Mercurial > hg > documentViewer
annotate documentViewer.py @ 516:7d7b639d7be7
add methods to use doc-info.xql.
read list of page numbers from doc-info.xql.
add original page numbers to thumbs.
| author | casties |
|---|---|
| date | Mon, 05 Mar 2012 18:04:49 +0100 |
| parents | c55e376be01b |
| children | 91051b36b9cc |
| 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 |
| 231 | 19 |
| 514 | 20 from SrvTxtUtils import getInt, utf8ify, getText, getHttpData, refreshingImageFileIndexHtml |
| 52 | 21 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
22 def serializeNode(node, encoding="utf-8"): |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
23 """returns a string containing node as XML""" |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
24 s = ET.tostring(node) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
25 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
26 # 4Suite: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
27 # stream = cStringIO.StringIO() |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
28 # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
29 # s = stream.getvalue() |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
30 # stream.close() |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
31 return s |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
32 |
| 387 | 33 def browserCheck(self): |
| 34 """check the browsers request to find out the browser type""" | |
| 35 bt = {} | |
| 36 ua = self.REQUEST.get_header("HTTP_USER_AGENT") | |
| 37 bt['ua'] = ua | |
| 38 bt['isIE'] = False | |
| 39 bt['isN4'] = False | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
40 bt['versFirefox']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
41 bt['versIE']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
42 bt['versSafariChrome']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
43 bt['versOpera']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
44 |
| 387 | 45 if string.find(ua, 'MSIE') > -1: |
| 46 bt['isIE'] = True | |
| 47 else: | |
| 48 bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
49 # Safari oder Chrome identification |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
50 try: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
51 nav = ua[string.find(ua, '('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
52 nav1=ua[string.find(ua,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
53 nav2=nav1[string.find(nav1,'('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
54 nav3=nav2[string.find(nav2,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
55 ie = string.split(nav, "; ")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
56 ie1 =string.split(nav1, " ")[2] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
57 ie2 =string.split(nav3, " ")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
58 ie3 =string.split(nav3, " ")[2] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
59 if string.find(ie3, "Safari") >-1: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
60 bt['versSafariChrome']=string.split(ie2, "/")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
61 except: pass |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
62 # IE identification |
| 387 | 63 try: |
| 64 nav = ua[string.find(ua, '('):] | |
| 65 ie = string.split(nav, "; ")[1] | |
| 66 if string.find(ie, "MSIE") > -1: | |
| 67 bt['versIE'] = string.split(ie, " ")[1] | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
68 except:pass |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
69 # Firefox identification |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
70 try: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
71 nav = ua[string.find(ua, '('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
72 nav1=ua[string.find(ua,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
73 if string.find(ie1, "Firefox") >-1: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
74 nav5= string.split(ie1, "/")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
75 logging.debug("FIREFOX: %s"%(nav5)) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
76 bt['versFirefox']=nav5[0:3] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
77 except:pass |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
78 #Opera identification |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
79 try: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
80 if string.find(ua,"Opera") >-1: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
81 nav = ua[string.find(ua, '('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
82 nav1=nav[string.find(nav,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
83 bt['versOpera']=string.split(nav1,"/")[2] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
84 except:pass |
| 387 | 85 |
| 86 bt['isMac'] = string.find(ua, 'Macintosh') > -1 | |
| 87 bt['isWin'] = string.find(ua, 'Windows') > -1 | |
| 88 bt['isIEWin'] = bt['isIE'] and bt['isWin'] | |
| 89 bt['isIEMac'] = bt['isIE'] and bt['isMac'] | |
| 90 bt['staticHTML'] = False | |
| 91 | |
| 92 return bt | |
| 234 | 93 |
| 464 | 94 def getParentPath(path, cnt=1): |
| 95 """returns pathname shortened by cnt""" | |
| 96 # make sure path doesn't end with / | |
| 97 path = path.rstrip('/') | |
| 98 # split by /, shorten, and reassemble | |
| 99 return '/'.join(path.split('/')[0:-cnt]) | |
| 100 | |
| 22 | 101 ## |
| 102 ## documentViewer class | |
| 103 ## | |
| 104 class documentViewer(Folder): | |
| 0 | 105 """document viewer""" |
| 106 meta_type="Document viewer" | |
| 107 | |
| 108 security=ClassSecurityInfo() | |
| 22 | 109 manage_options=Folder.manage_options+( |
| 507 | 110 {'label':'Configuration','action':'changeDocumentViewerForm'}, |
| 0 | 111 ) |
| 463 | 112 |
| 113 metadataService = None | |
| 114 """MetaDataFolder instance""" | |
| 0 | 115 |
| 22 | 116 # templates and forms |
| 479 | 117 viewer_text = PageTemplateFile('zpt/viewer_text', globals()) |
| 503 | 118 viewer_xml = PageTemplateFile('zpt/viewer_xml', globals()) |
| 483 | 119 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
|
120 viewer_index = PageTemplateFile('zpt/viewer_index', globals()) |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
121 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
|
122 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
|
123 toc_figures = PageTemplateFile('zpt/toc_figures', globals()) |
| 491 | 124 toc_none = PageTemplateFile('zpt/toc_none', globals()) |
| 501 | 125 common_template = PageTemplateFile('zpt/common_template', globals()) |
| 511 | 126 search_template = PageTemplateFile('zpt/search_template', globals()) |
| 57 | 127 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
| 487 | 128 docuviewer_css = ImageFile('css/docuviewer.css',globals()) |
|
489
55e3398e395e
more new templates. monkey-patch for App.ImageFile.
