Mercurial > hg > documentViewer
annotate documentViewer.py @ 482:7ca8ac7db06e elementtree
more new template stuff. more batching methods in documentViewer.
| author | casties |
|---|---|
| date | Tue, 16 Aug 2011 18:27:08 +0200 |
| parents | 50a28442f21c |
| children | ab9b34a1c62a |
| rev | line source |
|---|---|
| 0 | 1 from OFS.Folder import Folder |
| 480 | 2 from OFS.Image import File |
| 0 | 3 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate |
| 52 | 4 from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
| 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 #from Ft.Xml import EMPTY_NAMESPACE, Parse |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
10 #import Ft.Xml.Domlette |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
11 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
12 import xml.etree.ElementTree as ET |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
13 |
| 0 | 14 import os.path |
| 31 | 15 import sys |
| 0 | 16 import urllib |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
17 import logging |
| 61 | 18 import math |
| 46 | 19 import urlparse |
| 174 | 20 import re |
| 389 | 21 import string |
| 231 | 22 |
| 458 | 23 from SrvTxtUtils import getInt, getText, getHttpData |
| 24 | |
| 52 | 25 def logger(txt,method,txt2): |
| 26 """logging""" | |
| 27 logging.info(txt+ txt2) | |
| 28 | |
| 29 | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
30 def serializeNode(node, encoding="utf-8"): |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
31 """returns a string containing node as XML""" |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
32 s = ET.tostring(node) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
33 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
34 # 4Suite: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
35 # stream = cStringIO.StringIO() |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
36 # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
37 # s = stream.getvalue() |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
38 # stream.close() |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
39 return s |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
40 |
| 387 | 41 def browserCheck(self): |
| 42 """check the browsers request to find out the browser type""" | |
| 43 bt = {} | |
| 44 ua = self.REQUEST.get_header("HTTP_USER_AGENT") | |
| 45 bt['ua'] = ua | |
| 46 bt['isIE'] = False | |
| 47 bt['isN4'] = False | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
48 bt['versFirefox']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
49 bt['versIE']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
50 bt['versSafariChrome']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
51 bt['versOpera']="" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
52 |
| 387 | 53 if string.find(ua, 'MSIE') > -1: |
| 54 bt['isIE'] = True | |
| 55 else: | |
| 56 bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
57 # Safari oder Chrome identification |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
58 try: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
59 nav = ua[string.find(ua, '('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
60 nav1=ua[string.find(ua,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
61 nav2=nav1[string.find(nav1,'('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
62 nav3=nav2[string.find(nav2,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
63 ie = string.split(nav, "; ")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
64 ie1 =string.split(nav1, " ")[2] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
65 ie2 =string.split(nav3, " ")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
66 ie3 =string.split(nav3, " ")[2] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
67 if string.find(ie3, "Safari") >-1: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
68 bt['versSafariChrome']=string.split(ie2, "/")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
69 except: pass |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
70 # IE identification |
| 387 | 71 try: |
| 72 nav = ua[string.find(ua, '('):] | |
| 73 ie = string.split(nav, "; ")[1] | |
| 74 if string.find(ie, "MSIE") > -1: | |
| 75 bt['versIE'] = string.split(ie, " ")[1] | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
76 except:pass |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
77 # Firefox identification |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
78 try: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
79 nav = ua[string.find(ua, '('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
80 nav1=ua[string.find(ua,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
81 if string.find(ie1, "Firefox") >-1: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
82 nav5= string.split(ie1, "/")[1] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
83 logging.debug("FIREFOX: %s"%(nav5)) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
84 bt['versFirefox']=nav5[0:3] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
85 except:pass |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
86 #Opera identification |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
87 try: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
88 if string.find(ua,"Opera") >-1: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
89 nav = ua[string.find(ua, '('):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
90 nav1=nav[string.find(nav,')'):] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
91 bt['versOpera']=string.split(nav1,"/")[2] |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
92 except:pass |
| 387 | 93 |
| 94 bt['isMac'] = string.find(ua, 'Macintosh') > -1 | |
| 95 bt['isWin'] = string.find(ua, 'Windows') > -1 | |
