Mercurial > hg > documentViewer
annotate documentViewer.py @ 464:19bd41d95f62 elementtree
first version with new getdocinfo
author | casties |
---|---|
date | Fri, 29 Jul 2011 18:27:24 +0200 |
parents | 89ad327b4bbd |
children | 224aad394350 |
rev | line source |
---|---|
0 | 1 from OFS.Folder import Folder |
2 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate | |
52 | 3 from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
0 | 4 from AccessControl import ClassSecurityInfo |
32 | 5 from AccessControl import getSecurityManager |
0 | 6 from Globals import package_home |
7 | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
8 #from Ft.Xml import EMPTY_NAMESPACE, Parse |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
9 #import Ft.Xml.Domlette |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
10 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
11 import xml.etree.ElementTree as ET |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
12 |
0 | 13 import os.path |
31 | 14 import sys |
0 | 15 import urllib |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
16 import logging |
61 | 17 import math |
46 | 18 import urlparse |
174 | 19 import re |
389 | 20 import string |
231 | 21 |
458 | 22 from SrvTxtUtils import getInt, getText, getHttpData |
23 | |
52 | 24 def logger(txt,method,txt2): |
25 """logging""" | |
26 logging.info(txt+ txt2) | |
27 | |
28 | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
29 def serializeNode(node, encoding="utf-8"): |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
30 """returns a string containing node as XML""" |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
31 s = ET.tostring(node) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
32 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
33 # 4Suite: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
34 # stream = cStringIO.StringIO() |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
35 # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
36 # s = stream.getvalue() |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
37 # stream.close() |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
38 return s |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
39 |
387 | 40 def browserCheck(self): |
41 """check the browsers request to find out the browser type""" | |
42 bt = {} | |
43 ua = self.REQUEST.get_header("HTTP_USER_AGENT") | |
44 bt['ua'] = ua | |
45 bt['isIE'] = False | |
46 bt['isN4'] = False | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
47 bt['versFirefox']="" |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
48 bt['versIE']="" |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
49 bt['versSafariChrome']="" |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
50 bt['versOpera']="" |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
51 |
387 | 52 if string.find(ua, 'MSIE') > -1: |
53 bt['isIE'] = True | |
54 else: | |
55 bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
56 # Safari oder Chrome identification |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
57 try: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
58 nav = ua[string.find(ua, '('):] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
59 nav1=ua[string.find(ua,')'):] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
60 nav2=nav1[string.find(nav1,'('):] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
61 nav3=nav2[string.find(nav2,')'):] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
62 ie = string.split(nav, "; ")[1] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
63 ie1 =string.split(nav1, " ")[2] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
64 ie2 =string.split(nav3, " ")[1] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
65 ie3 =string.split(nav3, " ")[2] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
66 if string.find(ie3, "Safari") >-1: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
67 bt['versSafariChrome']=string.split(ie2, "/")[1] |
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 # IE identification |
387 | 70 try: |
71 nav = ua[string.find(ua, '('):] | |
72 ie = string.split(nav, "; ")[1] | |
73 if string.find(ie, "MSIE") > -1: | |
74 bt['versIE'] = string.split(ie, " ")[1] | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
75 except:pass |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
76 # Firefox identification |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
77 try: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
78 nav = ua[string.find(ua, '('):] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
79 nav1=ua[string.find(ua,')'):] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
80 if string.find(ie1, "Firefox") >-1: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
81 nav5= string.split(ie1, "/")[1] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
82 logging.debug("FIREFOX: %s"%(nav5)) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
83 bt['versFirefox']=nav5[0:3] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
84 except:pass |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
85 #Opera identification |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
86 try: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
87 if string.find(ua,"Opera") >-1: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
88 nav = ua[string.find(ua, '('):] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
89 nav1=nav[string.find(nav,')'):] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
90 bt['versOpera']=string.split(nav1,"/")[2] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
91 except:pass |
387 | 92 |
93 bt['isMac'] = string.find(ua, 'Macintosh') > -1 | |
94 bt['isWin'] = string.find(ua, 'Windows') > -1 | |
95 bt['isIEWin'] = bt['isIE'] and bt['isWin'] | |
96 bt['isIEMac'] = bt['isIE'] and bt['isMac'] | |
97 bt['staticHTML'] = False | |
98 | |
99 return bt | |
234 | 100 |
464 | 101 def getParentPath(path, cnt=1): |
102 """returns pathname shortened by cnt""" | |
103 # make sure path doesn't end with / | |
104 path = path.rstrip('/') | |
105 # split by /, shorten, and reassemble | |
106 return '/'.join(path.split('/')[0:-cnt]) | |
107 | |
461 | 108 |
22 | 109 ## |
110 ## documentViewer class | |
111 ## | |
112 class documentViewer(Folder): | |
0 | 113 """document viewer""" |
114 meta_type="Document viewer" | |
115 | |
116 security=ClassSecurityInfo() | |
22 | 117 manage_options=Folder.manage_options+( |
0 | 118 {'label':'main config','action':'changeDocumentViewerForm'}, |
119 ) | |
463 | 120 |
121 metadataService = None | |
122 """MetaDataFolder instance""" | |
0 | 123 |
22 | 124 # templates and forms |
125 viewer_main = PageTemplateFile('zpt/viewer_main', globals()) | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
126 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
|
127 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