casties
parents:
488
diff
changeset
|
129 # make ImageFile better for development |
|
490
6f116b86a226
more new template stuff. moved ImageFile index method to SrvTxtUtils
casties
parents:
489
diff
changeset
|
130 docuviewer_css.index_html = refreshingImageFileIndexHtml |
| 501 | 131 jquery_js = ImageFile('js/jquery.js',globals()) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
132 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
133 |
| 95 | 134 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
| 0 | 135 """init document viewer""" |
| 136 self.id=id | |
| 137 self.title=title | |
| 25 | 138 self.thumbcols = thumbcols |
| 139 self.thumbrows = thumbrows | |
| 32 | 140 # authgroups is list of authorized groups (delimited by ,) |
| 141 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
|
142 # 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
|
143 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
144 templateFolder = Folder('template') |
| 498 | 145 self['template'] = templateFolder # Zope-2.12 style |
| 146 #self._setObject('template',templateFolder) # old style | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
147 try: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
148 import MpdlXmlTextServer |
| 132 | 149 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
| 498 | 150 templateFolder['fulltextclient'] = textServer |
| 151 #templateFolder._setObject('fulltextclient',textServer) | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
152 except Exception, e: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
153 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
| 463 | 154 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
155 try: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
156 from Products.zogiLib.zogiLib import zogiLib |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
157 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
| 498 | 158 templateFolder['zogilib'] = zogilib |
| 159 #templateFolder._setObject('zogilib',zogilib) | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
160 except Exception, e: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
161 logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
| 463 | 162 |
| 163 try: | |
| 164 # assume MetaDataFolder instance is called metadata | |
| 165 self.metadataService = getattr(self, 'metadata') | |
| 166 except Exception, e: | |
| 167 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 168 | |
| 477 | 169 if digilibBaseUrl is not None: |
| 170 self.digilibBaseUrl = digilibBaseUrl | |
| 171 | |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
172 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
173 # proxy text server methods to fulltextclient |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
174 def getTextPage(self, **args): |
| 498 | 175 """returns full text content of page""" |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
176 return self.template.fulltextclient.getTextPage(**args) |
| 22 | 177 |
| 508 | 178 def getSearchResults(self, **args): |
| 179 """loads list of search results and stores XML in docinfo""" | |
| 180 return self.template.fulltextclient.getSearchResults(**args) | |
| 181 | |
| 182 def getResultsPage(self, **args): | |
| 183 """returns one page of the search results""" | |
| 184 return self.template.fulltextclient.getResultsPage(**args) | |
| 185 | |
| 516 | 186 def getTextInfo(self, **args): |
| 187 """returns document info from the text server""" | |
| 188 return self.template.fulltextclient.getTextInfo(**args) | |
| 189 | |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
190 def getToc(self, **args): |
| 508 | 191 """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
|
192 return self.template.fulltextclient.getToc(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
193 |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
194 def getTocPage(self, **args): |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
195 """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
|
196 return self.template.fulltextclient.getTocPage(**args) |
|
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
197 |
| 506 | 198 def getPlacesOnPage(self, **args): |
| 199 """get list of gis places on one page""" | |
| 200 return self.template.fulltextclient.getPlacesOnPage(**args) | |
| 307 | 201 |
| 498 | 202 #WTF? |
|
499
3f9703746fef
more cleanup. new template for viewMode=index (not pretty so far).