| 96 bt['isIEWin'] = bt['isIE'] and bt['isWin'] | |
| 97 bt['isIEMac'] = bt['isIE'] and bt['isMac'] | |
| 98 bt['staticHTML'] = False | |
| 99 | |
| 100 return bt | |
| 234 | 101 |
| 464 | 102 def getParentPath(path, cnt=1): |
| 103 """returns pathname shortened by cnt""" | |
| 104 # make sure path doesn't end with / | |
| 105 path = path.rstrip('/') | |
| 106 # split by /, shorten, and reassemble | |
| 107 return '/'.join(path.split('/')[0:-cnt]) | |
| 108 | |
| 461 | 109 |
| 22 | 110 ## |
| 111 ## documentViewer class | |
| 112 ## | |
| 113 class documentViewer(Folder): | |
| 0 | 114 """document viewer""" |
| 115 meta_type="Document viewer" | |
| 116 | |
| 117 security=ClassSecurityInfo() | |
| 22 | 118 manage_options=Folder.manage_options+( |
| 0 | 119 {'label':'main config','action':'changeDocumentViewerForm'}, |
| 120 ) | |
| 463 | 121 |
| 122 metadataService = None | |
| 123 """MetaDataFolder instance""" | |
| 0 | 124 |
| 22 | 125 # templates and forms |
| 479 | 126 viewer_text = PageTemplateFile('zpt/viewer_text', globals()) |
| 22 | 127 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
|
128 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
|
129 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
|
130 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
|
131 page_main_images = PageTemplateFile('zpt/page_main_images', globals()) |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
132 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
|
133 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
|
134 page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
| 140 | 135 page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) |
| 99 | 136 page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) |
| 404 | 137 page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals()) |
| 22 | 138 head_main = PageTemplateFile('zpt/head_main', globals()) |
| 57 | 139 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
| 480 | 140 # TODO: can this be nicer? |
| 141 docuviewer_css = File('docuviewer_css','',open(os.path.join(package_home(globals()),'css/docuviewer.css')), content_type='text/css') | |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
142 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
143 |
| 68 | 144 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
| 22 | 145 |
| 0 | 146 |
| 95 | 147 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
| 0 | 148 """init document viewer""" |
| 149 self.id=id | |
| 150 self.title=title | |
| 25 | 151 self.thumbcols = thumbcols |
| 152 self.thumbrows = thumbrows | |
| 32 | 153 # authgroups is list of authorized groups (delimited by ,) |
| 154 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
|
155 # 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
|
156 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
157 templateFolder = Folder('template') |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
158 #self['template'] = templateFolder # Zope-2.12 style |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
159 self._setObject('template',templateFolder) # old style |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
160 try: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
161 import MpdlXmlTextServer |
| 132 | 162 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
|
163 #templateFolder['fulltextclient'] = xmlRpcClient |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
164 templateFolder._setObject('fulltextclient',textServer) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
165 except Exception, e: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
166 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
| 463 | 167 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
168 try: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
169 from Products.zogiLib.zogiLib import zogiLib |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
170 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
|
171 #templateFolder['zogilib'] = zogilib |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
172 templateFolder._setObject('zogilib',zogilib) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
173 except Exception, e: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
174 logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
| 463 | 175 |
| 176 try: | |
| 177 # assume MetaDataFolder instance is called metadata | |
| 178 self.metadataService = getattr(self, 'metadata') | |
| 179 except Exception, e: | |
| 180 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 181 | |
| 477 | 182 if digilibBaseUrl is not None: |
| 183 self.digilibBaseUrl = digilibBaseUrl | |
| 184 | |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
185 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
186 # proxy text server methods to fulltextclient |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
187 def getTextPage(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
188 """get page""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
189 return self.template.fulltextclient.getTextPage(**args) |
| 22 | 190 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
191 def getOrigPages(self, **args): |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
192 """get page""" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
193 return self.template.fulltextclient.getOrigPages(**args) |
| 396 | 194 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
195 def getOrigPagesNorm(self, **args): |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
196 """get page""" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
197 return self.template.fulltextclient.getOrigPagesNorm(**args) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
