Mercurial > hg > documentViewer
annotate documentViewer.py @ 526:3f375a048402
moved search and dict into separate layers.
removed search_template.
added tocMode=concordance.
fixed bug with paging tocs.
| author | casties |
|---|---|
| date | Tue, 10 Apr 2012 19:41:44 +0200 |
| parents | 70c3ae5eac7c |
| children | f8a5f63eafc0 |
| 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()) |
| 525 | 126 # available layer types |
| 526 | 127 builtinLayers = {'text': ['dict','search','gis','annotator'], |
| 128 'xml': None, 'images': None, 'index': None} | |
| 129 availableLayers = builtinLayers; | |
| 525 | 130 # layer templates |
| 526 | 131 layer_text_dict = PageTemplateFile('zpt/layer_text_dict', globals()) |
| 132 layer_text_search = PageTemplateFile('zpt/layer_text_search', globals()) | |
| 525 | 133 layer_text_annotator = PageTemplateFile('zpt/layer_text_annotator', globals()) |
| 134 layer_text_gis = PageTemplateFile('zpt/layer_text_gis', globals()) | |
| 135 # toc templates | |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
136 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
|
137 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
|
138 toc_figures = PageTemplateFile('zpt/toc_figures', globals()) |
| 526 | 139 toc_concordance = PageTemplateFile('zpt/toc_concordance', globals()) |
| 491 | 140 toc_none = PageTemplateFile('zpt/toc_none', globals()) |
| 525 | 141 # other templates |
| 501 | 142 common_template = PageTemplateFile('zpt/common_template', globals()) |
| 57 | 143 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
| 487 | 144 docuviewer_css = ImageFile('css/docuviewer.css',globals()) |
|
489
55e3398e395e
more new templates. monkey-patch for App.ImageFile.
casties
parents:
488
diff
changeset
|
145 # make ImageFile better for development |
|
490
6f116b86a226
more new template stuff. moved ImageFile index method to SrvTxtUtils
casties
parents:
489
diff
changeset
|
146 docuviewer_css.index_html = refreshingImageFileIndexHtml |
| 501 | 147 jquery_js = ImageFile('js/jquery.js',globals()) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
148 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
149 |
| 95 | 150 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
| 0 | 151 """init document viewer""" |
| 152 self.id=id | |
| 153 self.title=title | |
| 25 | 154 self.thumbcols = thumbcols |
| 155 self.thumbrows = thumbrows | |
| 32 | 156 # authgroups is list of authorized groups (delimited by ,) |
| 157 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
|
158 # 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
|
159 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
160 templateFolder = Folder('template') |
| 498 | 161 self['template'] = templateFolder # Zope-2.12 style |
| 162 #self._setObject('template',templateFolder) # old style | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
163 try: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
164 import MpdlXmlTextServer |
| 132 | 165 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
| 498 | 166 templateFolder['fulltextclient'] = textServer |
| 167 #templateFolder._setObject('fulltextclient',textServer) | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
168 except Exception, e: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
169 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
| 463 | 170 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
171 try: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
172 from Products.zogiLib.zogiLib import zogiLib |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
173 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
| 498 | 174 templateFolder['zogilib'] = zogilib |
| 175 #templateFolder._setObject('zogilib',zogilib) | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
176 except Exception, e: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
177 logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
| 463 | 178 |
| 179 try: | |
| 180 # assume MetaDataFolder instance is called metadata | |
| 181 self.metadataService = getattr(self, 'metadata') | |
| 182 except Exception, e: | |
| 183 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 184 | |
| 477 | 185 if digilibBaseUrl is not None: |
| 186 self.digilibBaseUrl = digilibBaseUrl | |
| 187 | |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
188 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
189 # proxy text server methods to fulltextclient |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
190 def getTextPage(self, **args): |
| 498 | 191 """returns full text content of page""" |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
192 return self.template.fulltextclient.getTextPage(**args) |
| 22 | 193 |
| 508 | 194 def getSearchResults(self, **args): |
| 195 """loads list of search results and stores XML in docinfo""" | |