casties
parents:
498
diff
changeset
|
203 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
| 68 | 204 security.declareProtected('View','thumbs_rss') |
| 205 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
| 206 ''' | |
| 207 view it | |
| 208 @param mode: defines how to access the document behind url | |
| 209 @param url: url which contains display information | |
| 210 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
| 211 | |
| 212 ''' | |
| 167 | 213 logging.debug("HHHHHHHHHHHHHH:load the rss") |
| 458 | 214 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| 68 | 215 |
| 216 if not hasattr(self, 'template'): | |
| 217 # create template folder if it doesn't exist | |
| 218 self.manage_addFolder('template') | |
| 219 | |
| 220 if not self.digilibBaseUrl: | |
| 221 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 222 | |
| 223 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 338 | 224 #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
| 345 | 225 pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) |
| 331 | 226 ''' ZDES ''' |
| 68 | 227 pt = getattr(self.template, 'thumbs_main_rss') |
| 228 | |
| 229 if viewMode=="auto": # automodus gewaehlt | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
230 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
| 68 | 231 viewMode="text" |
| 232 else: | |
| 233 viewMode="images" | |
| 234 | |
| 235 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
| 465 | 236 |
| 68 | 237 |
| 22 | 238 security.declareProtected('View','index_html') |
| 503 | 239 def index_html(self,url,mode="texttool",viewMode="auto",viewLayer=None,tocMode="thumbs",start=1,pn=1): |
| 464 | 240 """ |
| 471 | 241 view page |
| 242 @param url: url which contains display information | |
| 57 | 243 @param mode: defines how to access the document behind url |
| 503 | 244 @param viewMode: 'images': display images, 'text': display text, 'xml': display xml, default is 'auto' |
| 245 @param viewLayer: sub-type of viewMode, e.g. 'dict' for viewMode='text' | |
| 99 | 246 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
| 464 | 247 """ |
| 0 | 248 |
| 503 | 249 logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewLayer=%s start=%s pn=%s"%(mode,url,viewMode,viewLayer,start,pn)) |
| 22 | 250 |
| 251 if not hasattr(self, 'template'): | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
252 # this won't work |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
253 logging.error("template folder missing!") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
254 return "ERROR: template folder missing!" |
| 22 | 255 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
256 if not getattr(self, 'digilibBaseUrl', None): |
| 132 | 257 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 22 | 258 |
| 25 | 259 docinfo = self.getDocinfo(mode=mode,url=url) |
| 97 | 260 |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
261 if tocMode != "thumbs": |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
262 # get table of contents |
| 508 | 263 self.getToc(mode=tocMode, docinfo=docinfo) |
| 455 | 264 |
| 471 | 265 # auto viewMode: text if there is a text else images |
| 455 | 266 if viewMode=="auto": |
| 267 if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): | |
| 471 | 268 viewMode = "text" |
| 508 | 269 if viewLayer is None: |
| 270 viewLayer = "dict" | |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
271 else: |
| 471 | 272 viewMode = "images" |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
273 |
| 474 | 274 elif viewMode == "text_dict": |
| 275 # legacy fix | |
| 276 viewMode = "text" | |
| 503 | 277 viewLayer = "dict" |
| 474 | 278 |
| 503 | 279 pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode) |
| 469 | 280 |
| 475 | 281 # get template /template/viewer_$viewMode |
| 282 pt = getattr(self.template, 'viewer_%s'%viewMode, None) | |
| 283 if pt is None: | |
| 284 logging.error("No template for viewMode=%s!"%viewMode) | |
| 285 # TODO: error page? | |
| 286 return "No template for viewMode=%s!"%viewMode | |
| 287 | |
| 455 | 288 # and execute with parameters |
| 471 | 289 return pt(docinfo=docinfo, pageinfo=pageinfo) |
| 0 | 290 |
| 506 | 291 #WTF? |
| 74 | 292 def generateMarks(self,mk): |
| 293 ret="" | |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
294 if mk is None: |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
295 return "" |
| 134 | 296 if not isinstance(mk, list): |
| 132 | 297 mk=[mk] |
| 74 | 298 for m in mk: |
|
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
299 ret+="mk=%s"%m |
| 74 | 300 return ret |
| 389 | 301 |
| 302 | |
| 387 | 303 def getBrowser(self): |
| 304 """getBrowser the version of browser """ | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
305 bt = browserCheck(self) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
306 logging.debug("BROWSER VERSION: %s"%(bt)) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
307 return bt |
| 387 | 308 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
309 def findDigilibUrl(self): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
310 """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
|
311 url = self.template.zogilib.getDLBaseUrl() |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