198 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
199 def getQuery(self, **args): |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
200 """get query in search""" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
201 return self.template.fulltextclient.getQuery(**args) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
202 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
203 def getSearch(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
204 """get search""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
205 return self.template.fulltextclient.getSearch(**args) |
| 256 | 206 |
| 207 def getGisPlaces(self, **args): | |
| 307 | 208 """get gis places""" |
| 256 | 209 return self.template.fulltextclient.getGisPlaces(**args) |
| 307 | 210 |
| 211 def getAllGisPlaces(self, **args): | |
| 310 | 212 """get all gis places """ |
| 213 return self.template.fulltextclient.getAllGisPlaces(**args) | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
214 |
| 478 | 215 def getWordInfo(self, **args): |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
216 """get translate""" |
| 478 | 217 return self.template.fulltextclient.getWordInfo(**args) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
218 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
219 def getLemma(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
220 """get lemma""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
221 return self.template.fulltextclient.getLemma(**args) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
222 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
223 def getLemmaQuery(self, **args): |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
224 """get query""" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
225 return self.template.fulltextclient.getLemmaQuery(**args) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
226 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
227 def getLex(self, **args): |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
228 """get lex""" |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
229 return self.template.fulltextclient.getLex(**args) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
230 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
231 def getToc(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
232 """get toc""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
233 return self.template.fulltextclient.getToc(**args) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
234 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
235 def getTocPage(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
236 """get tocpage""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
237 return self.template.fulltextclient.getTocPage(**args) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
238 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
239 |
| 68 | 240 security.declareProtected('View','thumbs_rss') |
| 241 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
| 242 ''' | |
| 243 view it | |
| 244 @param mode: defines how to access the document behind url | |
| 245 @param url: url which contains display information | |
| 246 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
| 247 | |
| 248 ''' | |
| 167 | 249 logging.debug("HHHHHHHHHHHHHH:load the rss") |
| 458 | 250 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| 68 | 251 |
| 252 if not hasattr(self, 'template'): | |
| 253 # create template folder if it doesn't exist | |
| 254 self.manage_addFolder('template') | |
| 255 | |
| 256 if not self.digilibBaseUrl: | |
| 257 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 258 | |
| 259 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 338 | 260 #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
| 345 | 261 pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) |
| 331 | 262 ''' ZDES ''' |
| 68 | 263 pt = getattr(self.template, 'thumbs_main_rss') |
| 264 | |
| 265 if viewMode=="auto": # automodus gewaehlt | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
266 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
| 68 | 267 viewMode="text" |
| 268 else: | |
| 269 viewMode="images" | |
| 270 | |
| 271 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
| 465 | 272 |
| 68 | 273 |
| 22 | 274 security.declareProtected('View','index_html') |
| 472 | 275 def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1): |
| 464 | 276 """ |
| 471 | 277 view page |
| 278 @param url: url which contains display information | |
| 57 | 279 @param mode: defines how to access the document behind url |
| 471 | 280 @param viewMode: 'images': display images, 'text': display text, default is 'auto' |
| 281 @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text' | |
| 99 | 282 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
| 464 | 283 """ |
| 0 | 284 |
| 475 | 285 logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewType=%s start=%s pn=%s"%(mode,url,viewMode,viewType,start,pn)) |
| 22 | 286 |
| 287 if not hasattr(self, 'template'): | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
288 # this won't work |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
289 logging.error("template folder missing!") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
290 return "ERROR: template folder missing!" |
| 22 | 291 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
292 if not getattr(self, 'digilibBaseUrl', None): |
| 132 | 293 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 22 | 294 |
| 25 | 295 docinfo = self.getDocinfo(mode=mode,url=url) |
| 97 | 296 |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
297 if tocMode != "thumbs": |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
298 # get table of contents |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
