Mercurial > hg > documentViewer
annotate documentViewer.py @ 89:3d95ba1bf535
first version with new full-text infrastructure and slightly changed templates
author | casties |
---|---|
date | Fri, 19 Mar 2010 12:42:40 +0100 |
parents | a6e4f9b6729a |
children | 6a4a72033d58 |
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 thumbs_main = PageTemplateFile('zpt/thumbs_main', globals()) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
91 image_main = PageTemplateFile('zpt/image_main', globals()) # obsolete! |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
92 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
|
93 page_main_text = PageTemplateFile('zpt/page_main_text', globals()) |
22 | 94 head_main = PageTemplateFile('zpt/head_main', globals()) |
95 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
57 | 96 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
22 | 97 |
68 | 98 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
22 | 99 security.declareProtected('View management screens','changeDocumentViewerForm') |
100 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
101 | |
0 | 102 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
103 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): |
0 | 104 """init document viewer""" |
105 self.id=id | |
106 self.title=title | |
25 | 107 self.thumbcols = thumbcols |
108 self.thumbrows = thumbrows | |
32 | 109 # authgroups is list of authorized groups (delimited by ,) |
110 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
|
111 # 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
|
112 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
113 templateFolder = Folder('template') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
114 #self['template'] = templateFolder # Zope-2.12 style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
115 self._setObject('template',templateFolder) # old style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
116 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
117 from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
118 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
|
119 #templateFolder['fulltextclient'] = xmlRpcClient |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
120 templateFolder._setObject('fulltextclient',xmlRpcClient) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
121 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
122 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
|
123 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
124 from Products.zogiLib.zogiLib import zogiLib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
125 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
|
126 #templateFolder['zogilib'] = zogilib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
127 templateFolder._setObject('zogilib',zogilib) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
128 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
129 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
|
130 |
22 | 131 |
68 | 132 security.declareProtected('View','thumbs_rss') |
133 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
134 ''' | |
135 view it | |
136 @param mode: defines how to access the document behind url | |
137 @param url: url which contains display information | |
138 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
139 | |
140 ''' | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
141 logging.debug("HHHHHHHHHHHHHH:load the rss") |
68 | 142 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
143 | |
144 if not hasattr(self, 'template'): | |
145 # create template folder if it doesn't exist | |
146 self.manage_addFolder('template') | |
147 | |
148 if not self.digilibBaseUrl: | |
149 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
150 | |
151 docinfo = self.getDocinfo(mode=mode,url=url) | |
152 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
153 pt = getattr(self.template, 'thumbs_main_rss') | |
154 | |
155 if viewMode=="auto": # automodus gewaehlt | |
156 if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert | |
157 viewMode="text" | |
158 else: | |
159 viewMode="images" | |
160 | |
161 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
162 | |
22 | 163 security.declareProtected('View','index_html') |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
164 def index_html(self,url,mode="texttool",viewMode="auto",start=None,pn=1,mk=None): |
22 | 165 ''' |
166 view it | |
57 | 167 @param mode: defines how to access the document behind url |
22 | 168 @param url: url which contains display information |
57 | 169 @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
46 | 170 |
22 | 171 ''' |
0 | 172 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
173 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
22 | 174 |
175 if not hasattr(self, 'template'): | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
176 # this won't work |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
177 logging.error("template folder missing!") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
178 return "ERROR: template folder missing!" |
22 | 179 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
180 if not getattr(self, 'digilibBaseUrl', None): |
22 | 181 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
182 | |
25 | 183 docinfo = self.getDocinfo(mode=mode,url=url) |
184 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
22 | 185 pt = getattr(self.template, 'viewer_main') |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
186 |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