312 return url |
| 480 | 313 |
| 314 def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None): | |
| 315 """returns URL to digilib Scaler with params""" | |
| 316 url = None | |
| 317 if docinfo is not None: | |
| 318 url = docinfo.get('imageURL', None) | |
| 319 | |
| 320 if url is None: | |
| 321 url = "%s/servlet/Scaler?"%self.digilibBaseUrl | |
| 322 if fn is None and docinfo is not None: | |
| 323 fn = docinfo.get('imagePath','') | |
| 324 | |
| 325 url += "fn=%s"%fn | |
| 326 | |
| 327 if pn: | |
| 328 url += "&pn=%s"%pn | |
| 329 | |
| 330 url += "&dw=%s&dh=%s"%(dw,dh) | |
| 331 return url | |
| 126 | 332 |
| 333 def getDocumentViewerURL(self): | |
| 334 """returns the URL of this instance""" | |
| 335 return self.absolute_url() | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
336 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
337 def getStyle(self, idx, selected, style=""): |
| 480 | 338 """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
|
339 #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
|
340 if idx == selected: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
341 return style + 'sel' |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
342 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
343 return style |
| 74 | 344 |
| 478 | 345 def getParams(self, param=None, val=None, params=None, duplicates=None): |
| 469 | 346 """returns dict with URL parameters. |
| 347 | |
| 348 Takes URL parameters and additionally param=val or dict params. | |
| 349 Deletes key if value is None.""" | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
350 # copy existing request params |
| 469 | 351 newParams=self.REQUEST.form.copy() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
352 # change single param |
| 25 | 353 if param is not None: |
| 31 | 354 if val is None: |
| 469 | 355 if newParams.has_key(param): |
| 356 del newParams[param] | |
| 25 | 357 else: |
| 469 | 358 newParams[param] = str(val) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
359 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
360 # change more params |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
361 if params is not None: |
| 478 | 362 for (k, v) in params.items(): |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
363 if v is None: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
364 # val=None removes param |
| 469 | 365 if newParams.has_key(k): |
| 366 del newParams[k] | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
367 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
368 else: |
| 469 | 369 newParams[k] = v |
| 478 | 370 |
| 371 if duplicates: | |
| 372 # eliminate lists (coming from duplicate keys) | |
| 373 for (k,v) in newParams.items(): | |
| 374 if isinstance(v, list): | |
| 375 if duplicates == 'comma': | |
| 376 # make comma-separated list of non-empty entries | |
| 377 newParams[k] = ','.join([t for t in v if t]) | |
| 378 elif duplicates == 'first': | |
| 379 # take first non-empty entry | |
| 380 newParams[k] = [t for t in v if t][0] | |
| 381 | |
| 469 | 382 return newParams |
| 383 | |
| 478 | 384 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
| 469 | 385 """returns URL to documentviewer with parameter param set to val or from dict params""" |
| 478 | 386 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
|
387 # quote values and assemble into query string (not escaping '/') |
| 514 | 388 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
|
389 if baseUrl is None: |
| 469 | 390 baseUrl = self.getDocumentViewerURL() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
391 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
392 url = "%s?%s"%(baseUrl, ps) |
| 25 | 393 return url |
| 394 | |
| 478 | 395 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
| 68 | 396 """link to documentviewer with parameter param set to val""" |
| 478 | 397 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
|
398 |
| 469 | 399 |
| 57 | 400 def getInfo_xml(self,url,mode): |
| 401 """returns info about the document as XML""" | |
| 402 if not self.digilibBaseUrl: | |
| 514 | 403 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 57 | 404 |
| 405 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 406 pt = getattr(self.template, 'info_xml') | |
| 407 return pt(docinfo=docinfo) | |
| 408 | |
| 35 | 409 def isAccessible(self, docinfo): |
| 32 | 410 """returns if access to the resource is granted""" |
| 411 access = docinfo.get('accessType', None) | |
| 167 | 412 logging.debug("documentViewer (accessOK) access type %s"%access) |
| 465 | 413 if access == 'free': |
| 167 | 414 logging.debug("documentViewer (accessOK) access is free") |
| 32 | 415 return True |
| 465 | 416 |
| 45 | 417 elif access is None or access in self.authgroups: |
| 35 | 418 # only local access -- only logged in users |
| 419 user = getSecurityManager().getUser() | |
| 167 | 420 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
| 35 | 421 if user is not None: |
| 422 #print "user: ", user | |
| 423 return (user.getUserName() != "Anonymous User") | |
| 424 else: | |
| 425 return False | |
| 32 | 426 |
| 167 | 427 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