299 docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
| 455 | 300 |
| 471 | 301 # auto viewMode: text if there is a text else images |
| 455 | 302 if viewMode=="auto": |
| 303 if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): | |
| 471 | 304 viewMode = "text" |
| 305 viewType = "dict" | |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
306 else: |
| 471 | 307 viewMode = "images" |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
308 |
| 474 | 309 elif viewMode == "text_dict": |
| 310 # legacy fix | |
| 311 viewMode = "text" | |
| 312 viewType = "dict" | |
| 313 | |
| 475 | 314 # stringify viewType |
| 315 if isinstance(viewType, list): | |
| 478 | 316 logging.debug("index_html: viewType is list:%s"%viewType) |
| 475 | 317 viewType = ','.join([t for t in viewType if t]) |
| 318 | |
| 472 | 319 pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode) |
| 469 | 320 |
| 475 | 321 # get template /template/viewer_$viewMode |
| 322 pt = getattr(self.template, 'viewer_%s'%viewMode, None) | |
| 323 if pt is None: | |
| 324 logging.error("No template for viewMode=%s!"%viewMode) | |
| 325 # TODO: error page? | |
| 326 return "No template for viewMode=%s!"%viewMode | |
| 327 | |
| 455 | 328 # and execute with parameters |
| 471 | 329 return pt(docinfo=docinfo, pageinfo=pageinfo) |
| 0 | 330 |
| 74 | 331 def generateMarks(self,mk): |
| 332 ret="" | |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
333 if mk is None: |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
334 return "" |
| 134 | 335 if not isinstance(mk, list): |
| 132 | 336 mk=[mk] |
| 74 | 337 for m in mk: |
|
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
338 ret+="mk=%s"%m |
| 74 | 339 return ret |
| 389 | 340 |
| 341 | |
| 387 | 342 def getBrowser(self): |
| 343 """getBrowser the version of browser """ | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
344 bt = browserCheck(self) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
345 logging.debug("BROWSER VERSION: %s"%(bt)) |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
346 return bt |
| 387 | 347 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
348 def findDigilibUrl(self): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
349 """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
|
350 url = self.template.zogilib.getDLBaseUrl() |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
351 return url |
| 480 | 352 |
| 353 def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None): | |
| 354 """returns URL to digilib Scaler with params""" | |
| 355 url = None | |
| 356 if docinfo is not None: | |
| 357 url = docinfo.get('imageURL', None) | |
| 358 | |
| 359 if url is None: | |
| 360 url = "%s/servlet/Scaler?"%self.digilibBaseUrl | |
| 361 if fn is None and docinfo is not None: | |
| 362 fn = docinfo.get('imagePath','') | |
| 363 | |
| 364 url += "fn=%s"%fn | |
| 365 | |
| 366 if pn: | |
| 367 url += "&pn=%s"%pn | |
| 368 | |
| 369 url += "&dw=%s&dh=%s"%(dw,dh) | |
| 370 return url | |
| 126 | 371 |
| 372 def getDocumentViewerURL(self): | |
| 373 """returns the URL of this instance""" | |
| 374 return self.absolute_url() | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
375 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
376 def getStyle(self, idx, selected, style=""): |
| 480 | 377 """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
|
378 #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
|
379 if idx == selected: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
380 return style + 'sel' |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
381 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
382 return style |
| 74 | 383 |
| 478 | 384 def getParams(self, param=None, val=None, params=None, duplicates=None): |
| 469 | 385 """returns dict with URL parameters. |
| 386 | |
| 387 Takes URL parameters and additionally param=val or dict params. | |
| 388 Deletes key if value is None.""" | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
389 # copy existing request params |
| 469 | 390 newParams=self.REQUEST.form.copy() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
391 # change single param |
| 25 | 392 if param is not None: |
| 31 | 393 if val is None: |
| 469 | 394 if newParams.has_key(param): |
| 395 del newParams[param] | |
| 25 | 396 else: |
| 469 | 397 newParams[param] = str(val) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
398 |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
399 # change more params |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
400 if params is not None: |
| 478 | 401 for (k, v) in params.items(): |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
402 if v is None: |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
403 # val=None removes param |
| 469 | 404 if newParams.has_key(k): |
| 405 del newParams[k] | |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
406 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
407 else: |
| 469 | 408 newParams[k] = v |
| 478 | 409 |
| 410 if duplicates: | |
| 411 # eliminate lists (coming from duplicate keys) | |
| 412 for (k,v) in newParams.items(): | |
| 413 if isinstance(v, list): | |
| 414 if duplicates == 'comma': | |
| 415 # make comma-separated list of non-empty entries | |
| 416 newParams[k] = ','.join([t for t in v if t]) | |
| 417 elif duplicates == 'first': | |
| 418 # take first non-empty entry | |
| 419 newParams[k] = [t for t in v if t][0] | |
| 420 | |
| 469 | 421 return newParams |
| 422 | |
| 478 | 423 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
| 469 | 424 """returns URL to documentviewer with parameter param set to val or from dict params""" |
| 478 | 425 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
|