|
128 toc_figures = PageTemplateFile('zpt/toc_figures', globals()) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
129 page_main_images = PageTemplateFile('zpt/page_main_images', globals()) |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
130 page_main_double = PageTemplateFile('zpt/page_main_double', globals()) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
131 page_main_text = PageTemplateFile('zpt/page_main_text', globals()) |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
132 page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
140 | 133 page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) |
99 | 134 page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) |
404 | 135 page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals()) |
22 | 136 head_main = PageTemplateFile('zpt/head_main', globals()) |
137 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
57 | 138 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
139 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
140 |
68 | 141 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
22 | 142 |
0 | 143 |
95 | 144 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
0 | 145 """init document viewer""" |
146 self.id=id | |
147 self.title=title | |
25 | 148 self.thumbcols = thumbcols |
149 self.thumbrows = thumbrows | |
32 | 150 # authgroups is list of authorized groups (delimited by ,) |
151 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
|
152 # 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
|
153 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
154 templateFolder = Folder('template') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
155 #self['template'] = templateFolder # Zope-2.12 style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
156 self._setObject('template',templateFolder) # old style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
157 try: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
158 import MpdlXmlTextServer |
132 | 159 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
160 #templateFolder['fulltextclient'] = xmlRpcClient |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
161 templateFolder._setObject('fulltextclient',textServer) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
162 except Exception, e: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
163 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
463 | 164 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
165 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
166 from Products.zogiLib.zogiLib import zogiLib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
167 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
168 #templateFolder['zogilib'] = zogilib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
169 templateFolder._setObject('zogilib',zogilib) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
170 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
171 logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
463 | 172 |
173 try: | |
174 # assume MetaDataFolder instance is called metadata | |
175 self.metadataService = getattr(self, 'metadata') | |
176 except Exception, e: | |
177 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
178 | |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
179 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
180 # proxy text server methods to fulltextclient |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
181 def getTextPage(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
182 """get page""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
183 return self.template.fulltextclient.getTextPage(**args) |
22 | 184 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
185 def getOrigPages(self, **args): |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
186 """get page""" |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
187 return self.template.fulltextclient.getOrigPages(**args) |
396 | 188 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
189 def getOrigPagesNorm(self, **args): |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
190 """get page""" |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
191 return self.template.fulltextclient.getOrigPagesNorm(**args) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
192 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
193 def getQuery(self, **args): |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
194 """get query in search""" |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
195 return self.template.fulltextclient.getQuery(**args) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
196 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
197 def getSearch(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
198 """get search""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
199 return self.template.fulltextclient.getSearch(**args) |
256 | 200 |
201 def getGisPlaces(self, **args): | |
307 | 202 """get gis places""" |
256 | 203 return self.template.fulltextclient.getGisPlaces(**args) |
307 | 204 |
205 def getAllGisPlaces(self, **args): | |
310 | 206 """get all gis places """ |
207 return self.template.fulltextclient.getAllGisPlaces(**args) | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
208 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
209 def getTranslate(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
210 """get translate""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
211 return self.template.fulltextclient.getTranslate(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
212 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
213 def getLemma(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
214 """get lemma""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
215 return self.template.fulltextclient.getLemma(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
216 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
217 def getLemmaQuery(self, **args): |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
218 """get query""" |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
219 return self.template.fulltextclient.getLemmaQuery(**args) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
220 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
221 def getLex(self, **args): |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
222 """get lex""" |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
223 return self.template.fulltextclient.getLex(**args) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
224 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
225 def getToc(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
226 """get toc""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
227 return self.template.fulltextclient.getToc(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
228 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