| 32 | 428 return False |
| 35 | 429 |
| 464 | 430 |
| 431 | |
| 432 def getDocinfo(self, mode, url): | |
| 433 """returns docinfo depending on mode""" | |
| 434 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) | |
| 435 # look for cached docinfo in session | |
| 436 if self.REQUEST.SESSION.has_key('docinfo'): | |
| 437 docinfo = self.REQUEST.SESSION['docinfo'] | |
| 438 # check if its still current | |
| 439 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: | |
| 440 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
| 441 return docinfo | |
| 442 | |
| 443 # new docinfo | |
| 444 docinfo = {'mode': mode, 'url': url} | |
| 445 # add self url | |
| 446 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
| 477 | 447 docinfo['digilibBaseUrl'] = self.digilibBaseUrl |
| 464 | 448 # get index.meta DOM |
| 449 docUrl = None | |
| 450 metaDom = None | |
| 451 if mode=="texttool": | |
| 452 # url points to document dir or index.meta | |
| 453 metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
| 454 docUrl = url.replace('/index.meta', '') | |
| 455 if metaDom is None: | |
| 456 raise IOError("Unable to find index.meta for mode=texttool!") | |
| 457 | |
| 458 elif mode=="imagepath": | |
| 459 # url points to folder with images, index.meta optional | |
| 460 # asssume index.meta in parent dir | |
| 461 docUrl = getParentPath(url) | |
| 462 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 463 | |
| 464 elif mode=="filepath": | |
| 465 # url points to image file, index.meta optional | |
| 466 # asssume index.meta is two path segments up | |
| 467 docUrl = getParentPath(url, 2) | |
| 468 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 469 | |
| 470 else: | |
| 471 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
| 472 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
| 473 | |
| 474 docinfo['documentUrl'] = docUrl | |
| 475 # process index.meta contents | |
| 473 | 476 if metaDom is not None and metaDom.tag == 'resource': |
| 464 | 477 # document directory name and path |
| 478 resource = self.metadataService.getResourceData(dom=metaDom) | |
| 479 if resource: | |
| 480 docinfo = self.getDocinfoFromResource(docinfo, resource) | |
| 481 | |
| 482 # texttool info | |
| 483 texttool = self.metadataService.getTexttoolData(dom=metaDom) | |
| 484 if texttool: | |
| 485 docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
| 516 | 486 # document info from full text |
| 487 if docinfo.get('textURLPath', None): | |
| 488 docinfo = self.getTextInfo(docinfo=docinfo) | |
| 464 | 489 |
| 490 # bib info | |
| 491 bib = self.metadataService.getBibData(dom=metaDom) | |
| 492 if bib: | |
| 493 docinfo = self.getDocinfoFromBib(docinfo, bib) | |
| 465 | 494 else: |
| 495 # no bib - try info.xml | |
| 496 docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) | |
| 464 | 497 |
| 498 # auth info | |
| 499 access = self.metadataService.getAccessData(dom=metaDom) | |
| 500 if access: | |
| 501 docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 502 | |
| 466 | 503 # attribution info |
| 504 attribution = self.metadataService.getAttributionData(dom=metaDom) | |
| 505 if attribution: | |
| 506 logging.debug("getDocinfo: attribution=%s"%repr(attribution)) | |
| 507 docinfo['attribution'] = attribution | |
| 508 #docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 509 | |
| 510 # copyright info | |
| 511 copyright = self.metadataService.getCopyrightData(dom=metaDom) | |
| 512 if copyright: | |
| 513 logging.debug("getDocinfo: copyright=%s"%repr(copyright)) | |
| 514 docinfo['copyright'] = copyright | |
| 515 #docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 516 | |
| 464 | 517 # image path |
| 518 if mode != 'texttool': | |
| 516 | 519 # override image path from texttool with url TODO: how about mode=auto? |
| 465 | 520 docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1) |
| 464 | 521 |
| 522 # number of images from digilib | |
| 523 if docinfo.get('imagePath', None): | |
| 524 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath'] | |
| 525 docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath']) | |
| 526 | |
| 516 | 527 # check numPages |
| 528 if docinfo.get('numPages', 0) == 0: | |
| 529 if docinfo.get('numTextPages', 0) > 0: | |
| 530 # replace with numTextPages (text-only?) | |
| 531 docinfo['numPages'] = docinfo['numTextPages'] | |
| 532 | |
| 464 | 533 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
| 534 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) | |
| 535 # store in session | |
| 536 self.REQUEST.SESSION['docinfo'] = docinfo | |
| 537 return docinfo | |
| 538 | |
| 516 | 539 |
| 464 | 540 def getDocinfoFromResource(self, docinfo, resource): |
| 541 """reads contents of resource element into docinfo""" | |
| 542 docName = resource.get('name', None) | |
| 543 docinfo['documentName'] = docName | |
| 544 docPath = resource.get('archive-path', None) | |
| 545 if docPath: | |
| 546 # clean up document path | |
| 547 if docPath[0] != '/': | |
| 548 docPath = '/' + docPath | |
| 549 | |
| 550 if docName and (not docPath.endswith(docName)): | |
| 551 docPath += "/" + docName | |
| 552 | |
| 553 else: | |
| 554 # use docUrl as docPath | |
