Mercurial > hg > documentViewer
annotate documentViewer.py @ 90:6a4a72033d58
new version with new full-text infrastructure and some more changed templates
author | casties |
---|---|
date | Thu, 08 Apr 2010 13:04:51 +0200 |
parents | a6e4f9b6729a |
children | db6d594aa4d9 |
rev | line source |
---|---|
46 | 1 |
0 | 2 from OFS.Folder import Folder |
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 | |
9 from Ft.Xml.Domlette import NonvalidatingReader | |
10 from Ft.Xml.Domlette import PrettyPrint, Print | |
38 | 11 from Ft.Xml import EMPTY_NAMESPACE, Parse |
0 | 12 |
83 | 13 |
0 | 14 import Ft.Xml.XPath |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
15 import cStringIO |
83 | 16 import xmlrpclib |
0 | 17 import os.path |
31 | 18 import sys |
0 | 19 import cgi |
20 import urllib | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
21 import logging |
61 | 22 import math |
52 | 23 |
46 | 24 import urlparse |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
25 from types import * |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
26 |
52 | 27 def logger(txt,method,txt2): |
28 """logging""" | |
29 logging.info(txt+ txt2) | |
30 | |
31 | |
25 | 32 def getInt(number, default=0): |
33 """returns always an int (0 in case of problems)""" | |
34 try: | |
35 return int(number) | |
36 except: | |
62 | 37 return int(default) |
25 | 38 |
0 | 39 def getTextFromNode(nodename): |
46 | 40 """get the cdata content of a node""" |
32 | 41 if nodename is None: |
42 return "" | |
0 | 43 nodelist=nodename.childNodes |
44 rc = "" | |
45 for node in nodelist: | |
46 if node.nodeType == node.TEXT_NODE: | |
47 rc = rc + node.data | |
48 return rc | |
49 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
50 def serializeNode(node, encoding='utf-8'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
51 """returns a string containing node as XML""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
52 buf = cStringIO.StringIO() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
53 Print(node, stream=buf, encoding=encoding) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
54 s = buf.getvalue() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
55 buf.close() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
56 return s |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
57 |
35 | 58 |
59 def getParentDir(path): | |
60 """returns pathname shortened by one""" | |
61 return '/'.join(path.split('/')[0:-1]) | |
62 | |
63 | |
0 | 64 import socket |
65 | |
32 | 66 def urlopen(url,timeout=2): |
0 | 67 """urlopen mit timeout""" |
32 | 68 socket.setdefaulttimeout(timeout) |
0 | 69 ret=urllib.urlopen(url) |
70 socket.setdefaulttimeout(5) | |
71 return ret | |
72 | |
73 | |
22 | 74 ## |
75 ## documentViewer class | |
76 ## | |
77 class documentViewer(Folder): | |
0 | 78 """document viewer""" |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
79 #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" |
46 | 80 |
0 | 81 meta_type="Document viewer" |
82 | |
83 security=ClassSecurityInfo() | |
22 | 84 manage_options=Folder.manage_options+( |
0 | 85 {'label':'main config','action':'changeDocumentViewerForm'}, |
86 ) | |
87 | |
22 | 88 # templates and forms |
89 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
|
90 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
|
91 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
|
92 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
|
93 page_main_images = PageTemplateFile('zpt/page_main_images', globals()) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
94 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
|
95 page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
22 | 96 head_main = PageTemplateFile('zpt/head_main', globals()) |
97 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
57 | 98 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
22 | 99 |
68 | 100 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
22 | 101 security.declareProtected('View management screens','changeDocumentViewerForm') |
102 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
103 | |
0 | 104 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
105 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): |
0 | 106 """init document viewer""" |
107 self.id=id | |
108 self.title=title | |
25 | 109 self.thumbcols = thumbcols |
110 self.thumbrows = thumbrows | |
32 | 111 # authgroups is list of authorized groups (delimited by ,) |
112 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
|
113 # 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
|
114 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
115 templateFolder = Folder('template') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
116 #self['template'] = templateFolder # Zope-2.12 style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
117 self._setObject('template',templateFolder) # old style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
118 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
119 from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
120 xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
121 #templateFolder['fulltextclient'] = xmlRpcClient |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
122 templateFolder._setObject('fulltextclient',xmlRpcClient) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
123 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
124 logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e)) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
125 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
126 from Products.zogiLib.zogiLib import zogiLib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
127 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
|
128 #templateFolder['zogilib'] = zogilib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
129 templateFolder._setObject('zogilib',zogilib) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
130 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
131 logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
132 |
22 | 133 |
68 | 134 security.declareProtected('View','thumbs_rss') |
135 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
136 ''' | |
137 view it | |
138 @param mode: defines how to access the document behind url | |
139 @param url: url which contains display information | |
140 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
141 | |
142 ''' | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
143 logging.debug("HHHHHHHHHHHHHH:load the rss") |
68 | 144 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
145 | |
146 if not hasattr(self, 'template'): | |
147 # create template folder if it doesn't exist | |
148 self.manage_addFolder('template') | |
149 | |
150 if not self.digilibBaseUrl: | |
151 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
152 | |
153 docinfo = self.getDocinfo(mode=mode,url=url) | |
154 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
155 pt = getattr(self.template, 'thumbs_main_rss') | |
156 | |
157 if viewMode=="auto": # automodus gewaehlt | |
158 if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert | |
159 viewMode="text" | |
160 else: | |
161 viewMode="images" | |
162 | |
163 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
164 | |