229 def getTocPage(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
230 """get tocpage""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
231 return self.template.fulltextclient.getTocPage(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
232 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
233 |
68 | 234 security.declareProtected('View','thumbs_rss') |
235 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
236 ''' | |
237 view it | |
238 @param mode: defines how to access the document behind url | |
239 @param url: url which contains display information | |
240 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
241 | |
242 ''' | |
167 | 243 logging.debug("HHHHHHHHHHHHHH:load the rss") |
458 | 244 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
68 | 245 |
246 if not hasattr(self, 'template'): | |
247 # create template folder if it doesn't exist | |
248 self.manage_addFolder('template') | |
249 | |
250 if not self.digilibBaseUrl: | |
251 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
252 | |
253 docinfo = self.getDocinfo(mode=mode,url=url) | |
338 | 254 #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
345 | 255 pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) |
331 | 256 ''' ZDES ''' |
68 | 257 pt = getattr(self.template, 'thumbs_main_rss') |
258 | |
259 if viewMode=="auto": # automodus gewaehlt | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
260 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
68 | 261 viewMode="text" |
262 else: | |
263 viewMode="images" | |
264 | |
265 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
266 | |
22 | 267 security.declareProtected('View','index_html') |
405 | 268 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None): |
464 | 269 """ |
22 | 270 view it |
57 | 271 @param mode: defines how to access the document behind url |
22 | 272 @param url: url which contains display information |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
273 @param viewMode: if images display images, if text display text, default is auto (text,images or auto) |
99 | 274 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
464 | 275 """ |
0 | 276 |
345 | 277 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
22 | 278 |
279 if not hasattr(self, 'template'): | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
280 # this won't work |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
281 logging.error("template folder missing!") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
282 return "ERROR: template folder missing!" |
22 | 283 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
284 if not getattr(self, 'digilibBaseUrl', None): |
132 | 285 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
22 | 286 |
25 | 287 docinfo = self.getDocinfo(mode=mode,url=url) |
97 | 288 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
289 if tocMode != "thumbs": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
290 # get table of contents |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
291 docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
455 | 292 |
293 # auto viewMode: text_dict if text else images | |
294 if viewMode=="auto": | |
295 if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): | |
296 #texturl gesetzt und textViewer konfiguriert | |
127 | 297 viewMode="text_dict" |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
298 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
299 viewMode="images" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
300 |
455 | 301 pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode) |
127 | 302 |
455 | 303 if viewMode != 'images' and docinfo.get('textURLPath', None): |
304 # get full text page | |
305 page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo) | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
306 pageinfo['textPage'] = page |
455 | 307 |
308 # get template /template/viewer_main | |
309 pt = getattr(self.template, 'viewer_main') | |
310 # and execute with parameters | |
311 return pt(docinfo=docinfo, pageinfo=pageinfo, viewMode=viewMode, mk=self.generateMarks(mk)) | |
0 | 312 |
74 | 313 def generateMarks(self,mk): |
314 ret="" | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
315 if mk is None: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
316 return "" |
134 | 317 if not isinstance(mk, list): |
132 | 318 mk=[mk] |
74 | 319 for m in mk: |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
320 ret+="mk=%s"%m |
74 | 321 return ret |
389 | 322 |
323 | |
387 | 324 def getBrowser(self): |
325 """getBrowser the version of browser """ | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
326 bt = browserCheck(self) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
327 logging.debug("BROWSER VERSION: %s"%(bt)) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
328 return bt |
387 | 329 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
330 def findDigilibUrl(self): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
331 """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
|
332 url = self.template.zogilib.getDLBaseUrl() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
333 return url |
126 | 334 |
335 def getDocumentViewerURL(self): | |
336 """returns the URL of this instance""" | |
337 return self.absolute_url() | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
338 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
339 def getStyle(self, idx, selected, style=""): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
340 """returns a string with the given style and append 'sel' if path == selected.""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
341 #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
|
342 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
343 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
344 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
345 return style |
74 | 346 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
347 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'): |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
348 """returns URL to documentviewer with parameter param set to val or from dict params""" |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
349 # copy existing request params |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
350 urlParams=self.REQUEST.form.copy() |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
351 # change single param |
25 | 352 if param is not None: |
31 | 353 if val is None: |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
354 if urlParams.has_key(param): |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
355 del urlParams[param] |
25 | 356 else: |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
357 urlParams[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
358 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