| 196 return self.template.fulltextclient.getSearchResults(**args) | |
| 197 | |
| 198 def getResultsPage(self, **args): | |
| 199 """returns one page of the search results""" | |
| 200 return self.template.fulltextclient.getResultsPage(**args) | |
| 201 | |
| 516 | 202 def getTextInfo(self, **args): |
| 203 """returns document info from the text server""" | |
| 204 return self.template.fulltextclient.getTextInfo(**args) | |
| 205 | |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
206 def getToc(self, **args): |
| 508 | 207 """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
|
208 return self.template.fulltextclient.getToc(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
209 |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
210 def getTocPage(self, **args): |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
211 """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
|
212 return self.template.fulltextclient.getTocPage(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
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 |
| 498 | 218 #WTF? |
|
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 | |
| 226 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
| 227 | |
| 228 ''' | |
| 167 | 229 logging.debug("HHHHHHHHHHHHHH:load the rss") |
| 458 | 230 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| 68 | 231 |
| 232 if not hasattr(self, 'template'): | |
| 233 # create template folder if it doesn't exist | |
| 234 self.manage_addFolder('template') | |
| 235 | |
| 236 if not self.digilibBaseUrl: | |
| 237 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 238 | |
| 239 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 338 | 240 #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
| 345 | 241 pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) |
| 331 | 242 ''' ZDES ''' |
| 68 | 243 pt = getattr(self.template, 'thumbs_main_rss') |
| 244 | |
| 245 if viewMode=="auto": # automodus gewaehlt | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
246 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
| 68 | 247 viewMode="text" |
| 248 else: | |
| 249 viewMode="images" | |
| 250 | |
| 251 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
| 465 | 252 |
| 68 | 253 |
| 22 | 254 security.declareProtected('View','index_html') |
| 503 | 255 def index_html(self,url,mode="texttool",viewMode="auto",viewLayer=None,tocMode="thumbs",start=1,pn=1): |
| 464 | 256 """ |
| 471 | 257 view page |
| 258 @param url: url which contains display information | |
| 57 | 259 @param mode: defines how to access the document behind url |
| 503 | 260 @param viewMode: 'images': display images, 'text': display text, 'xml': display xml, default is 'auto' |
| 261 @param viewLayer: sub-type of viewMode, e.g. 'dict' for viewMode='text' | |
| 99 | 262 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
| 464 | 263 """ |
| 0 | 264 |
| 503 | 265 logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewLayer=%s start=%s pn=%s"%(mode,url,viewMode,viewLayer,start,pn)) |
| 22 | 266 |
| 267 if not hasattr(self, 'template'): | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
268 # this won't work |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
269 logging.error("template folder missing!") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
270 return "ERROR: template folder missing!" |
| 22 | 271 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
272 if not getattr(self, 'digilibBaseUrl', None): |
| 132 | 273 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 22 | 274 |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
275 docinfo = self.getDocinfo(mode=mode,url=url,tocMode=tocMode) |
| 97 | 276 |
| 471 | 277 # auto viewMode: text if there is a text else images |
| 455 | 278 if viewMode=="auto": |
| 279 if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): | |
| 471 | 280 viewMode = "text" |
| 508 | 281 if viewLayer is None: |
| 282 viewLayer = "dict" | |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
283 else: |
| 471 | 284 viewMode = "images" |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
285 |
| 474 | 286 elif viewMode == "text_dict": |
| 287 # legacy fix | |
| 288 viewMode = "text" | |
| 503 | 289 viewLayer = "dict" |
| 474 | 290 |
| 503 | 291 pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode) |
| 469 | 292 |
| 475 | 293 # get template /template/viewer_$viewMode |
| 294 pt = getattr(self.template, 'viewer_%s'%viewMode, None) | |
| 295 if pt is None: | |
| 296 logging.error("No template for viewMode=%s!"%viewMode) | |
| 297 # TODO: error page? | |
| 298 return "No template for viewMode=%s!"%viewMode | |
| 299 | |
| 455 | 300 # and execute with parameters |
| 471 | 301 return pt(docinfo=docinfo, pageinfo=pageinfo) |
| 0 | 302 |
| 506 | 303 #WTF? |
| 74 | 304 def generateMarks(self,mk): |