22 | 165 security.declareProtected('View','index_html') |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
166 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None): |
22 | 167 ''' |
168 view it | |
57 | 169 @param mode: defines how to access the document behind url |
22 | 170 @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
|
171 @param viewMode: if images display images, if text display text, default is auto (text,images or auto) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
172 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures) |
22 | 173 ''' |
0 | 174 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
175 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
22 | 176 |
177 if not hasattr(self, 'template'): | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
178 # this won't work |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
179 logging.error("template folder missing!") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
180 return "ERROR: template folder missing!" |
22 | 181 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
182 if not getattr(self, 'digilibBaseUrl', None): |
22 | 183 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
184 | |
25 | 185 docinfo = self.getDocinfo(mode=mode,url=url) |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
186 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
187 if tocMode != "thumbs": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
188 # get table of contents |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
189 docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
190 |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
191 if viewMode=="auto": # automodus gewaehlt |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
192 if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
193 viewMode="text" |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
194 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
195 viewMode="images" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
196 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
197 pt = getattr(self.template, 'viewer_main') |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
198 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
0 | 199 |
74 | 200 def generateMarks(self,mk): |
201 ret="" | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
202 if mk is None: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
203 return "" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
204 if type(mk) is not ListType: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
205 mk=[mk] |
74 | 206 for m in mk: |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
207 ret+="mk=%s"%m |
74 | 208 return ret |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
209 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
210 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
211 def findDigilibUrl(self): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
212 """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
|
213 url = self.template.zogilib.getDLBaseUrl() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
214 return url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
215 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
216 def getStyle(self, idx, selected, style=""): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
217 """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
|
218 #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
|
219 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
220 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
221 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
222 return style |
74 | 223 |
25 | 224 def getLink(self,param=None,val=None): |
225 """link to documentviewer with parameter param set to val""" | |
35 | 226 params=self.REQUEST.form.copy() |
25 | 227 if param is not None: |
31 | 228 if val is None: |
229 if params.has_key(param): | |
230 del params[param] | |
25 | 231 else: |
35 | 232 params[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
233 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
234 if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
78 | 235 params["mode"] = "imagepath" |
236 params["url"] = getParentDir(params["url"]) | |
31 | 237 |
35 | 238 # quote values and assemble into query string |
239 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
240 url=self.REQUEST['URL1']+"?"+ps | |
25 | 241 return url |
242 | |
68 | 243 def getLinkAmp(self,param=None,val=None): |
244 """link to documentviewer with parameter param set to val""" | |
245 params=self.REQUEST.form.copy() | |
246 if param is not None: | |
247 if val is None: | |
248 if params.has_key(param): | |
249 del params[param] | |
250 else: | |
251 params[param] = str(val) | |
252 | |
253 # quote values and assemble into query string | |
254 logging.info("XYXXXXX: %s"%repr(params.items())) | |
255 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
256 url=self.REQUEST['URL1']+"?"+ps | |
257 return url | |
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
258 |
57 | 259 def getInfo_xml(self,url,mode): |
260 """returns info about the document as XML""" | |
261 | |
262 if not self.digilibBaseUrl: | |
263 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
264 | |
265 docinfo = self.getDocinfo(mode=mode,url=url) | |
266 pt = getattr(self.template, 'info_xml') | |
267 return pt(docinfo=docinfo) | |
268 | |
0 | 269 |
35 | 270 def isAccessible(self, docinfo): |
32 | 271 """returns if access to the resource is granted""" |
272 access = docinfo.get('accessType', None) | |
52 | 273 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
45 | 274 if access is not None and access == 'free': |
52 | 275 logger("documentViewer (accessOK)", logging.INFO, "access is free") |
32 | 276 return True |
45 | 277 elif access is None or access in self.authgroups: |
35 | 278 # only local access -- only logged in users |
279 user = getSecurityManager().getUser() | |
280 if user is not None: | |
281 #print "user: ", user | |
282 return (user.getUserName() != "Anonymous User") | |
283 else: | |
284 return False | |
32 | 285 |
52 | 286 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
32 | 287 return False |
35 | 288 |
32 | 289 |
73 | 290 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
29 | 291 """gibt param von dlInfo aus""" |
40 | 292 num_retries = 3 |
31 | 293 if docinfo is None: |
294 docinfo = {} | |
73 | 295 |
296 for x in range(cut): | |
78 | 297 |
73 | 298 path=getParentDir(path) |
78 | 299 |
40 | 300 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 301 |
52 | 302 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
29 | 303 |
40 | 304 for cnt in range(num_retries): |
35 | 305 try: |
40 | 306 # dom = NonvalidatingReader.parseUri(imageUrl) |
307 txt=urllib.urlopen(infoUrl).read() | |
308 dom = Parse(txt) | |
35 | 309 break |
310 except: | |
52 | 311 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
35 | 312 else: |
40 | 313 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
29 | 314 |
37 | 315 sizes=dom.xpath("//dir/size") |
52 | 316 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
29 | 317 |
37 | 318 if sizes: |
319 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
31 | 320 else: |