359 # change more params |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
360 if params is not None: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
361 for k in params.keys(): |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
362 v = params[k] |
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 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
365 if urlParams.has_key(k): |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
366 del urlParams[k] |
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: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
369 urlParams[k] = v |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
370 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
371 # FIXME: does this belong here? |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
372 if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
373 urlParams["mode"] = "imagepath" |
464 | 374 urlParams["url"] = getParentPath(urlParams["url"]) |
31 | 375 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
376 # quote values and assemble into query string (not escaping '/') |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
377 ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()]) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
378 #ps = urllib.urlencode(urlParams) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
379 if baseUrl is None: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
380 baseUrl = self.REQUEST['URL1'] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
381 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
382 url = "%s?%s"%(baseUrl, ps) |
25 | 383 return url |
384 | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
385 |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
386 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None): |
68 | 387 """link to documentviewer with parameter param set to val""" |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
388 return self.getLink(param, val, params, baseUrl, '&') |
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
389 |
57 | 390 def getInfo_xml(self,url,mode): |
391 """returns info about the document as XML""" | |
392 | |
393 if not self.digilibBaseUrl: | |
394 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
395 | |
396 docinfo = self.getDocinfo(mode=mode,url=url) | |
397 pt = getattr(self.template, 'info_xml') | |
398 return pt(docinfo=docinfo) | |
399 | |
394 | 400 def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True): |
401 """returns new option state""" | |
397 | 402 if not self.REQUEST.SESSION.has_key(optionName): |
394 | 403 # not in session -- initial |
404 opt = {'lastState': newState, 'state': initialState} | |
405 else: | |
397 | 406 opt = self.REQUEST.SESSION.get(optionName) |
394 | 407 if opt['lastState'] != newState: |
408 # state in session has changed -- toggle | |
409 opt['state'] = not opt['state'] | |
410 opt['lastState'] = newState | |
411 | |
412 self.REQUEST.SESSION[optionName] = opt | |
413 return opt['state'] | |
0 | 414 |
35 | 415 def isAccessible(self, docinfo): |
32 | 416 """returns if access to the resource is granted""" |
417 access = docinfo.get('accessType', None) | |
167 | 418 logging.debug("documentViewer (accessOK) access type %s"%access) |
45 | 419 if access is not None and access == 'free': |
167 | 420 logging.debug("documentViewer (accessOK) access is free") |
32 | 421 return True |
45 | 422 elif access is None or access in self.authgroups: |
35 | 423 # only local access -- only logged in users |
424 user = getSecurityManager().getUser() | |
167 | 425 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
35 | 426 if user is not None: |
427 #print "user: ", user | |
428 return (user.getUserName() != "Anonymous User") | |
429 else: | |
430 return False | |
32 | 431 |
167 | 432 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
32 | 433 return False |
35 | 434 |
32 | 435 |
73 | 436 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
29 | 437 """gibt param von dlInfo aus""" |
31 | 438 if docinfo is None: |
439 docinfo = {} | |
73 | 440 |
441 for x in range(cut): | |
464 | 442 path=getParentPath(path) |
78 | 443 |
40 | 444 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 445 |
167 | 446 logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) |
29 | 447 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
448 txt = getHttpData(infoUrl) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
449 if txt is None: |
40 | 450 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
451 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
452 dom = ET.fromstring(txt) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
453 #dom = Parse(txt) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
454 size=getText(dom.find("size")) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
455 #sizes=dom.xpath("//dir/size") |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
456 logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size) |
29 | 457 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
458 if size: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
459 docinfo['numPages'] = int(size) |
31 | 460 else: |
461 docinfo['numPages'] = 0 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
462 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
463 # TODO: produce and keep list of image names and numbers |
31 | 464 |
465 return docinfo | |
32 | 466 |
174 | 467 def getIndexMetaPath(self,url): |
468 """gib nur den Pfad zurueck""" | |
469 regexp = re.compile(r".*(experimental|permanent)/(.*)") | |
470 regpath = regexp.match(url) | |
471 if (regpath==None): | |
472 return "" | |
224 | 473 logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2)) |
174 | 474 return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2)) |
475 | |
225 | 476 |
477 | |
174 | 478 def getIndexMetaUrl(self,url): |
479 """returns utr of index.meta document at url""" | |
480 | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
481 metaUrl = None |
35 | 482 if url.startswith("http://"): |
483 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
484 metaUrl = url |
35 | 485 else: |
486 # online path | |
487 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 488 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 489 if not metaUrl.endswith("index.meta"): |
490 metaUrl += "/index.meta" | |
174 | 491 |
492 return metaUrl | |
493 | |
494 def getDomFromIndexMeta(self, url): | |
495 """get dom from index meta""" | |
496 dom = None | |
497 metaUrl = self.getIndexMetaUrl(url) | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
498 |
174 | 499 logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
500 txt=getHttpData(metaUrl) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
501 if txt is None: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
502 raise IOError("Unable to read index meta from %s"%(url)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