| 305 ret="" | |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
306 if mk is None: |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
307 return "" |
| 134 | 308 if not isinstance(mk, list): |
| 132 | 309 mk=[mk] |
| 74 | 310 for m in mk: |
|
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
311 ret+="mk=%s"%m |
| 74 | 312 return ret |
| 389 | 313 |
| 314 | |
| 525 | 315 def getAvailableLayers(self): |
| 316 """returns dict with list of available layers per viewMode""" | |
| 317 return self.availableLayers | |
| 318 | |
| 387 | 319 def getBrowser(self): |
| 320 """getBrowser the version of browser """ | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
321 bt = browserCheck(self) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
322 logging.debug("BROWSER VERSION: %s"%(bt)) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
323 return bt |
| 387 | 324 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
325 def findDigilibUrl(self): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
326 """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
|
327 url = self.template.zogilib.getDLBaseUrl() |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
328 return url |
| 480 | 329 |
| 330 def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None): | |
| 331 """returns URL to digilib Scaler with params""" | |
| 332 url = None | |
| 333 if docinfo is not None: | |
| 334 url = docinfo.get('imageURL', None) | |
| 335 | |
| 336 if url is None: | |
| 337 url = "%s/servlet/Scaler?"%self.digilibBaseUrl | |
| 338 if fn is None and docinfo is not None: | |
| 339 fn = docinfo.get('imagePath','') | |
| 340 | |
| 341 url += "fn=%s"%fn | |
| 342 | |
| 343 if pn: | |
| 344 url += "&pn=%s"%pn | |
| 345 | |
| 346 url += "&dw=%s&dh=%s"%(dw,dh) | |
| 347 return url | |
| 126 | 348 |
| 349 def getDocumentViewerURL(self): | |
| 350 """returns the URL of this instance""" | |
| 351 return self.absolute_url() | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
352 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
353 def getStyle(self, idx, selected, style=""): |
| 480 | 354 """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
|
355 #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
|
356 if idx == selected: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
357 return style + 'sel' |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
358 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
359 return style |
| 74 | 360 |
| 478 | 361 def getParams(self, param=None, val=None, params=None, duplicates=None): |
| 469 | 362 """returns dict with URL parameters. |
| 363 | |
| 364 Takes URL parameters and additionally param=val or dict params. | |
| 365 Deletes key if value is None.""" | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
366 # copy existing request params |
| 469 | 367 newParams=self.REQUEST.form.copy() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
368 # change single param |
| 25 | 369 if param is not None: |
| 31 | 370 if val is None: |
| 469 | 371 if newParams.has_key(param): |
| 372 del newParams[param] | |
| 25 | 373 else: |
| 469 | 374 newParams[param] = str(val) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
375 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
376 # change more params |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
377 if params is not None: |
| 478 | 378 for (k, v) in params.items(): |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
379 if v is None: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
380 # val=None removes param |
| 469 | 381 if newParams.has_key(k): |
| 382 del newParams[k] | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
383 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
384 else: |
| 469 | 385 newParams[k] = v |
| 478 | 386 |
| 387 if duplicates: | |
| 388 # eliminate lists (coming from duplicate keys) | |
| 389 for (k,v) in newParams.items(): | |
| 390 if isinstance(v, list): | |
| 391 if duplicates == 'comma': | |
| 392 # make comma-separated list of non-empty entries | |
| 393 newParams[k] = ','.join([t for t in v if t]) | |
| 394 elif duplicates == 'first': | |
| 395 # take first non-empty entry | |
| 396 newParams[k] = [t for t in v if t][0] | |
| 397 | |
| 469 | 398 return newParams |
| 399 | |
| 478 | 400 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
| 469 | 401 """returns URL to documentviewer with parameter param set to val or from dict params""" |
| 478 | 402 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
|
403 # quote values and assemble into query string (not escaping '/') |
| 514 | 404 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
|
405 if baseUrl is None: |
| 469 | 406 baseUrl = self.getDocumentViewerURL() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
407 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