426 # quote values and assemble into query string (not escaping '/') |
| 475 | 427 ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()]) |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
428 if baseUrl is None: |
| 469 | 429 baseUrl = self.getDocumentViewerURL() |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
430 |
|
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
431 url = "%s?%s"%(baseUrl, ps) |
| 25 | 432 return url |
| 433 | |
| 478 | 434 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
| 68 | 435 """link to documentviewer with parameter param set to val""" |
| 478 | 436 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
|
437 |
| 469 | 438 |
| 57 | 439 def getInfo_xml(self,url,mode): |
| 440 """returns info about the document as XML""" | |
| 441 if not self.digilibBaseUrl: | |
| 442 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 443 | |
| 444 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 445 pt = getattr(self.template, 'info_xml') | |
| 446 return pt(docinfo=docinfo) | |
| 447 | |
| 35 | 448 def isAccessible(self, docinfo): |
| 32 | 449 """returns if access to the resource is granted""" |
| 450 access = docinfo.get('accessType', None) | |
| 167 | 451 logging.debug("documentViewer (accessOK) access type %s"%access) |
| 465 | 452 if access == 'free': |
| 167 | 453 logging.debug("documentViewer (accessOK) access is free") |
| 32 | 454 return True |
| 465 | 455 |
| 45 | 456 elif access is None or access in self.authgroups: |
| 35 | 457 # only local access -- only logged in users |
| 458 user = getSecurityManager().getUser() | |
| 167 | 459 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
| 35 | 460 if user is not None: |
| 461 #print "user: ", user | |
| 462 return (user.getUserName() != "Anonymous User") | |
| 463 else: | |
| 464 return False | |
| 32 | 465 |
| 167 | 466 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
| 32 | 467 return False |
| 35 | 468 |
| 464 | 469 |
| 470 | |
| 471 def getDocinfo(self, mode, url): | |
| 472 """returns docinfo depending on mode""" | |
| 473 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) | |
| 474 # look for cached docinfo in session | |
| 475 if self.REQUEST.SESSION.has_key('docinfo'): | |
| 476 docinfo = self.REQUEST.SESSION['docinfo'] | |
| 477 # check if its still current | |
| 478 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: | |
| 479 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) | |
| 480 return docinfo | |
| 481 | |
| 482 # new docinfo | |
| 483 docinfo = {'mode': mode, 'url': url} | |
| 484 # add self url | |
| 485 docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
| 477 | 486 docinfo['digilibBaseUrl'] = self.digilibBaseUrl |
| 464 | 487 # get index.meta DOM |
| 488 docUrl = None | |
| 489 metaDom = None | |
| 490 if mode=="texttool": | |
| 491 # url points to document dir or index.meta | |
| 492 metaDom = self.metadataService.getDomFromPathOrUrl(url) | |
| 493 docUrl = url.replace('/index.meta', '') | |
| 494 if metaDom is None: | |
| 495 raise IOError("Unable to find index.meta for mode=texttool!") | |
| 496 | |
| 497 elif mode=="imagepath": | |
| 498 # url points to folder with images, index.meta optional | |
| 499 # asssume index.meta in parent dir | |
| 500 docUrl = getParentPath(url) | |
| 501 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 502 | |
| 503 elif mode=="filepath": | |
| 504 # url points to image file, index.meta optional | |
| 505 # asssume index.meta is two path segments up | |
| 506 docUrl = getParentPath(url, 2) | |
| 507 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) | |
| 508 | |
| 509 else: | |
| 510 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | |
| 511 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) | |
| 512 | |
| 513 docinfo['documentUrl'] = docUrl | |
| 514 # process index.meta contents | |
| 473 | 515 if metaDom is not None and metaDom.tag == 'resource': |
| 464 | 516 # document directory name and path |
| 517 resource = self.metadataService.getResourceData(dom=metaDom) | |
| 518 if resource: | |
| 519 docinfo = self.getDocinfoFromResource(docinfo, resource) | |
| 520 | |
| 521 # texttool info | |
| 522 texttool = self.metadataService.getTexttoolData(dom=metaDom) | |
| 523 if texttool: | |
| 524 docinfo = self.getDocinfoFromTexttool(docinfo, texttool) | |
| 525 | |
| 526 # bib info | |
| 527 bib = self.metadataService.getBibData(dom=metaDom) | |
| 528 if bib: | |
| 529 docinfo = self.getDocinfoFromBib(docinfo, bib) | |
| 465 | 530 else: |
| 531 # no bib - try info.xml | |
| 532 docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) | |
| 464 | 533 |
| 534 # auth info | |
| 535 access = self.metadataService.getAccessData(dom=metaDom) | |
| 536 if access: | |
| 537 docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 538 | |
| 466 | 539 # attribution info |
| 540 attribution = self.metadataService.getAttributionData(dom=metaDom) | |
| 541 if attribution: | |
| 542 logging.debug("getDocinfo: attribution=%s"%repr(attribution)) | |
| 543 docinfo['attribution'] = attribution | |
| 544 #docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 545 | |
| 546 # copyright info | |
| 547 copyright = self.metadataService.getCopyrightData(dom=metaDom) | |
| 548 if copyright: | |
| 549 logging.debug("getDocinfo: copyright=%s"%repr(copyright)) | |
| 550 docinfo['copyright'] = copyright | |
| 551 #docinfo = self.getDocinfoFromAccess(docinfo, access) | |
| 552 | |
| 464 | 553 # image path |
| 554 if mode != 'texttool': | |
| 477 | 555 # override image path from texttool with url |
| 465 | 556 docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1) |
| 464 | 557 |
| 558 # number of images from digilib | |
| 559 if docinfo.get('imagePath', None): | |