503 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
504 dom = ET.fromstring(txt) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
505 #dom = Parse(txt) |
35 | 506 return dom |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
507 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
508 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
509 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
510 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
511 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
512 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
513 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
514 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
515 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
516 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
517 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
518 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
519 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
520 txt=getHttpData(metaUrl) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
521 if txt is None: |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
522 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
523 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
524 dom = ET.fromstring(txt) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
525 #dom = Parse(txt) |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
526 return dom |
35 | 527 |
528 | |
70 | 529 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 530 """gets authorization info from the index.meta file at path or given by dom""" |
167 | 531 logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) |
32 | 532 |
533 access = None | |
534 | |
535 if docinfo is None: | |
536 docinfo = {} | |
537 | |
538 if dom is None: | |
78 | 539 for x in range(cut): |
464 | 540 path=getParentPath(path) |
174 | 541 dom = self.getDomFromIndexMeta(path) |
46 | 542 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
543 acc = dom.find(".//access-conditions/access") |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
544 if acc is not None: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
545 acctype = acc.get('type') |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
546 #acctype = dom.xpath("//access-conditions/access/@type") |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
547 if acctype: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
548 access=acctype |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
549 if access in ['group', 'institution']: |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
550 access = dom.find(".//access-conditions/access/name").text.lower() |
32 | 551 |
552 docinfo['accessType'] = access | |
553 return docinfo | |
29 | 554 |
32 | 555 |
70 | 556 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 557 """gets bibliographical info from the index.meta file at path or given by dom""" |
167 | 558 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 559 |
22 | 560 if docinfo is None: |
561 docinfo = {} | |
78 | 562 |
22 | 563 if dom is None: |
78 | 564 for x in range(cut): |
70 | 565 path=getParentDir(path) |
174 | 566 dom = self.getDomFromIndexMeta(path) |
567 | |
568 docinfo['indexMetaPath']=self.getIndexMetaPath(path); | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
569 |
167 | 570 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
463 | 571 if self.metadataService is not None: |
462 | 572 # put all raw bib fields in dict "bib" |
463 | 573 bib = self.metadataService.getBibData(dom=dom) |
462 | 574 docinfo['bib'] = bib |
575 bibtype = bib.get('@type', None) | |
576 docinfo['bib_type'] = bibtype | |
577 # also store DC metadata for convenience | |
463 | 578 dc = self.metadataService.getDCMappedData(bib) |
462 | 579 docinfo['creator'] = dc.get('creator',None) |
580 docinfo['title'] = dc.get('title',None) | |
581 docinfo['date'] = dc.get('date',None) | |
582 else: | |
463 | 583 logging.error("MetadataService not found!") |
22 | 584 return docinfo |
83 | 585 |
454 | 586 |
587 # TODO: is this needed? | |
218 | 588 def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
589 """gets name info from the index.meta file at path or given by dom""" | |
590 if docinfo is None: | |
591 docinfo = {} | |
592 | |
593 if dom is None: | |
594 for x in range(cut): | |
464 | 595 path=getParentPath(path) |
218 | 596 dom = self.getDomFromIndexMeta(path) |
330 | 597 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
598 docinfo['name']=getText(dom.find("name")) |
230 | 599 logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) |
218 | 600 return docinfo |
463 | 601 |
83 | 602 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
603 def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
604 """parse texttool tag in index meta""" |
167 | 605 logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
606 if docinfo is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
607 docinfo = {} |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
608 if docinfo.get('lang', None) is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
609 docinfo['lang'] = '' # default keine Sprache gesetzt |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
610 if dom is None: |
174 | 611 dom = self.getDomFromIndexMeta(url) |
463 | 612 |
613 texttool = self.metadata.getTexttoolData(dom=dom) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
614 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
615 archivePath = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
616 archiveName = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
617 |
454 | 618 archiveName = getText(dom.find("name")) |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
619 if not archiveName: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
620 logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
621 |
454 | 622 archivePath = getText(dom.find("archive-path")) |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
623 if archivePath: |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
624 # clean up archive path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
625 if archivePath[0] != '/': |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
626 archivePath = '/' + archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
627 if archiveName and (not archivePath.endswith(archiveName)): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
628 archivePath += "/" + archiveName |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
629 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
630 # try to get archive-path from url |
167 | 631 logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url)) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
632 if (not url.startswith('http')): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
633 archivePath = url.replace('index.meta', '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