408 url = "%s?%s"%(baseUrl, ps) |
| 25 | 409 return url |
| 410 | |
| 478 | 411 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
| 68 | 412 """link to documentviewer with parameter param set to val""" |
| 478 | 413 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
|
414 |
| 526 | 415 |
| 416 def setAvailableLayers(self, newLayerString=None): | |
| 417 """sets availableLayers to newLayerString or tries to autodetect available layers. | |
| 418 assumes layer templates have the form layer_{m}_{l} for layer l in mode m. | |
| 419 newLayerString is parsed as JSON.""" | |
| 420 if newLayerString is not None: | |
| 421 try: | |
| 422 layers = json.loads(newLayerString) | |
| 423 if 'text' in layers and 'images' in layers: | |
| 424 self.availableLayers = layers | |
| 425 return | |
| 426 except: | |
| 427 pass | |
| 428 | |
| 429 logging.error("invalid layers=%s! autodetecting..."%repr(newLayerString)) | |
| 430 | |
| 431 # start with builtin layers | |
| 432 self.availableLayers = self.builtinLayers.copy() | |
| 433 # add layers from templates | |
| 434 for t in self.template: | |
| 435 if t.startswith('layer_'): | |
| 436 try: | |
| 437 (x, m, l) = t.split('_', 3) | |
| 438 if m not in self.availableLayers: | |
| 439 # mode m doesn't exist -> new list | |
| 440 self.availableLayers[m] = [l] | |
| 441 | |
| 442 else: | |
| 443 # m exists -> append | |
| 444 if l not in self.availableLayers[m]: | |
| 445 self.availableLayers[m].append() | |
| 446 | |
| 447 except: | |
| 448 pass | |
| 449 | |
| 450 def getAvailableLayersJson(self): | |
| 451 """returns available layers as JSON string.""" | |
| 452 return json.dumps(self.availableLayers) | |
| 453 | |
| 469 | 454 |
| 57 | 455 def getInfo_xml(self,url,mode): |
| 456 """returns info about the document as XML""" | |
| 457 if not self.digilibBaseUrl: | |
| 514 | 458 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 57 | 459 |
| 460 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 461 pt = getattr(self.template, 'info_xml') | |
| 462 return pt(docinfo=docinfo) | |
| 463 | |
| 35 | 464 def isAccessible(self, docinfo): |
| 32 | 465 """returns if access to the resource is granted""" |
| 466 access = docinfo.get('accessType', None) | |
| 167 | 467 logging.debug("documentViewer (accessOK) access type %s"%access) |
| 465 | 468 if access == 'free': |
| 167 | 469 logging.debug("documentViewer (accessOK) access is free") |
| 32 | 470 return True |
| 465 | 471 |
| 45 | 472 elif access is None or access in self.authgroups: |
| 35 | 473 # only local access -- only logged in users |
| 474 user = getSecurityManager().getUser() | |
| 167 | 475 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
| 35 | 476 if user is not None: |
| 477 #print "user: ", user | |
| 478 return (user.getUserName() != "Anonymous User") | |
| 479 else: | |
| 480 return False | |
| 32 | 481 |
| 167 | 482 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
| 32 | 483 return False |
| 35 | 484 |
| 464 | 485 |
| 486 | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
487 def getDocinfo(self, mode, url, tocMode=None): |
| 464 | 488 """returns docinfo depending on mode""" |
| 489 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) | |
| 490 # look for cached docinfo in session | |
| 491 if self.REQUEST.SESSION.has_key('docinfo'): | |
| 492 docinfo = self.REQUEST.SESSION['docinfo'] | |
| 493 # check if its still current | |
| 494 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: | |
| 495 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
| 496 return docinfo | |
| 497 | |
| 498 # new docinfo | |
| 499 docinfo = {'mode': mode, 'url': url} | |
| 500 # add self url | |
| 501 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
| 477 | 502 docinfo['digilibBaseUrl'] = self.digilibBaseUrl |
| 464 | 503 # get index.meta DOM |
| 504 docUrl = None | |
| 505 metaDom = None | |
| 506 if mode=="texttool": | |
| 507 # url points to document dir or index.meta | |
| 508 metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
| 509 docUrl = url.replace('/index.meta', '') | |
| 510 if metaDom is None: | |
| 511 raise IOError("Unable to find index.meta for mode=texttool!") | |
| 512 | |
| 513 elif mode=="imagepath": | |
| 514 # url points to folder with images, index.meta optional | |
| 515 # asssume index.meta in parent dir | |
| 516 docUrl = getParentPath(url) | |
| 517 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 518 | |
| 519 elif mode=="filepath": | |
| 520 # url points to image file, index.meta optional | |
| 521 # asssume index.meta is two path segments up | |
| 522 docUrl = getParentPath(url, 2) | |
| 523 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 524 | |
| 525 else: | |
| 526 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
| 527 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
| 528 | |