321 docinfo['numPages'] = 0 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
322 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
323 # TODO: produce and keep list of image names and numbers |
31 | 324 |
325 return docinfo | |
32 | 326 |
29 | 327 |
35 | 328 def getIndexMeta(self, url): |
329 """returns dom of index.meta document at url""" | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
330 num_retries = 3 |
35 | 331 dom = None |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
332 metaUrl = None |
35 | 333 if url.startswith("http://"): |
334 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
335 metaUrl = url |
35 | 336 else: |
337 # online path | |
338 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 339 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 340 if not metaUrl.endswith("index.meta"): |
341 metaUrl += "/index.meta" | |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
342 logging.debug("METAURL: %s"%metaUrl) |
40 | 343 for cnt in range(num_retries): |
35 | 344 try: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
345 # patch dirk encoding fehler treten dann nicht mehr auf |
38 | 346 # dom = NonvalidatingReader.parseUri(metaUrl) |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
347 txt=urllib.urlopen(metaUrl).read() |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
348 dom = Parse(txt) |
40 | 349 break |
35 | 350 except: |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
351 logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
352 |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
353 if dom is None: |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
354 raise IOError("Unable to read index meta from %s"%(url)) |
35 | 355 |
356 return dom | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
357 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
358 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
359 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
360 num_retries = 3 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
361 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
362 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
363 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
364 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
365 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
366 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
367 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
368 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
369 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
370 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
371 for cnt in range(num_retries): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
372 try: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
373 # patch dirk encoding fehler treten dann nicht mehr auf |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
374 # dom = NonvalidatingReader.parseUri(metaUrl) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
375 txt=urllib.urlopen(metaUrl).read() |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
376 dom = Parse(txt) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
377 break |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
378 except: |
52 | 379 logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
380 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
381 if dom is None: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
382 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
383 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
384 return dom |
35 | 385 |
386 | |
70 | 387 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 388 """gets authorization info from the index.meta file at path or given by dom""" |
52 | 389 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
32 | 390 |
391 access = None | |
392 | |
393 if docinfo is None: | |
394 docinfo = {} | |
395 | |
396 if dom is None: | |
78 | 397 for x in range(cut): |
70 | 398 path=getParentDir(path) |
399 dom = self.getIndexMeta(path) | |
46 | 400 |
32 | 401 acctype = dom.xpath("//access-conditions/access/@type") |
402 if acctype and (len(acctype)>0): | |
403 access=acctype[0].value | |
35 | 404 if access in ['group', 'institution']: |
32 | 405 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
406 | |
407 docinfo['accessType'] = access | |
408 return docinfo | |
29 | 409 |
32 | 410 |
70 | 411 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 412 """gets bibliographical info from the index.meta file at path or given by dom""" |
59 | 413 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 414 |
22 | 415 if docinfo is None: |
416 docinfo = {} | |
78 | 417 |
22 | 418 if dom is None: |
78 | 419 for x in range(cut): |
70 | 420 path=getParentDir(path) |
421 dom = self.getIndexMeta(path) | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
422 |
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
423 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
59 | 424 # put in all raw bib fields as dict "bib" |
425 bib = dom.xpath("//bib/*") | |
426 if bib and len(bib)>0: | |
427 bibinfo = {} | |
428 for e in bib: | |
429 bibinfo[e.localName] = getTextFromNode(e) | |
430 docinfo['bib'] = bibinfo | |
431 | |
432 # extract some fields (author, title, year) according to their mapping | |
25 | 433 metaData=self.metadata.main.meta.bib |
434 bibtype=dom.xpath("//bib/@type") | |
435 if bibtype and (len(bibtype)>0): | |
436 bibtype=bibtype[0].value | |
20 | 437 else: |
25 | 438 bibtype="generic" |
59 | 439 |
25 | 440 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
59 | 441 docinfo['bib_type'] = bibtype |
25 | 442 bibmap=metaData.generateMappingForType(bibtype) |
32 | 443 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
31 | 444 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
63 | 445 try: |
446 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
447 except: pass | |
448 try: | |
449 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
450 except: pass | |
451 try: | |
452 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
453 except: pass | |
59 | 454 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
52 | 455 try: |
456 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
457 except: | |
458 docinfo['lang']='' | |
59 | 459 |
22 | 460 return docinfo |
83 | 461 |
462 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
463 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
|
464 """parse texttool tag in index meta""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
465 logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url)) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
466 if docinfo is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
467 docinfo = {} |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
468 if docinfo.get('lang', None) is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
469 docinfo['lang'] = '' # default keine Sprache gesetzt |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
470 if dom is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
471 dom = self.getIndexMeta(url) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
472 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
473 archivePath = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