| 555 docUrl = docinfo['documentURL'] | |
| 556 if not docUrl.startswith('http:'): | |
| 557 docPath = docUrl | |
| 465 | 558 if docPath: |
| 559 # fix URLs starting with /mpiwg/online | |
| 560 docPath = docPath.replace('/mpiwg/online', '', 1) | |
| 561 | |
| 464 | 562 docinfo['documentPath'] = docPath |
| 563 return docinfo | |
| 564 | |
| 565 def getDocinfoFromTexttool(self, docinfo, texttool): | |
| 566 """reads contents of texttool element into docinfo""" | |
| 567 # image dir | |
| 568 imageDir = texttool.get('image', None) | |
| 569 docPath = docinfo.get('documentPath', None) | |
| 570 if imageDir and docPath: | |
| 571 #print "image: ", imageDir, " archivepath: ", archivePath | |
| 572 imageDir = os.path.join(docPath, imageDir) | |
| 573 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
| 574 docinfo['imagePath'] = imageDir | |
| 575 | |
| 576 # old style text URL | |
| 577 textUrl = texttool.get('text', None) | |
| 578 if textUrl and docPath: | |
| 579 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
| 580 textUrl = os.path.join(docPath, textUrl) | |
| 581 | |
| 582 docinfo['textURL'] = textUrl | |
| 583 | |
| 584 # new style text-url-path | |
| 585 textUrl = texttool.get('text-url-path', None) | |
| 586 if textUrl: | |
| 587 docinfo['textURLPath'] = textUrl | |
| 468 | 588 |
| 589 # page flow | |
| 590 docinfo['pageFlow'] = texttool.get('page-flow', 'ltr') | |
| 591 | |
| 592 # odd pages are left | |
| 476 | 593 docinfo['oddPage'] = texttool.get('odd-scan-position', 'left') |
| 468 | 594 |
| 469 | 595 # number of title page (0: not defined) |
| 468 | 596 docinfo['titlePage'] = texttool.get('title-scan-no', 0) |
| 464 | 597 |
| 598 # old presentation stuff | |
| 599 presentation = texttool.get('presentation', None) | |
| 600 if presentation and docPath: | |
| 465 | 601 if presentation.startswith('http:'): |
| 602 docinfo['presentationUrl'] = presentation | |
| 603 else: | |
| 604 docinfo['presentationUrl'] = os.path.join(docPath, presentation) | |
| 464 | 605 |
| 468 | 606 |
| 464 | 607 return docinfo |
| 608 | |
| 609 def getDocinfoFromBib(self, docinfo, bib): | |
| 610 """reads contents of bib element into docinfo""" | |
| 465 | 611 logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
| 464 | 612 # put all raw bib fields in dict "bib" |
| 613 docinfo['bib'] = bib | |
| 614 bibtype = bib.get('@type', None) | |
| 615 docinfo['bibType'] = bibtype | |
| 616 # also store DC metadata for convenience | |
| 617 dc = self.metadataService.getDCMappedData(bib) | |
| 618 docinfo['creator'] = dc.get('creator',None) | |
| 619 docinfo['title'] = dc.get('title',None) | |
| 620 docinfo['date'] = dc.get('date',None) | |
| 621 return docinfo | |
| 622 | |
| 623 def getDocinfoFromAccess(self, docinfo, acc): | |
| 624 """reads contents of access element into docinfo""" | |
| 625 #TODO: also read resource type | |
| 465 | 626 logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
| 464 | 627 try: |
| 465 | 628 acctype = acc['@attr']['type'] |
| 464 | 629 if acctype: |
| 630 access=acctype | |
| 631 if access in ['group', 'institution']: | |
| 632 access = acc['name'].lower() | |
| 633 | |
| 634 docinfo['accessType'] = access | |
| 635 | |
| 636 except: | |
| 637 pass | |
| 638 | |
| 639 return docinfo | |
| 640 | |
| 641 def getDocinfoFromDigilib(self, docinfo, path): | |
| 642 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path | |
| 643 # fetch data | |
| 644 txt = getHttpData(infoUrl) | |
| 645 if not txt: | |
| 646 logging.error("Unable to get dir-info from %s"%(infoUrl)) | |
| 647 return docinfo | |
| 648 | |
| 649 dom = ET.fromstring(txt) | |
| 650 size = getText(dom.find("size")) | |
| 651 logging.debug("getDocinfoFromDigilib: size=%s"%size) | |
| 652 if size: | |
| 653 docinfo['numPages'] = int(size) | |
| 654 else: | |
| 655 docinfo['numPages'] = 0 | |
| 656 | |
| 657 # TODO: produce and keep list of image names and numbers | |
| 658 return docinfo | |
| 659 | |
| 660 | |
| 465 | 661 def getDocinfoFromPresentationInfoXml(self,docinfo): |
| 662 """gets DC-like bibliographical information from the presentation entry in texttools""" | |
| 663 url = docinfo.get('presentationUrl', None) | |
| 664 if not url: | |
| 665 logging.error("getDocinfoFromPresentation: no URL!") | |
| 666 return docinfo | |
| 667 | |
| 668 dom = None | |
| 669 metaUrl = None | |
| 670 if url.startswith("http://"): | |
| 671 # real URL | |
| 672 metaUrl = url | |
| 673 else: | |
| 674 # online path | |
| 675 | |
| 676 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 677 metaUrl=server+url | |
| 678 | |
| 679 txt=getHttpData(metaUrl) | |
| 680 if txt is None: | |
| 681 logging.error("Unable to read info.xml from %s"%(url)) | |
| 682 return docinfo | |
| 683 | |
| 684 dom = ET.fromstring(txt) | |
| 685 docinfo['creator']=getText(dom.find(".//author")) | |
| 686 docinfo['title']=getText(dom.find(".//title")) | |
| 687 docinfo['date']=getText(dom.find(".//date")) | |
| 688 return docinfo | |
| 689 | |
| 690 | |
| 503 | 691 def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewLayer=None, tocMode=None): |
| 22 | 692 """returns pageinfo with the given parameters""" |
| 503 | 693 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 | 694 pageinfo = {} |