| 529 docinfo['documentUrl'] = docUrl | |
| 530 # process index.meta contents | |
| 473 | 531 if metaDom is not None and metaDom.tag == 'resource': |
| 464 | 532 # document directory name and path |
| 533 resource = self.metadataService.getResourceData(dom=metaDom) | |
| 534 if resource: | |
| 535 docinfo = self.getDocinfoFromResource(docinfo, resource) | |
| 536 | |
| 537 # texttool info | |
| 538 texttool = self.metadataService.getTexttoolData(dom=metaDom) | |
| 539 if texttool: | |
| 540 docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
541 # document info (including toc) from full text |
| 516 | 542 if docinfo.get('textURLPath', None): |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
543 docinfo = self.getTextInfo(mode=tocMode, docinfo=docinfo) |
| 464 | 544 |
| 545 # bib info | |
| 546 bib = self.metadataService.getBibData(dom=metaDom) | |
| 547 if bib: | |
| 548 docinfo = self.getDocinfoFromBib(docinfo, bib) | |
| 465 | 549 else: |
| 550 # no bib - try info.xml | |
| 551 docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) | |
| 464 | 552 |
| 553 # auth info | |
| 554 access = self.metadataService.getAccessData(dom=metaDom) | |
| 555 if access: | |
| 556 docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 557 | |
| 466 | 558 # attribution info |
| 559 attribution = self.metadataService.getAttributionData(dom=metaDom) | |
| 560 if attribution: | |
| 561 logging.debug("getDocinfo: attribution=%s"%repr(attribution)) | |
| 562 docinfo['attribution'] = attribution | |
| 563 #docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 564 | |
| 565 # copyright info | |
| 566 copyright = self.metadataService.getCopyrightData(dom=metaDom) | |
| 567 if copyright: | |
| 568 logging.debug("getDocinfo: copyright=%s"%repr(copyright)) | |
| 569 docinfo['copyright'] = copyright | |
| 570 #docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 571 | |
| 464 | 572 # image path |
| 573 if mode != 'texttool': | |
| 516 | 574 # override image path from texttool with url TODO: how about mode=auto? |
| 465 | 575 docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1) |
| 464 | 576 |
| 577 # number of images from digilib | |
| 578 if docinfo.get('imagePath', None): | |
| 579 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath'] | |
| 580 docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath']) | |
| 581 | |
| 516 | 582 # check numPages |
| 583 if docinfo.get('numPages', 0) == 0: | |
| 584 if docinfo.get('numTextPages', 0) > 0: | |
| 585 # replace with numTextPages (text-only?) | |
| 586 docinfo['numPages'] = docinfo['numTextPages'] | |
| 587 | |
| 464 | 588 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
| 589 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) | |
| 590 # store in session | |
| 591 self.REQUEST.SESSION['docinfo'] = docinfo | |
| 592 return docinfo | |
| 593 | |
| 516 | 594 |
| 464 | 595 def getDocinfoFromResource(self, docinfo, resource): |
| 596 """reads contents of resource element into docinfo""" | |
| 597 docName = resource.get('name', None) | |
| 598 docinfo['documentName'] = docName | |
| 599 docPath = resource.get('archive-path', None) | |
| 600 if docPath: | |
| 601 # clean up document path | |
| 602 if docPath[0] != '/': | |
| 603 docPath = '/' + docPath | |
| 604 | |
| 605 if docName and (not docPath.endswith(docName)): | |
| 606 docPath += "/" + docName | |
| 607 | |
| 608 else: | |
| 609 # use docUrl as docPath | |
| 610 docUrl = docinfo['documentURL'] | |
| 611 if not docUrl.startswith('http:'): | |
| 612 docPath = docUrl | |
| 465 | 613 if docPath: |
| 614 # fix URLs starting with /mpiwg/online | |
| 615 docPath = docPath.replace('/mpiwg/online', '', 1) | |
| 616 | |
| 464 | 617 docinfo['documentPath'] = docPath |
| 618 return docinfo | |
| 619 | |
| 620 def getDocinfoFromTexttool(self, docinfo, texttool): | |
| 621 """reads contents of texttool element into docinfo""" | |
| 622 # image dir | |
| 623 imageDir = texttool.get('image', None) | |
| 624 docPath = docinfo.get('documentPath', None) | |
| 625 if imageDir and docPath: | |
| 626 #print "image: ", imageDir, " archivepath: ", archivePath | |
| 627 imageDir = os.path.join(docPath, imageDir) | |
| 628 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
| 629 docinfo['imagePath'] = imageDir | |
| 630 | |
| 631 # old style text URL | |
| 632 textUrl = texttool.get('text', None) | |
| 633 if textUrl and docPath: | |
| 634 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
| 635 textUrl = os.path.join(docPath, textUrl) | |
| 636 | |
| 637 docinfo['textURL'] = textUrl | |
| 638 | |
| 639 # new style text-url-path | |
| 640 textUrl = texttool.get('text-url-path', None) | |
| 641 if textUrl: | |
| 642 docinfo['textURLPath'] = textUrl | |
| 468 | 643 |
| 644 # page flow | |
| 645 docinfo['pageFlow'] = texttool.get('page-flow', 'ltr') | |
| 646 | |