187 if viewMode=="auto": # automodus gewaehlt |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
188 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
|
189 viewMode="text" |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
190 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
191 viewMode="images" |
52 | 192 |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
193 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
0 | 194 |
74 | 195 def generateMarks(self,mk): |
196 ret="" | |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
197 if mk is None: |
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
198 return "" |
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
199 |
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
200 if type(mk) is not ListType: |
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
201 mk=[mk] |
74 | 202 for m in mk: |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
203 ret+="mk=%s"%m |
74 | 204 return ret |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
205 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
206 def findDigilibUrl(self): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
207 """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
|
208 url = self.template.zogilib.getDLBaseUrl() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
209 return url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
210 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
211 def getStyle(self, idx, selected, style=""): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
212 """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
|
213 #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
|
214 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
215 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
216 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
217 return style |
74 | 218 |
25 | 219 def getLink(self,param=None,val=None): |
220 """link to documentviewer with parameter param set to val""" | |
35 | 221 params=self.REQUEST.form.copy() |
25 | 222 if param is not None: |
31 | 223 if val is None: |
224 if params.has_key(param): | |
225 del params[param] | |
25 | 226 else: |
35 | 227 params[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
228 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
229 if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
78 | 230 params["mode"] = "imagepath" |
231 params["url"] = getParentDir(params["url"]) | |
31 | 232 |
35 | 233 # quote values and assemble into query string |
234 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
235 url=self.REQUEST['URL1']+"?"+ps | |
25 | 236 return url |
237 | |
68 | 238 def getLinkAmp(self,param=None,val=None): |
239 """link to documentviewer with parameter param set to val""" | |
240 params=self.REQUEST.form.copy() | |
241 if param is not None: | |
242 if val is None: | |
243 if params.has_key(param): | |
244 del params[param] | |
245 else: | |
246 params[param] = str(val) | |
247 | |
248 # quote values and assemble into query string | |
249 logging.info("XYXXXXX: %s"%repr(params.items())) | |
250 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
251 url=self.REQUEST['URL1']+"?"+ps | |
252 return url | |
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
253 |
57 | 254 def getInfo_xml(self,url,mode): |
255 """returns info about the document as XML""" | |
256 | |
257 if not self.digilibBaseUrl: | |
258 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
259 | |
260 docinfo = self.getDocinfo(mode=mode,url=url) | |
261 pt = getattr(self.template, 'info_xml') | |
262 return pt(docinfo=docinfo) | |
263 | |
0 | 264 |
35 | 265 def isAccessible(self, docinfo): |
32 | 266 """returns if access to the resource is granted""" |
267 access = docinfo.get('accessType', None) | |
52 | 268 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
45 | 269 if access is not None and access == 'free': |
52 | 270 logger("documentViewer (accessOK)", logging.INFO, "access is free") |
32 | 271 return True |
45 | 272 elif access is None or access in self.authgroups: |
35 | 273 # only local access -- only logged in users |
274 user = getSecurityManager().getUser() | |
275 if user is not None: | |
276 #print "user: ", user | |
277 return (user.getUserName() != "Anonymous User") | |
278 else: | |
279 return False | |
32 | 280 |
52 | 281 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
32 | 282 return False |
35 | 283 |
32 | 284 |
73 | 285 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
29 | 286 """gibt param von dlInfo aus""" |
40 | 287 num_retries = 3 |
31 | 288 if docinfo is None: |
289 docinfo = {} | |
73 | 290 |
291 for x in range(cut): | |
78 | 292 |
73 | 293 path=getParentDir(path) |
78 | 294 |
40 | 295 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 296 |
52 | 297 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
29 | 298 |
40 | 299 for cnt in range(num_retries): |
35 | 300 try: |
40 | 301 # dom = NonvalidatingReader.parseUri(imageUrl) |
302 txt=urllib.urlopen(infoUrl).read() | |
303 dom = Parse(txt) | |
35 | 304 break |
305 except: | |
52 | 306 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
35 | 307 else: |
40 | 308 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
29 | 309 |
37 | 310 sizes=dom.xpath("//dir/size") |
52 | 311 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
29 | 312 |
37 | 313 if sizes: |
314 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
31 | 315 else: |
316 docinfo['numPages'] = 0 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