| 560 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath'] | |
| 561 docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath']) | |
| 562 | |
| 563 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) | |
| 564 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) | |
| 565 # store in session | |
| 566 self.REQUEST.SESSION['docinfo'] = docinfo | |
| 567 return docinfo | |
| 568 | |
| 569 def getDocinfoFromResource(self, docinfo, resource): | |
| 570 """reads contents of resource element into docinfo""" | |
| 571 docName = resource.get('name', None) | |
| 572 docinfo['documentName'] = docName | |
| 573 docPath = resource.get('archive-path', None) | |
| 574 if docPath: | |
| 575 # clean up document path | |
| 576 if docPath[0] != '/': | |
| 577 docPath = '/' + docPath | |
| 578 | |
| 579 if docName and (not docPath.endswith(docName)): | |
| 580 docPath += "/" + docName | |
| 581 | |
| 582 else: | |
| 583 # use docUrl as docPath | |
| 584 docUrl = docinfo['documentURL'] | |
| 585 if not docUrl.startswith('http:'): | |
| 586 docPath = docUrl | |
| 465 | 587 if docPath: |
| 588 # fix URLs starting with /mpiwg/online | |
| 589 docPath = docPath.replace('/mpiwg/online', '', 1) | |
| 590 | |
| 464 | 591 docinfo['documentPath'] = docPath |
| 592 return docinfo | |
| 593 | |
| 594 def getDocinfoFromTexttool(self, docinfo, texttool): | |
| 595 """reads contents of texttool element into docinfo""" | |
| 596 # image dir | |
| 597 imageDir = texttool.get('image', None) | |
| 598 docPath = docinfo.get('documentPath', None) | |
| 599 if imageDir and docPath: | |
| 600 #print "image: ", imageDir, " archivepath: ", archivePath | |
| 601 imageDir = os.path.join(docPath, imageDir) | |
| 602 imageDir = imageDir.replace('/mpiwg/online', '', 1) | |
| 603 docinfo['imagePath'] = imageDir | |
| 604 | |
| 605 # old style text URL | |
| 606 textUrl = texttool.get('text', None) | |
| 607 if textUrl and docPath: | |
| 608 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
| 609 textUrl = os.path.join(docPath, textUrl) | |
| 610 | |
| 611 docinfo['textURL'] = textUrl | |
| 612 | |
| 613 # new style text-url-path | |
| 614 textUrl = texttool.get('text-url-path', None) | |
| 615 if textUrl: | |
| 616 docinfo['textURLPath'] = textUrl | |
| 468 | 617 |
| 618 # page flow | |
| 619 docinfo['pageFlow'] = texttool.get('page-flow', 'ltr') | |
| 620 | |
| 621 # odd pages are left | |
| 476 | 622 docinfo['oddPage'] = texttool.get('odd-scan-position', 'left') |
| 468 | 623 |
| 469 | 624 # number of title page (0: not defined) |
| 468 | 625 docinfo['titlePage'] = texttool.get('title-scan-no', 0) |
| 464 | 626 |
| 627 # old presentation stuff | |
| 628 presentation = texttool.get('presentation', None) | |
| 629 if presentation and docPath: | |
| 465 | 630 if presentation.startswith('http:'): |
| 631 docinfo['presentationUrl'] = presentation | |
| 632 else: | |
| 633 docinfo['presentationUrl'] = os.path.join(docPath, presentation) | |
| 464 | 634 |
| 468 | 635 |
| 464 | 636 return docinfo |
| 637 | |
| 638 def getDocinfoFromBib(self, docinfo, bib): | |
| 639 """reads contents of bib element into docinfo""" | |
| 465 | 640 logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
| 464 | 641 # put all raw bib fields in dict "bib" |
| 642 docinfo['bib'] = bib | |
| 643 bibtype = bib.get('@type', None) | |
| 644 docinfo['bibType'] = bibtype | |
| 645 # also store DC metadata for convenience | |
| 646 dc = self.metadataService.getDCMappedData(bib) | |
| 647 docinfo['creator'] = dc.get('creator',None) | |
| 648 docinfo['title'] = dc.get('title',None) | |
| 649 docinfo['date'] = dc.get('date',None) | |
| 650 return docinfo | |
| 651 | |
| 652 def getDocinfoFromAccess(self, docinfo, acc): | |
| 653 """reads contents of access element into docinfo""" | |
| 654 #TODO: also read resource type | |
| 465 | 655 logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
| 464 | 656 try: |
| 465 | 657 acctype = acc['@attr']['type'] |
| 464 | 658 if acctype: |
| 659 access=acctype | |
| 660 if access in ['group', 'institution']: | |
| 661 access = acc['name'].lower() | |
| 662 | |
| 663 docinfo['accessType'] = access | |
| 664 | |
| 665 except: | |
| 666 pass | |
| 667 | |
| 668 return docinfo | |
| 669 | |
| 670 def getDocinfoFromDigilib(self, docinfo, path): | |
| 671 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path | |
| 672 # fetch data | |
| 673 txt = getHttpData(infoUrl) | |
| 674 if not txt: | |
| 675 logging.error("Unable to get dir-info from %s"%(infoUrl)) | |
| 676 return docinfo | |
| 677 | |
| 678 dom = ET.fromstring(txt) | |
| 679 size = getText(dom.find("size")) | |
| 680 logging.debug("getDocinfoFromDigilib: size=%s"%size) | |
| 681 if size: | |
| 682 docinfo['numPages'] = int(size) | |
| 683 else: | |
| 684 docinfo['numPages'] = 0 | |
| 685 | |
| 686 # TODO: produce and keep list of image names and numbers | |
| 687 return docinfo | |
| 688 | |
| 689 | |
| 465 | 690 def getDocinfoFromPresentationInfoXml(self,docinfo): |
| 691 """gets DC-like bibliographical information from the presentation entry in texttools""" | |
| 692 url = docinfo.get('presentationUrl', None) | |
| 693 if not url: | |
| 694 logging.error("getDocinfoFromPresentation: no URL!") | |
| 695 return docinfo | |
| 696 | |
| 697 dom = None | |
| 698 metaUrl = None | |
| 699 if url.startswith("http://"): | |
| 700 # real URL | |
| 701 metaUrl = url | |
| 702 else: | |
| 703 # online path | |
| 704 | |
| 705 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 706 metaUrl=server+url | |
| 707 | |
| 708 txt=getHttpData(metaUrl) | |
| 709 if txt is None: | |
| 710 logging.error("Unable to read info.xml from %s"%(url)) | |
| 711 return docinfo | |
| 712 | |
| 713 dom = ET.fromstring(txt) | |
| 714 docinfo['creator']=getText(dom.find(".//author")) | |