| 647 # odd pages are left | |
| 476 | 648 docinfo['oddPage'] = texttool.get('odd-scan-position', 'left') |
| 468 | 649 |
| 469 | 650 # number of title page (0: not defined) |
| 468 | 651 docinfo['titlePage'] = texttool.get('title-scan-no', 0) |
| 464 | 652 |
| 653 # old presentation stuff | |
| 654 presentation = texttool.get('presentation', None) | |
| 655 if presentation and docPath: | |
| 465 | 656 if presentation.startswith('http:'): |
| 657 docinfo['presentationUrl'] = presentation | |
| 658 else: | |
| 659 docinfo['presentationUrl'] = os.path.join(docPath, presentation) | |
| 464 | 660 |
| 468 | 661 |
| 464 | 662 return docinfo |
| 663 | |
| 664 def getDocinfoFromBib(self, docinfo, bib): | |
| 665 """reads contents of bib element into docinfo""" | |
| 465 | 666 logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
| 464 | 667 # put all raw bib fields in dict "bib" |
| 668 docinfo['bib'] = bib | |
| 669 bibtype = bib.get('@type', None) | |
| 670 docinfo['bibType'] = bibtype | |
| 671 # also store DC metadata for convenience | |
| 672 dc = self.metadataService.getDCMappedData(bib) | |
| 673 docinfo['creator'] = dc.get('creator',None) | |
| 674 docinfo['title'] = dc.get('title',None) | |
| 675 docinfo['date'] = dc.get('date',None) | |
| 676 return docinfo | |
| 677 | |
| 678 def getDocinfoFromAccess(self, docinfo, acc): | |
| 679 """reads contents of access element into docinfo""" | |
| 680 #TODO: also read resource type | |
| 465 | 681 logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
| 464 | 682 try: |
| 465 | 683 acctype = acc['@attr']['type'] |
| 464 | 684 if acctype: |
| 685 access=acctype | |
| 686 if access in ['group', 'institution']: | |
| 687 access = acc['name'].lower() | |
| 688 | |
| 689 docinfo['accessType'] = access | |
| 690 | |
| 691 except: | |
| 692 pass | |
| 693 | |
| 694 return docinfo | |
| 695 | |
| 696 def getDocinfoFromDigilib(self, docinfo, path): | |
| 697 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path | |
| 698 # fetch data | |
| 699 txt = getHttpData(infoUrl) | |
| 700 if not txt: | |
| 701 logging.error("Unable to get dir-info from %s"%(infoUrl)) | |
| 702 return docinfo | |
| 703 | |
| 704 dom = ET.fromstring(txt) | |
| 705 size = getText(dom.find("size")) | |
| 706 logging.debug("getDocinfoFromDigilib: size=%s"%size) | |
| 707 if size: | |
| 708 docinfo['numPages'] = int(size) | |
| 709 else: | |
| 710 docinfo['numPages'] = 0 | |
| 711 | |
| 712 # TODO: produce and keep list of image names and numbers | |
| 713 return docinfo | |
| 714 | |
| 715 | |
| 465 | 716 def getDocinfoFromPresentationInfoXml(self,docinfo): |
| 717 """gets DC-like bibliographical information from the presentation entry in texttools""" | |
| 718 url = docinfo.get('presentationUrl', None) | |
| 719 if not url: | |
| 720 logging.error("getDocinfoFromPresentation: no URL!") | |
| 721 return docinfo | |
| 722 | |
| 723 dom = None | |
| 724 metaUrl = None | |
| 725 if url.startswith("http://"): | |
| 726 # real URL | |
| 727 metaUrl = url | |
| 728 else: | |
| 729 # online path | |
| 730 | |
| 731 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 732 metaUrl=server+url | |
| 733 | |
| 734 txt=getHttpData(metaUrl) | |
| 735 if txt is None: | |
| 736 logging.error("Unable to read info.xml from %s"%(url)) | |
| 737 return docinfo | |
| 738 | |
| 739 dom = ET.fromstring(txt) | |
| 740 docinfo['creator']=getText(dom.find(".//author")) | |
| 741 docinfo['title']=getText(dom.find(".//title")) | |
| 742 docinfo['date']=getText(dom.find(".//date")) | |
| 743 return docinfo | |
| 744 | |
| 745 | |
| 503 | 746 def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewLayer=None, tocMode=None): |
| 22 | 747 """returns pageinfo with the given parameters""" |
| 503 | 748 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 | 749 pageinfo = {} |
| 471 | 750 pageinfo['viewMode'] = viewMode |
| 508 | 751 # split viewLayer if necessary |
| 752 if isinstance(viewLayer,basestring): | |
| 753 viewLayer = viewLayer.split(',') | |
| 754 | |
| 755 if isinstance(viewLayer, list): | |
| 756 logging.debug("getPageinfo: viewLayer is list:%s"%viewLayer) | |
| 757 # save (unique) list in viewLayers | |
| 758 seen = set() | |
| 759 viewLayers = [l for l in viewLayer if l and l not in seen and not seen.add(l)] | |
| 760 pageinfo['viewLayers'] = viewLayers | |
| 761 # stringify viewLayer | |
| 762 viewLayer = ','.join(viewLayers) | |
| 763 else: | |
| 764 #create list | |
| 765 pageinfo['viewLayers'] = [viewLayer] | |
| 766 | |
| 503 | 767 pageinfo['viewLayer'] = viewLayer |
| 471 | 768 pageinfo['tocMode'] = tocMode |
| 769 | |
| 516 | 770 # TODO: unify current and pn! |
| 25 | 771 current = getInt(current) |
| 772 pageinfo['current'] = current | |
| 480 | 773 pageinfo['pn'] = current |
| 25 | 774 rows = int(rows or self.thumbrows) |
| 775 pageinfo['rows'] = rows | |