634 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
635 if archivePath is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
636 # we balk without archive-path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
637 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
22 | 638 |
463 | 639 imageDir = texttool.get('image', None) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
640 |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
641 if not imageDir: |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
642 # we balk with no image tag / not necessary anymore because textmode is now standard |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
643 #raise IOError("No text-tool info in %s"%(url)) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
644 imageDir = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
645 #xquery="//pb" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
646 docinfo['imagePath'] = "" # keine Bilder |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
647 docinfo['imageURL'] = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
648 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
649 if imageDir and archivePath: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
650 #print "image: ", imageDir, " archivepath: ", archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
651 imageDir = os.path.join(archivePath, imageDir) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
652 imageDir = imageDir.replace("/mpiwg/online", '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
653 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
654 docinfo['imagePath'] = imageDir |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
655 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
656 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
657 |
463 | 658 viewerUrl = texttool.get('digiliburlprefix', None) |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
659 if viewerUrl: |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
660 docinfo['viewerURL'] = viewerUrl |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
661 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
662 # old style text URL |
463 | 663 textUrl = texttool.get('text', None) |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
664 if textUrl: |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
665 if urlparse.urlparse(textUrl)[0] == "": #keine url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
666 textUrl = os.path.join(archivePath, textUrl) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
667 # fix URLs starting with /mpiwg/online |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
668 if textUrl.startswith("/mpiwg/online"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
669 textUrl = textUrl.replace("/mpiwg/online", '', 1) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
670 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
671 docinfo['textURL'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
672 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
673 # new style text-url-path |
463 | 674 textUrl = texttool.get('text-url-path', None) |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
675 if textUrl: |
102 | 676 docinfo['textURLPath'] = textUrl |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
677 textUrlkurz = string.split(textUrl, ".")[0] |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
678 docinfo['textURLPathkurz'] = textUrlkurz |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
679 #if not docinfo['imagePath']: |
102 | 680 # text-only, no page images |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
681 #docinfo = self.getNumTextPages(docinfo) |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
682 |
463 | 683 # get bib info |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
684 docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag |
454 | 685 # TODO: is this needed here? |
228 | 686 docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) |
386 | 687 |
463 | 688 # TODO: what to do with presentation? |
689 presentationUrl = texttool.get('presentation', None) | |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
690 if presentationUrl: # ueberschreibe diese durch presentation informationen |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
691 # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
692 # durch den relativen Pfad auf die presentation infos |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
693 presentationPath = presentationUrl |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
694 if url.endswith("index.meta"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
695 presentationUrl = url.replace('index.meta', presentationPath) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
696 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
697 presentationUrl = url + "/" + presentationPath |
102 | 698 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
699 docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
700 |
463 | 701 # get authorization |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
702 docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
703 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
704 return docinfo |
22 | 705 |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
706 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
707 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
708 """gets the bibliographical information from the preseantion entry in texttools |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
709 """ |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
710 dom=self.getPresentationInfoXML(url) |
454 | 711 docinfo['author']=getText(dom.find(".//author")) |
712 docinfo['title']=getText(dom.find(".//title")) | |
713 docinfo['year']=getText(dom.find(".//date")) | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
714 return docinfo |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
715 |
70 | 716 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
22 | 717 """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
167 | 718 logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) |
22 | 719 if docinfo is None: |
720 docinfo = {} | |
29 | 721 path=path.replace("/mpiwg/online","") |
22 | 722 docinfo['imagePath'] = path |
73 | 723 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
78 | 724 |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
725 pathorig=path |
78 | 726 for x in range(cut): |
464 | 727 path=getParentPath(path) |
167 | 728 logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) |
31 | 729 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
22 | 730 docinfo['imageURL'] = imageUrl |
731 | |
460 | 732 #TODO: use getDocinfoFromIndexMeta |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