474 archiveName = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
475 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
476 archiveNames = dom.xpath("//resource/name") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
477 if archiveNames and (len(archiveNames) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
478 archiveName = getTextFromNode(archiveNames[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
479 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
480 logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url)) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
481 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
482 archivePaths = dom.xpath("//resource/archive-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
483 if archivePaths and (len(archivePaths) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
484 archivePath = getTextFromNode(archivePaths[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
485 # clean up archive path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
486 if archivePath[0] != '/': |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
487 archivePath = '/' + archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
488 if archiveName and (not archivePath.endswith(archiveName)): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
489 archivePath += "/" + archiveName |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
490 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
491 # try to get archive-path from url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
492 logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url)) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
493 if (not url.startswith('http')): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
494 archivePath = url.replace('index.meta', '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
495 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
496 if archivePath is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
497 # we balk without archive-path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
498 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
22 | 499 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
500 imageDirs = dom.xpath("//texttool/image") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
501 if imageDirs and (len(imageDirs) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
502 imageDir = getTextFromNode(imageDirs[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
503 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
504 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
505 # 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
|
506 #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
|
507 imageDir = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
508 #xquery="//pb" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
509 docinfo['imagePath'] = "" # keine Bilder |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
510 docinfo['imageURL'] = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
511 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
512 if imageDir and archivePath: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
513 #print "image: ", imageDir, " archivepath: ", archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
514 imageDir = os.path.join(archivePath, imageDir) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
515 imageDir = imageDir.replace("/mpiwg/online", '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
516 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
517 docinfo['imagePath'] = imageDir |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
518 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
519 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
|
520 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
521 viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
522 if viewerUrls and (len(viewerUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
523 viewerUrl = getTextFromNode(viewerUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
524 docinfo['viewerURL'] = viewerUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
525 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
526 textUrls = dom.xpath("//texttool/text") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
527 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
528 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
529 if urlparse.urlparse(textUrl)[0] == "": #keine url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
530 textUrl = os.path.join(archivePath, textUrl) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
531 # fix URLs starting with /mpiwg/online |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
532 if textUrl.startswith("/mpiwg/online"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
533 textUrl = textUrl.replace("/mpiwg/online", '', 1) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
534 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
535 docinfo['textURL'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
536 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
537 textUrls = dom.xpath("//texttool/text-url-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
538 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
539 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
540 docinfo['textURLPath'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
541 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
542 presentationUrls = dom.xpath("//texttool/presentation") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
543 docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
544 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
545 if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
546 # 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
|
547 # durch den relativen Pfad auf die presentation infos |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
548 presentationPath = getTextFromNode(presentationUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
549 if url.endswith("index.meta"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
550 presentationUrl = url.replace('index.meta', presentationPath) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
551 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
552 presentationUrl = url + "/" + presentationPath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
553 docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
554 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
|
555 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
556 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
|
557 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
558 return docinfo |
22 | 559 |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
560 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
561 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
562 """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
|
563 """ |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
564 dom=self.getPresentationInfoXML(url) |
62 | 565 try: |
566 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
567 except: | |
568 pass | |
569 try: | |
570 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
571 except: | |