| 776 cols = int(cols or self.thumbcols) | |
| 777 pageinfo['cols'] = cols | |
| 778 grpsize = cols * rows | |
| 779 pageinfo['groupsize'] = grpsize | |
| 476 | 780 # is start is empty use one around current |
| 61 | 781 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
| 782 # int(current / grpsize) * grpsize +1)) | |
| 22 | 783 pageinfo['start'] = start |
| 511 | 784 # get number of pages |
| 469 | 785 np = int(docinfo.get('numPages', 0)) |
| 786 if np == 0: | |
|
518
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
787 # try numTextPages |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
788 np = docinfo.get('numTextPages', 0) |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
789 if np != 0: |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
790 docinfo['numPages'] = np |
|
91051b36b9cc
uses xml info from doc-info.xql for table of contents now.
casties
parents:
516
diff
changeset
|
791 |
| 511 | 792 # cache table of contents |
| 793 pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) | |
| 469 | 794 pageinfo['numgroups'] = int(np / grpsize) |
| 795 if np % grpsize > 0: | |
| 796 pageinfo['numgroups'] += 1 | |
| 476 | 797 |
| 798 pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' | |
| 799 oddScanLeft = docinfo.get('oddPage', 'left') != 'right' | |
| 800 # add zeroth page for two columns | |
| 801 pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) | |
| 802 pageinfo['pageZero'] = pageZero | |
| 480 | 803 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np) |
| 516 | 804 # more page parameters |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
805 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
| 516 | 806 if docinfo.get('pageNumbers'): |
| 807 # get original page numbers | |
| 808 pageNumber = docinfo['pageNumbers'].get(current, None) | |
| 809 if pageNumber is not None: | |
| 810 pageinfo['pageNumberOrig'] = pageNumber['no'] | |
| 811 pageinfo['pageNumberOrigNorm'] = pageNumber['non'] | |
| 158 | 812 |
| 511 | 813 # cache search results |
| 814 pageinfo['resultPageSize'] = getInt(self.REQUEST.get('resultPageSize', 10)) | |
| 815 query = self.REQUEST.get('query',None) | |
| 816 pageinfo['query'] = query | |
| 817 if query: | |
| 818 queryType = self.REQUEST.get('queryType', 'fulltextMorph') | |
| 819 pageinfo['queryType'] = queryType | |
| 820 pageinfo['resultStart'] = getInt(self.REQUEST.get('resultStart', '1')) | |
| 821 self.getSearchResults(mode=queryType, query=query, pageinfo=pageinfo, docinfo=docinfo) | |
| 822 | |
| 823 # highlighting | |
| 824 highlightQuery = self.REQUEST.get('highlightQuery', None) | |
| 825 if highlightQuery: | |
| 826 pageinfo['highlightQuery'] = highlightQuery | |
| 827 pageinfo['highlightElement'] = self.REQUEST.get('highlightElement', '') | |
| 828 pageinfo['highlightElementPos'] = self.REQUEST.get('highlightElementPos', '') | |
| 460 | 829 |
| 22 | 830 return pageinfo |
| 460 | 831 |
| 463 | 832 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
833 def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0): |
| 480 | 834 """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
|
835 batch = {} |
| 480 | 836 grpsize = rows * cols |
| 476 | 837 if maxIdx == 0: |
| 480 | 838 maxIdx = start + grpsize |
| 476 | 839 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
840 nb = int(math.ceil(maxIdx / float(grpsize))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
841 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
842 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
843 if pageZero: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
844 ofs = 0 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
845 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
846 ofs = 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
847 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
848 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
849 s = i * grpsize + ofs |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
850 e = min((i + 1) * grpsize + ofs - 1, maxIdx) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
851 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
852 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
853 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
854 |
| 476 | 855 pages = [] |
| 856 if pageZero and start == 1: | |
| 857 # correct beginning | |
| 858 idx = 0 | |
| 859 else: | |
| 860 idx = start | |
| 861 | |
| 862 for r in range(rows): | |
| 863 row = [] | |
| 864 for c in range(cols): | |
| 865 if idx < minIdx or idx > maxIdx: | |
| 866 page = {'idx':None} | |
| 867 else: | |
| 868 page = {'idx':idx} | |
| 869 | |
| 870 idx += 1 | |
| 871 if pageFlowLtr: | |
| 872 row.append(page) | |
| 873 else: | |
| 874 row.insert(0, page) | |
| 875 | |
| 876 pages.append(row) | |
| 877 | |
| 480 | 878 if start > 1: |