733 #path ist the path to the images it assumes that the index.meta file is one level higher. |
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
734 docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
735 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
22 | 736 return docinfo |
20 | 737 |
22 | 738 |
464 | 739 def OLDgetDocinfo(self, mode, url): |
22 | 740 """returns docinfo depending on mode""" |
167 | 741 logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) |
22 | 742 # look for cached docinfo in session |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
743 if self.REQUEST.SESSION.has_key('docinfo'): |
22 | 744 docinfo = self.REQUEST.SESSION['docinfo'] |
745 # check if its still current | |
746 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
455 | 747 logging.debug("documentViewer (getdocinfo) docinfo in session. keys=%s"%docinfo.keys()) |
22 | 748 return docinfo |
455 | 749 |
22 | 750 # new docinfo |
751 docinfo = {'mode': mode, 'url': url} | |
455 | 752 # add self url |
753 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
754 if mode=="texttool": | |
755 # index.meta with texttool information | |
22 | 756 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) |
757 elif mode=="imagepath": | |
455 | 758 # folder with images, index.meta optional |
22 | 759 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) |
70 | 760 elif mode=="filepath": |
455 | 761 # filename |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
762 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
22 | 763 else: |
167 | 764 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
765 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
766 |
458 | 767 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
768 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) | |
460 | 769 # store in session |
22 | 770 self.REQUEST.SESSION['docinfo'] = docinfo |
771 return docinfo | |
464 | 772 |
773 | |
774 def getDocinfo(self, mode, url): | |
775 """returns docinfo depending on mode""" | |
776 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) | |
777 # look for cached docinfo in session | |
778 if self.REQUEST.SESSION.has_key('docinfo'): | |
779 docinfo = self.REQUEST.SESSION['docinfo'] | |
780 # check if its still current | |
781 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: | |
782 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
783 return docinfo | |
784 | |
785 # new docinfo | |
786 docinfo = {'mode': mode, 'url': url} | |
787 # add self url | |
788 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
789 # get index.meta DOM | |
790 docUrl = None | |
791 metaDom = None | |
792 if mode=="texttool": | |
793 # url points to document dir or index.meta | |
794 metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
795 docUrl = url.replace('/index.meta', '') | |
796 if metaDom is None: | |
797 raise IOError("Unable to find index.meta for mode=texttool!") | |
798 | |
799 elif mode=="imagepath": | |
800 # url points to folder with images, index.meta optional | |
801 # asssume index.meta in parent dir | |
802 docUrl = getParentPath(url) | |
803 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
804 | |
805 elif mode=="filepath": | |
806 # url points to image file, index.meta optional | |
807 # asssume index.meta is two path segments up | |
808 docUrl = getParentPath(url, 2) | |
809 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
810 | |
811 else: | |
812 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
813 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
814 | |
815 docinfo['documentUrl'] = docUrl | |
816 # process index.meta contents | |
817 if metaDom is not None: | |
818 # document directory name and path | |
819 resource = self.metadataService.getResourceData(dom=metaDom) | |
820 if resource: | |
821 docinfo = self.getDocinfoFromResource(docinfo, resource) | |
822 | |
823 # texttool info | |
824 texttool = self.metadataService.getTexttoolData(dom=metaDom) | |
825 if texttool: | |
826 docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
827 | |
828 # bib info | |
829 bib = self.metadataService.getBibData(dom=metaDom) | |
830 if bib: | |
831 docinfo = self.getDocinfoFromBib(docinfo, bib) | |
832 | |
833 # auth info | |
834 access = self.metadataService.getAccessData(dom=metaDom) | |
835 if access: | |
836 docinfo = self.getDocinfoFromAccess(docinfo, access) | |
837 | |
838 # image path | |
839 if mode != 'texttool': | |
840 # override image path from texttool | |
841 docinfo['imagePath'] = url | |
842 | |
843 # number of images from digilib | |
844 if docinfo.get('imagePath', None): | |
845 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath'] | |
846 docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath']) | |
847 | |
848 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) | |
849 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) | |
850 # store in session | |
851 self.REQUEST.SESSION['docinfo'] = docinfo | |
852 return docinfo | |
853 | |
854 def getDocinfoFromResource(self, docinfo, resource): | |
855 """reads contents of resource element into docinfo""" | |
856 docName = resource.get('name', None) | |
857 docinfo['documentName'] = docName | |
858 docPath = resource.get('archive-path', None) | |
859 if docPath: | |
860 # clean up document path | |
861 if docPath[0] != '/': | |
862 docPath = '/' + docPath | |
863 | |
864 if docName and (not docPath.endswith(docName)): | |
865 docPath += "/" + docName | |
866 | |
867 else: | |
868 # use docUrl as docPath | |
869 docUrl = docinfo['documentURL'] | |
870 if not docUrl.startswith('http:'): | |
871 docPath = docUrl | |
872 | |
873 docinfo['documentPath'] = docPath | |
874 return docinfo | |
875 | |
876 def getDocinfoFromTexttool(self, docinfo, texttool): | |
877 """reads contents of texttool element into docinfo""" | |
878 # image dir | |
879 imageDir = texttool.get('image', None) | |
880 docPath = docinfo.get('documentPath', None) | |
881 if imageDir and docPath: | |
882 #print "image: ", imageDir, " archivepath: ", archivePath | |
883 imageDir = os.path.join(docPath, imageDir) | |
884 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
885 docinfo['imagePath'] = imageDir | |
886 | |
887 # old style text URL | |
888 textUrl = texttool.get('text', None) | |
889 if textUrl and docPath: | |
890 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
891 textUrl = os.path.join(docPath, textUrl) | |
892 # fix URLs starting with /mpiwg/online | |
893 textUrl = textUrl.replace('/mpiwg/online', '', 1) | |
894 | |
895 docinfo['textURL'] = textUrl | |
896 | |
897 # new style text-url-path | |
898 textUrl = texttool.get('text-url-path', None) | |
899 if textUrl: | |
900 docinfo['textURLPath'] = textUrl | |
901 #TODO: ugly: | |
902 #textUrlkurz = string.split(textUrl, ".")[0] | |
903 #docinfo['textURLPathkurz'] = textUrlkurz | |
904 | |
905 # old presentation stuff | |
906 presentation = texttool.get('presentation', None) | |
