
| 957 self.setAvailableLayers(availableLayers) | |
| 463 | 958 |
| 22 | 959 if RESPONSE is not None: |
| 960 RESPONSE.redirect('manage_main') | |
| 0 | 961 |
| 962 def manage_AddDocumentViewerForm(self): | |
| 963 """add the viewer form""" | |
| 22 | 964 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| 0 | 965 return pt() |
| 966 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
967 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
| 0 | 968 """add the viewer""" |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
969 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
| 0 | 970 self._setObject(id,newObj) |
| 971 | |
| 972 if RESPONSE is not None: | |
| 973 RESPONSE.redirect('manage_main') |