| 879 batch['prevStart'] = max(start - grpsize, 1) | |
| 880 else: | |
| 881 batch['prevStart'] = None | |
| 882 | |
| 526 | 883 if start + grpsize <= maxIdx: |
| 480 | 884 batch['nextStart'] = start + grpsize |
| 885 else: | |
| 886 batch['nextStart'] = None | |
| 887 | |
| 888 batch['pages'] = pages | |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
889 return batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
890 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
891 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
|
892 """returns dict with information for one screenfull of data.""" |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
893 batch = {} |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
894 if end == 0: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
895 end = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
896 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
897 nb = int(math.ceil(end / float(size))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
898 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
899 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
900 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
901 s = i * size + 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
902 e = min((i + 1) * size, end) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
903 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
904 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
905 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
906 # list of elements in this batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
907 this = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
908 j = 0 |
| 526 | 909 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
|
910 if data: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
911 if fullData: |
| 526 | 912 d = data.get(i, None) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
913 else: |
| 526 | 914 d = data.get(j, None) |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
915 j += 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
916 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
917 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
918 d = i+1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
919 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
920 this.append(d) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
921 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
922 batch['this'] = this |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
923 if start > 1: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
924 batch['prevStart'] = max(start - size, 1) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
925 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
926 batch['prevStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
927 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
928 if start + size < end: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
929 batch['nextStart'] = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
930 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
931 batch['nextStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
932 |
| 526 | 933 logging.debug("getBatch start=%s size=%s end=%s batch=%s"%(start,size,end,repr(batch))) |
| 480 | 934 return batch |
| 476 | 935 |
| 936 | |
| 463 | 937 security.declareProtected('View management screens','changeDocumentViewerForm') |
| 938 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 22 | 939 |
| 526 | 940 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',availableLayers=None,RESPONSE=None): |
| 22 | 941 """init document viewer""" |
| 942 self.title=title | |
| 943 self.digilibBaseUrl = digilibBaseUrl | |
| 25 | 944 self.thumbrows = thumbrows |
| 945 self.thumbcols = thumbcols | |
| 32 | 946 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| 463 | 947 try: |
| 948 # assume MetaDataFolder instance is called metadata | |
| 949 self.metadataService = getattr(self, 'metadata') | |
| 950 except Exception, e: | |
| 951 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 526 | 952 |
| 953 self.setAvailableLayers(availableLayers) | |
| 463 | 954 |
| 22 | 955 if RESPONSE is not None: |
| 956 RESPONSE.redirect('manage_main') | |
| 0 | 957 |
| 958 def manage_AddDocumentViewerForm(self): | |
| 959 """add the viewer form""" | |
| 22 | 960 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| 0 | 961 return pt() |
| 962 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
963 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
| 0 | 964 """add the viewer""" |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
965 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
| 0 | 966 self._setObject(id,newObj) |
| 967 | |
| 968 if RESPONSE is not None: | |
| 969 RESPONSE.redirect('manage_main') |