| 715 docinfo['title']=getText(dom.find(".//title")) | |
| 716 docinfo['date']=getText(dom.find(".//date")) | |
| 717 return docinfo | |
| 718 | |
| 719 | |
| 478 | 720 def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None): |
| 22 | 721 """returns pageinfo with the given parameters""" |
| 478 | 722 logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewType=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewType,tocMode)) |
| 22 | 723 pageinfo = {} |
| 471 | 724 pageinfo['viewMode'] = viewMode |
| 725 pageinfo['viewType'] = viewType | |
| 726 pageinfo['tocMode'] = tocMode | |
| 727 | |
| 25 | 728 current = getInt(current) |
| 729 pageinfo['current'] = current | |
| 480 | 730 pageinfo['pn'] = current |
| 25 | 731 rows = int(rows or self.thumbrows) |
| 732 pageinfo['rows'] = rows | |
| 733 cols = int(cols or self.thumbcols) | |
| 734 pageinfo['cols'] = cols | |
| 735 grpsize = cols * rows | |
| 736 pageinfo['groupsize'] = grpsize | |
| 476 | 737 # is start is empty use one around current |
| 61 | 738 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
| 739 # int(current / grpsize) * grpsize +1)) | |
| 22 | 740 pageinfo['start'] = start |
| 480 | 741 |
| 469 | 742 np = int(docinfo.get('numPages', 0)) |
| 743 if np == 0: | |
| 744 # numPages unknown - maybe we can get it from text page | |
| 745 if docinfo.get('textURLPath', None): | |
| 746 # cache text page as well | |
| 480 | 747 pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=current, docinfo=docinfo, pageinfo=pageinfo) |
| 469 | 748 np = int(docinfo.get('numPages', 0)) |
| 749 | |
| 750 pageinfo['numgroups'] = int(np / grpsize) | |
| 751 if np % grpsize > 0: | |
| 752 pageinfo['numgroups'] += 1 | |
| 476 | 753 |
| 754 pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' | |
| 755 oddScanLeft = docinfo.get('oddPage', 'left') != 'right' | |
| 756 # add zeroth page for two columns | |
| 757 pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) | |
| 758 pageinfo['pageZero'] = pageZero | |
| 480 | 759 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np) |
| 460 | 760 |
| 480 | 761 # TODO: do we need this here? |
|
453
beb7ccb92564
first version using elementtree instead of 4suite xml
casties
parents:
405
diff
changeset
|
762 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
| 398 | 763 pageinfo['query'] = self.REQUEST.get('query','') |
| 384 | 764 pageinfo['queryType'] = self.REQUEST.get('queryType','') |
| 95 | 765 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
| 384 | 766 pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
| 476 | 767 pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) |
| 768 pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10)) | |
| 769 pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1')) | |
| 770 pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1')) | |
| 158 | 771 |
| 476 | 772 # limit tocPN |
| 99 | 773 if 'tocSize_%s'%tocMode in docinfo: |
| 476 | 774 tocSize = docinfo['tocSize_%s'%tocMode] |
| 775 tocPageSize = pageinfo['tocPageSize'] | |
| 128 | 776 # cached toc |
| 99 | 777 if tocSize%tocPageSize>0: |
| 778 tocPages=tocSize/tocPageSize+1 | |
| 779 else: | |
| 780 tocPages=tocSize/tocPageSize | |
| 460 | 781 |
| 476 | 782 pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN']) |
| 460 | 783 |
| 22 | 784 return pageinfo |
| 460 | 785 |
| 463 | 786 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
787 def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0): |
| 480 | 788 """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
|
789 batch = {} |
| 480 | 790 grpsize = rows * cols |
| 476 | 791 if maxIdx == 0: |
| 480 | 792 maxIdx = start + grpsize |
| 476 | 793 |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
794 nb = int(math.ceil(maxIdx / float(grpsize))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
795 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
796 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
797 if pageZero: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
798 ofs = 0 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
799 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
800 ofs = 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
801 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
802 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
803 s = i * grpsize + ofs |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
804 e = min((i + 1) * grpsize + ofs - 1, maxIdx) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
805 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
806 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
807 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
808 |
| 476 | 809 pages = [] |
| 810 if pageZero and start == 1: | |
| 811 # correct beginning | |
| 812 idx = 0 | |
| 813 else: | |
| 814 idx = start | |
| 815 | |
| 816 for r in range(rows): | |
| 817 row = [] | |
| 818 for c in range(cols): | |
| 819 if idx < minIdx or idx > maxIdx: | |
| 820 page = {'idx':None} | |
| 821 else: | |
| 822 page = {'idx':idx} | |
| 823 | |
| 824 idx += 1 | |
| 825 if pageFlowLtr: | |
| 826 row.append(page) | |
| 827 else: | |
| 828 row.insert(0, page) | |
| 829 | |
| 830 pages.append(row) | |
| 831 | |
| 480 | 832 if start > 1: |
| 833 batch['prevStart'] = max(start - grpsize, 1) | |
| 834 else: | |
| 835 batch['prevStart'] = None | |
| 836 | |
| 837 if start + grpsize < maxIdx: | |
| 838 batch['nextStart'] = start + grpsize | |
| 839 else: | |
| 840 batch['nextStart'] = None | |
| 841 | |
| 842 batch['pages'] = pages | |
|
482
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
843 return batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
844 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
845 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