907 if presentation and docPath: | |
908 docinfo['presentationPath'] = os.path.join(docPath, presentation) | |
909 | |
910 return docinfo | |
911 | |
912 def getDocinfoFromBib(self, docinfo, bib): | |
913 """reads contents of bib element into docinfo""" | |
914 # put all raw bib fields in dict "bib" | |
915 docinfo['bib'] = bib | |
916 bibtype = bib.get('@type', None) | |
917 docinfo['bibType'] = bibtype | |
918 # also store DC metadata for convenience | |
919 dc = self.metadataService.getDCMappedData(bib) | |
920 docinfo['creator'] = dc.get('creator',None) | |
921 docinfo['title'] = dc.get('title',None) | |
922 docinfo['date'] = dc.get('date',None) | |
923 return docinfo | |
924 | |
925 def getDocinfoFromAccess(self, docinfo, acc): | |
926 """reads contents of access element into docinfo""" | |
927 #TODO: also read resource type | |
928 try: | |
929 acctype = accc['@attr']['type'] | |
930 if acctype: | |
931 access=acctype | |
932 if access in ['group', 'institution']: | |
933 access = acc['name'].lower() | |
934 | |
935 docinfo['accessType'] = access | |
936 | |
937 except: | |
938 pass | |
939 | |
940 return docinfo | |
941 | |
942 def getDocinfoFromDigilib(self, docinfo, path): | |
943 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path | |
944 # fetch data | |
945 txt = getHttpData(infoUrl) | |
946 if not txt: | |
947 logging.error("Unable to get dir-info from %s"%(infoUrl)) | |
948 return docinfo | |
949 | |
950 dom = ET.fromstring(txt) | |
951 size = getText(dom.find("size")) | |
952 logging.debug("getDocinfoFromDigilib: size=%s"%size) | |
953 if size: | |
954 docinfo['numPages'] = int(size) | |
955 else: | |
956 docinfo['numPages'] = 0 | |
957 | |
958 # TODO: produce and keep list of image names and numbers | |
959 return docinfo | |
960 | |
961 | |
405 | 962 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): |
22 | 963 """returns pageinfo with the given parameters""" |
964 pageinfo = {} | |
25 | 965 current = getInt(current) |
338 | 966 |
25 | 967 pageinfo['current'] = current |
968 rows = int(rows or self.thumbrows) | |
969 pageinfo['rows'] = rows | |
970 cols = int(cols or self.thumbcols) | |
971 pageinfo['cols'] = cols | |
972 grpsize = cols * rows | |
973 pageinfo['groupsize'] = grpsize | |
460 | 974 # what does this do? |
61 | 975 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
976 # int(current / grpsize) * grpsize +1)) | |
22 | 977 pageinfo['start'] = start |
25 | 978 pageinfo['end'] = start + grpsize |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
979 if (docinfo is not None) and ('numPages' in docinfo): |
25 | 980 np = int(docinfo['numPages']) |
981 pageinfo['end'] = min(pageinfo['end'], np) | |
982 pageinfo['numgroups'] = int(np / grpsize) | |
983 if np % grpsize > 0: | |
460 | 984 pageinfo['numgroups'] += 1 |
985 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
986 pageinfo['viewMode'] = viewMode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
987 pageinfo['tocMode'] = tocMode |
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
988 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
989 #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1') |
398 | 990 pageinfo['query'] = self.REQUEST.get('query','') |
384 | 991 pageinfo['queryType'] = self.REQUEST.get('queryType','') |
95 | 992 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
99 | 993 pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
384 | 994 pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
95 | 995 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
105 | 996 pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') |
460 | 997 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
998 # WTF?: | |
999 toc = int(pageinfo['tocPN']) | |
1000 pageinfo['textPages'] =int(toc) | |
158 | 1001 |
460 | 1002 # What does this do? |
99 | 1003 if 'tocSize_%s'%tocMode in docinfo: |
1004 tocSize = int(docinfo['tocSize_%s'%tocMode]) | |
1005 tocPageSize = int(pageinfo['tocPageSize']) | |
128 | 1006 # cached toc |
99 | 1007 if tocSize%tocPageSize>0: |
1008 tocPages=tocSize/tocPageSize+1 | |
1009 else: | |
1010 tocPages=tocSize/tocPageSize | |
460 | 1011 |
1012 pageinfo['tocPN'] = min(tocPages,toc) | |
1013 | |
95 | 1014 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
112 | 1015 pageinfo['sn'] =self.REQUEST.get('sn','') |
22 | 1016 return pageinfo |
460 | 1017 |
463 | 1018 |
1019 security.declareProtected('View management screens','changeDocumentViewerForm') | |
1020 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
22 | 1021 |
460 | 1022 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
22 | 1023 """init document viewer""" |
1024 self.title=title | |
1025 self.digilibBaseUrl = digilibBaseUrl | |
25 | 1026 self.thumbrows = thumbrows |
1027 self.thumbcols = thumbcols | |
32 | 1028 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
463 | 1029 try: |
1030 # assume MetaDataFolder instance is called metadata | |
1031 self.metadataService = getattr(self, 'metadata') | |
1032 except Exception, e: | |
1033 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
1034 | |
22 | 1035 if RESPONSE is not None: |
1036 RESPONSE.redirect('manage_main') | |
0 | 1037 |
1038 def manage_AddDocumentViewerForm(self): | |
1039 """add the viewer form""" | |
22 | 1040 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 1041 return pt() |
1042 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1043 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 1044 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
1045 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 1046 self._setObject(id,newObj) |
1047 | |
1048 if RESPONSE is not None: | |
1049 RESPONSE.redirect('manage_main') | |
22 | 1050 |
1051 ## DocumentViewerTemplate class | |
1052 class DocumentViewerTemplate(ZopePageTemplate): | |
1053 """Template for document viewer""" | |
1054 meta_type="DocumentViewer Template" | |
1055 | |
1056 | |
1057 def manage_addDocumentViewerTemplateForm(self): | |
1058 """Form for adding""" | |
1059 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
1060 return pt() | |
1061 | |
1062 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
1063 REQUEST=None, submit=None): | |
1064 "Add a Page Template with optional file content." | |
1065 | |
1066 self._setObject(id, DocumentViewerTemplate(id)) | |
1067 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
1068 txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
167 | 1069 logging.info("txt %s:"%txt) |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
1070 ob.pt_edit(txt,"text/html") |
22 | 1071 if title: |
1072 ob.pt_setTitle(title) | |
1073 try: | |
1074 u = self.DestinationURL() | |
1075 except AttributeError: | |
1076 u = REQUEST['URL1'] | |
1077 | |
1078 u = "%s/%s" % (u, urllib.quote(id)) | |
1079 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
1080 return '' | |
1081 | |
1082 | |
41 | 1083 |