| 471 | 695 pageinfo['viewMode'] = viewMode |
| 508 | 696 # split viewLayer if necessary |
| 697 if isinstance(viewLayer,basestring): | |
| 698 viewLayer = viewLayer.split(',') | |
| 699 | |
| 700 if isinstance(viewLayer, list): | |
| 701 logging.debug("getPageinfo: viewLayer is list:%s"%viewLayer) | |
| 702 # save (unique) list in viewLayers | |
| 703 seen = set() | |
| 704 viewLayers = [l for l in viewLayer if l and l not in seen and not seen.add(l)] | |
| 705 pageinfo['viewLayers'] = viewLayers | |
| 706 # stringify viewLayer | |
| 707 viewLayer = ','.join(viewLayers) | |
| 708 else: | |
| 709 #create list | |
| 710 pageinfo['viewLayers'] = [viewLayer] | |
| 711 | |
| 503 | 712 pageinfo['viewLayer'] = viewLayer |
| 471 | 713 pageinfo['tocMode'] = tocMode |
| 714 | |
| 516 | 715 # TODO: unify current and pn! |
| 25 | 716 current = getInt(current) |
| 717 pageinfo['current'] = current | |
| 480 | 718 pageinfo['pn'] = current |
| 25 | 719 rows = int(rows or self.thumbrows) |
| 720 pageinfo['rows'] = rows | |
| 721 cols = int(cols or self.thumbcols) | |
| 722 pageinfo['cols'] = cols | |
| 723 grpsize = cols * rows | |
| 724 pageinfo['groupsize'] = grpsize | |
| 476 | 725 # is start is empty use one around current |
| 61 | 726 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
| 727 # int(current / grpsize) * grpsize +1)) | |
| 22 | 728 pageinfo['start'] = start |
| 511 | 729 # get number of pages |
| 469 | 730 np = int(docinfo.get('numPages', 0)) |
| 731 if np == 0: | |
| 732 # numPages unknown - maybe we can get it from text page | |
| 516 | 733 logging.warn("getPageInfo: numPages=0 trying getTextPage!") |
| 469 | 734 if docinfo.get('textURLPath', None): |
| 735 # cache text page as well | |
| 503 | 736 pageinfo['textPage'] = self.getTextPage(mode=viewLayer, pn=current, docinfo=docinfo, pageinfo=pageinfo) |
| 469 | 737 np = int(docinfo.get('numPages', 0)) |
| 738 | |
| 511 | 739 # cache table of contents |
| 740 pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) | |
| 469 | 741 pageinfo['numgroups'] = int(np / grpsize) |
| 742 if np % grpsize > 0: | |
| 743 pageinfo['numgroups'] += 1 | |
| 476 | 744 |
| 745 pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' | |
| 746 oddScanLeft = docinfo.get('oddPage', 'left') != 'right' | |
| 747 # add zeroth page for two columns | |
| 748 pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) | |
| 749 pageinfo['pageZero'] = pageZero | |
| 480 | 750 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np) |
| 516 | 751 # more page parameters |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
752 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
| 516 | 753 if docinfo.get('pageNumbers'): |
| 754 # get original page numbers | |
| 755 pageNumber = docinfo['pageNumbers'].get(current, None) | |
| 756 if pageNumber is not None: | |
| 757 pageinfo['pageNumberOrig'] = pageNumber['no'] | |
| 758 pageinfo['pageNumberOrigNorm'] = pageNumber['non'] | |
| 158 | 759 |
| 511 | 760 # cache search results |
| 761 pageinfo['resultPageSize'] = getInt(self.REQUEST.get('resultPageSize', 10)) | |
| 762 query = self.REQUEST.get('query',None) | |
| 763 pageinfo['query'] = query | |
| 764 if query: | |
| 765 queryType = self.REQUEST.get('queryType', 'fulltextMorph') | |
| 766 pageinfo['queryType'] = queryType | |
| 767 pageinfo['resultStart'] = getInt(self.REQUEST.get('resultStart', '1')) | |
| 768 self.getSearchResults(mode=queryType, query=query, pageinfo=pageinfo, docinfo=docinfo) | |
| 769 | |
| 770 # highlighting | |
| 771 highlightQuery = self.REQUEST.get('highlightQuery', None) | |
| 772 if highlightQuery: | |
| 773 pageinfo['highlightQuery'] = highlightQuery | |
| 774 pageinfo['highlightElement'] = self.REQUEST.get('highlightElement', '') | |
| 775 pageinfo['highlightElementPos'] = self.REQUEST.get('highlightElementPos', '') | |
| 460 | 776 |
| 22 | 777 return pageinfo |
| 460 | 778 |
| 463 | 779 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
780 def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0): |
| 480 | 781 """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
|
782 batch = {} |
| 480 | 783 grpsize = rows * cols |
| 476 | 784 if maxIdx == 0: |
| 480 | 785 maxIdx = start + grpsize |
| 476 | 786 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
787 nb = int(math.ceil(maxIdx / float(grpsize))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
788 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
789 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
790 if pageZero: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
791 ofs = 0 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
792 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
793 ofs = 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
794 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
795 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
796 s = i * grpsize + ofs |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
797 e = min((i + 1) * grpsize + ofs - 1, maxIdx) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
798 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
799 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
800 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