|
846 """returns dict with information for one screenfull of data.""" |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
847 batch = {} |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
848 if end == 0: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
849 end = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
850 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
851 nb = int(math.ceil(end / float(size))) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
852 # list of all batch start and end points |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
853 batches = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
854 for i in range(nb): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
855 s = i * size + 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
856 e = min((i + 1) * size, end) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
857 batches.append({'start':s, 'end':e}) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
858 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
859 batch['batches'] = batches |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
860 # list of elements in this batch |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
861 this = [] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
862 j = 0 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
863 for i in range(start, min(start+size, end)): |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
864 if data: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
865 if fullData: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
866 d = data[i] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
867 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
868 d = data[j] |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
869 j += 1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
870 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
871 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
872 d = i+1 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
873 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
874 this.append(d) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
875 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
876 batch['this'] = this |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
877 if start > 1: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
878 batch['prevStart'] = max(start - size, 1) |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
879 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
880 batch['prevStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
881 |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
882 if start + size < end: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
883 batch['nextStart'] = start + size |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
884 else: |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
885 batch['nextStart'] = None |
|
7ca8ac7db06e
more new template stuff. more batching methods in documentViewer.
casties
parents:
480
diff
changeset
|
886 |
| 480 | 887 return batch |
| 476 | 888 |
| 889 | |
| 463 | 890 security.declareProtected('View management screens','changeDocumentViewerForm') |
| 891 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 22 | 892 |
| 460 | 893 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
| 22 | 894 """init document viewer""" |
| 895 self.title=title | |
| 896 self.digilibBaseUrl = digilibBaseUrl | |
| 25 | 897 self.thumbrows = thumbrows |
| 898 self.thumbcols = thumbcols | |
| 32 | 899 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| 463 | 900 try: |
| 901 # assume MetaDataFolder instance is called metadata | |
| 902 self.metadataService = getattr(self, 'metadata') | |
| 903 except Exception, e: | |
| 904 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) | |
| 905 | |
| 22 | 906 if RESPONSE is not None: |
| 907 RESPONSE.redirect('manage_main') | |
| 0 | 908 |
| 909 def manage_AddDocumentViewerForm(self): | |
| 910 """add the viewer form""" | |
| 22 | 911 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| 0 | 912 return pt() |
| 913 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
914 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
| 0 | 915 """add the viewer""" |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
916 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
| 0 | 917 self._setObject(id,newObj) |
| 918 | |
| 919 if RESPONSE is not None: | |
| 920 RESPONSE.redirect('manage_main') | |
| 22 | 921 |
| 922 ## DocumentViewerTemplate class | |
| 923 class DocumentViewerTemplate(ZopePageTemplate): | |
| 924 """Template for document viewer""" | |
| 925 meta_type="DocumentViewer Template" | |
| 926 | |
| 927 | |
| 928 def manage_addDocumentViewerTemplateForm(self): | |
| 929 """Form for adding""" | |
| 930 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
| 931 return pt() | |
| 932 | |
| 933 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
| 934 REQUEST=None, submit=None): | |
| 935 "Add a Page Template with optional file content." | |
| 936 | |
| 937 self._setObject(id, DocumentViewerTemplate(id)) | |
| 938 ob = getattr(self, id) | |
|
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
939 txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
| 167 | 940 logging.info("txt %s:"%txt) |
|
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
941 ob.pt_edit(txt,"text/html") |
| 22 | 942 if title: |
| 943 ob.pt_setTitle(title) | |
| 944 try: | |
| 945 u = self.DestinationURL() | |
| 946 except AttributeError: | |
| 947 u = REQUEST['URL1'] | |
| 948 | |
| 949 u = "%s/%s" % (u, urllib.quote(id)) | |
| 950 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
| 951 return '' | |
| 952 | |
| 953 | |
| 41 | 954 |