572 pass | |
573 try: | |
574 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
575 except: | |
576 pass | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
577 return docinfo |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
578 |
70 | 579 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
22 | 580 """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
52 | 581 logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
22 | 582 if docinfo is None: |
583 docinfo = {} | |
29 | 584 path=path.replace("/mpiwg/online","") |
22 | 585 docinfo['imagePath'] = path |
73 | 586 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
78 | 587 |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
588 pathorig=path |
78 | 589 for x in range(cut): |
590 path=getParentDir(path) | |
591 logging.error("PATH:"+path) | |
31 | 592 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
22 | 593 docinfo['imageURL'] = imageUrl |
594 | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
595 #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
|
596 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
|
597 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
22 | 598 return docinfo |
20 | 599 |
22 | 600 |
601 def getDocinfo(self, mode, url): | |
602 """returns docinfo depending on mode""" | |
52 | 603 logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
22 | 604 # look for cached docinfo in session |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
605 if self.REQUEST.SESSION.has_key('docinfo'): |
22 | 606 docinfo = self.REQUEST.SESSION['docinfo'] |
607 # check if its still current | |
608 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
52 | 609 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
22 | 610 return docinfo |
611 # new docinfo | |
612 docinfo = {'mode': mode, 'url': url} | |
613 if mode=="texttool": #index.meta with texttool information | |
614 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
615 elif mode=="imagepath": | |
616 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
70 | 617 elif mode=="filepath": |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
618 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
22 | 619 else: |
52 | 620 logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
621 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
37 | 622 |
52 | 623 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
22 | 624 self.REQUEST.SESSION['docinfo'] = docinfo |
625 return docinfo | |
20 | 626 |
627 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
628 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): |
22 | 629 """returns pageinfo with the given parameters""" |
630 pageinfo = {} | |
25 | 631 current = getInt(current) |
632 pageinfo['current'] = current | |
633 rows = int(rows or self.thumbrows) | |
634 pageinfo['rows'] = rows | |
635 cols = int(cols or self.thumbcols) | |
636 pageinfo['cols'] = cols | |
637 grpsize = cols * rows | |
638 pageinfo['groupsize'] = grpsize | |
61 | 639 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
640 # int(current / grpsize) * grpsize +1)) | |
22 | 641 pageinfo['start'] = start |
25 | 642 pageinfo['end'] = start + grpsize |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
643 if (docinfo is not None) and ('numPages' in docinfo): |
25 | 644 np = int(docinfo['numPages']) |
645 pageinfo['end'] = min(pageinfo['end'], np) | |
646 pageinfo['numgroups'] = int(np / grpsize) | |
647 if np % grpsize > 0: | |
648 pageinfo['numgroups'] += 1 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
649 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
650 pageinfo['viewMode'] = viewMode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
651 pageinfo['tocMode'] = tocMode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
652 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '10') |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
653 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
78 | 654 |
22 | 655 return pageinfo |
656 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
657 |
0 | 658 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
659 def getNumPages(self,docinfo=None): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
660 """get list of pages from fulltext and put in docinfo""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
661 xquery = '//pb' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
662 text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
663 # TODO: better processing of the page list. do we need the info somewhere else also? |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
664 docinfo['numPages'] = text.count("<pb ") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
665 return docinfo |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
666 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
667 def getTextPage(self, mode="text", pn=1, docinfo=None): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
668 """returns single page from fulltext""" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
669 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
670 if mode == "text_dict": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
671 textmode = "textPollux" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
672 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
673 textmode = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
674 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
675 pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
676 # post-processing downloaded xml |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
677 pagedom = Parse(pagexml) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
678 # plain text mode |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
679 if mode == "text": |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
680 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
681 pagedivs = pagedom.xpath("/div") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
682 if len(pagedivs) > 0: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
683 pagenode = pagedivs[0] |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
684 return serializeNode(pagenode) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
685 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
686 # text-with-links mode |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
687 if mode == "text_dict": |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
688 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
689 pagedivs = pagedom.xpath("/div") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
690 if len(pagedivs) > 0: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
691 pagenode = pagedivs[0] |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
692 # check all a-tags |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
693 links = pagenode.xpath("//a") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
694 for l in links: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
695 hrefNode = l.getAttributeNodeNS(None, u"href") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
696 if hrefNode: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
697 # is link with href |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