801 |
| 476 | 802 pages = [] |
| 803 if pageZero and start == 1: | |
| 804 # correct beginning | |
| 805 idx = 0 | |
| 806 else: | |
| 807 idx = start | |
| 808 | |
| 809 for r in range(rows): | |
| 810 row = [] | |
| 811 for c in range(cols): | |
| 812 if idx < minIdx or idx > maxIdx: | |
| 813 page = {'idx':None} | |
| 814 else: | |
| 815 page = {'idx':idx} | |
| 816 | |
| 817 idx += 1 | |
| 818 if pageFlowLtr: | |
| 819 row.append(page) | |
| 820 else: | |
| 821 row.insert(0, page) | |
| 822 | |
| 823 pages.append(row) | |
| 824 | |
| 480 | 825 if start > 1: |
| 826 batch['prevStart'] = max(start - grpsize, 1) | |
| 827 else: | |
| 828 batch['prevStart'] = None | |
| 829 | |
| 830 if start + grpsize < maxIdx: | |
| 831 batch['nextStart'] = start + grpsize | |
| 832 else: | |
| 833 batch['nextStart'] = None | |
| 834 | |
| 835 batch['pages'] = pages | |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
836 return batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
837 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
838 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
|
839 """returns dict with information for one screenfull of data.""" |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
840 batch = {} |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
841 if end == 0: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
842 end = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
843 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
844 nb = int(math.ceil(end / float(size))) |
|
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 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
848 s = i * size + 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
849 e = min((i + 1) * size, end) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
850 batches.append({'start':s, 'end':e}) |
|
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 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
853 # list of elements in this batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
854 this = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
855 j = 0 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
856 for i in range(start, min(start+size, end)): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
857 if data: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
858 if fullData: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
859 d = data[i] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
860 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
861 d = data[j] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
862 j += 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
863 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
864 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
865 d = i+1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
866 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
867 this.append(d) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
868 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
869 batch['this'] = this |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
870 if start > 1: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
871 batch['prevStart'] = max(start - size, 1) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
872 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
873 batch['prevStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
874 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
875 if start + size < end: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
876 batch['nextStart'] = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
877 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
878 batch['nextStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
879 |
| 480 | 880 return batch |
| 476 | 881 |
| 882 | |
| 463 | 883 security.declareProtected('View management screens','changeDocumentViewerForm') |
| 884 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 22 | 885 |
| 460 | 886 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
| 22 | 887 """init document viewer""" |
| 888 self.title=title | |
| 889 self.digilibBaseUrl = digilibBaseUrl | |
| 25 | 890 self.thumbrows = thumbrows |
| 891 self.thumbcols = thumbcols | |
| 32 | 892 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| 463 | 893 try: |
| 894 # assume MetaDataFolder instance is called metadata | |
| 895 self.metadataService = getattr(self, 'metadata') | |
| 896 except Exception, e: | |
| 897 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 898 | |
| 22 | 899 if RESPONSE is not None: |
| 900 RESPONSE.redirect('manage_main') | |
| 0 | 901 |
| 902 def manage_AddDocumentViewerForm(self): | |
| 903 """add the viewer form""" | |
| 22 | 904 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| 0 | 905 return pt() |
| 906 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
907 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
| 0 | 908 """add the viewer""" |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
909 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
| 0 | 910 self._setObject(id,newObj) |
| 911 | |
| 912 if RESPONSE is not None: | |
| 913 RESPONSE.redirect('manage_main') |