698 href = hrefNode.nodeValue |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
699 if href.startswith('lt/lex.xql'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
700 # is pollux link |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
701 selfurl = self.absolute_url() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
702 # change href |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
703 hrefNode.nodeValue = href.replace('lt/lex.xql','%s/head_main_voc'%selfurl) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
704 # add target |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
705 l.setAttributeNS(None, 'target', '_blank') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
706 return serializeNode(pagenode) |
0 | 707 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
708 return "no text here" |
22 | 709 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
710 def getToc(self, mode="text", docinfo=None): |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
711 """loads table of contents and stores in docinfo""" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
712 logging.debug("documentViewer (gettoc) mode: %s"%(mode)) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
713 if 'tocSize_%s'%mode in docinfo: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
714 # cached toc |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
715 return docinfo |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
716 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
717 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
718 # we need to set a result set size |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
719 pagesize = 1000 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
720 pn = 1 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
721 if mode == "text": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
722 queryType = "toc" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
723 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
724 queryType = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
725 # number of entries in toc |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
726 tocSize = 0 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
727 tocDiv = None |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
728 pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
729 # post-processing downloaded xml |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
730 pagedom = Parse(pagexml) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
731 # get number of entries |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
732 numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
733 if len(numdivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
734 tocSize = int(getTextFromNode(numdivs[0])) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
735 # div contains text |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
736 #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
737 #if len(pagedivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
738 # tocDiv = pagedivs[0] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
739 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
740 docinfo['tocSize_%s'%mode] = tocSize |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
741 #docinfo['tocDiv_%s'%mode] = tocDiv |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
742 return docinfo |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
743 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
744 def getTocPage(self, mode="toc", pn=1, pageinfo=None, docinfo=None): |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
745 """returns single page from the table of contents""" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
746 # TODO: this should use the cached TOC |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
747 if mode == "text": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
748 queryType = "toc" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
749 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
750 queryType = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
751 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
752 pagesize = pageinfo['tocPageSize'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
753 pn = pageinfo['tocPN'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
754 pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
755 # post-processing downloaded xml |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
756 pagedom = Parse(pagexml) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
757 # div contains text |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
758 pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
759 if len(pagedivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
760 pagenode = pagedivs[0] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
761 return serializeNode(pagenode) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
762 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
763 return "No TOC!" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
764 |
22 | 765 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
766 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): |
22 | 767 """init document viewer""" |
768 self.title=title | |
769 self.digilibBaseUrl = digilibBaseUrl | |
25 | 770 self.thumbrows = thumbrows |
771 self.thumbcols = thumbcols | |
32 | 772 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
22 | 773 if RESPONSE is not None: |
774 RESPONSE.redirect('manage_main') | |
0 | 775 |
776 | |
777 | |
778 def manage_AddDocumentViewerForm(self): | |
779 """add the viewer form""" | |
22 | 780 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 781 return pt() |
782 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
783 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 784 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
785 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 786 self._setObject(id,newObj) |
787 | |
788 if RESPONSE is not None: | |
789 RESPONSE.redirect('manage_main') | |
22 | 790 |
791 | |
792 ## | |
793 ## DocumentViewerTemplate class | |
794 ## | |
795 class DocumentViewerTemplate(ZopePageTemplate): | |
796 """Template for document viewer""" | |
797 meta_type="DocumentViewer Template" | |
798 | |
799 | |
800 def manage_addDocumentViewerTemplateForm(self): | |
801 """Form for adding""" | |
802 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
803 return pt() | |
804 | |
805 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
806 REQUEST=None, submit=None): | |
807 "Add a Page Template with optional file content." | |
808 | |
809 self._setObject(id, DocumentViewerTemplate(id)) | |
810 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
811 txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
812 logging.info("txt %s:"%txt) |
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
813 ob.pt_edit(txt,"text/html") |
22 | 814 if title: |
815 ob.pt_setTitle(title) | |
816 try: | |
817 u = self.DestinationURL() | |
818 except AttributeError: | |
819 u = REQUEST['URL1'] | |
820 | |
821 u = "%s/%s" % (u, urllib.quote(id)) | |
822 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
823 return '' | |
824 | |
825 | |
41 | 826 |