317 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
318 # TODO: produce and keep list of image names and numbers |
31 | 319 |
320 return docinfo | |
32 | 321 |
29 | 322 |
35 | 323 def getIndexMeta(self, url): |
324 """returns dom of index.meta document at url""" | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
325 num_retries = 3 |
35 | 326 dom = None |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
327 metaUrl = None |
35 | 328 if url.startswith("http://"): |
329 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
330 metaUrl = url |
35 | 331 else: |
332 # online path | |
333 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 334 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 335 if not metaUrl.endswith("index.meta"): |
336 metaUrl += "/index.meta" | |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
337 logging.debug("METAURL: %s"%metaUrl) |
40 | 338 for cnt in range(num_retries): |
35 | 339 try: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
340 # patch dirk encoding fehler treten dann nicht mehr auf |
38 | 341 # dom = NonvalidatingReader.parseUri(metaUrl) |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
342 txt=urllib.urlopen(metaUrl).read() |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
343 dom = Parse(txt) |
40 | 344 break |
35 | 345 except: |
52 | 346 logger("ERROR documentViewer (getIndexMata)", 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
|
347 |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
348 if dom is None: |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
349 raise IOError("Unable to read index meta from %s"%(url)) |
35 | 350 |
351 return dom | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
352 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
353 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
354 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
355 num_retries = 3 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
356 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
357 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
358 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
359 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
360 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
361 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
362 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
363 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
364 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
365 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
366 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
367 for cnt in range(num_retries): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
368 try: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
369 # patch dirk encoding fehler treten dann nicht mehr auf |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
370 # dom = NonvalidatingReader.parseUri(metaUrl) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
371 txt=urllib.urlopen(metaUrl).read() |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
372 dom = Parse(txt) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
373 break |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
374 except: |
52 | 375 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
|
376 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
377 if dom is None: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
378 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
379 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
380 return dom |
35 | 381 |
382 | |
70 | 383 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 384 """gets authorization info from the index.meta file at path or given by dom""" |
52 | 385 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
32 | 386 |
387 access = None | |
388 | |
389 if docinfo is None: | |
390 docinfo = {} | |
391 | |
392 if dom is None: | |
78 | 393 for x in range(cut): |
70 | 394 path=getParentDir(path) |
395 dom = self.getIndexMeta(path) | |
46 | 396 |
32 | 397 acctype = dom.xpath("//access-conditions/access/@type") |
398 if acctype and (len(acctype)>0): | |
399 access=acctype[0].value | |
35 | 400 if access in ['group', 'institution']: |
32 | 401 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
402 | |
403 docinfo['accessType'] = access | |
404 return docinfo | |
29 | 405 |
32 | 406 |
70 | 407 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 408 """gets bibliographical info from the index.meta file at path or given by dom""" |
59 | 409 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 410 |
22 | 411 if docinfo is None: |
412 docinfo = {} | |
78 | 413 |
22 | 414 if dom is None: |
78 | 415 for x in range(cut): |
70 | 416 path=getParentDir(path) |
417 dom = self.getIndexMeta(path) | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
418 |
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
419 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
59 | 420 # put in all raw bib fields as dict "bib" |
421 bib = dom.xpath("//bib/*") | |
422 if bib and len(bib)>0: | |
423 bibinfo = {} | |
424 for e in bib: | |
425 bibinfo[e.localName] = getTextFromNode(e) | |
426 docinfo['bib'] = bibinfo | |
427 | |
428 # extract some fields (author, title, year) according to their mapping | |
25 | 429 metaData=self.metadata.main.meta.bib |
430 bibtype=dom.xpath("//bib/@type") | |
431 if bibtype and (len(bibtype)>0): | |
432 bibtype=bibtype[0].value | |
20 | 433 else: |
25 | 434 bibtype="generic" |
59 | 435 |
25 | 436 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
59 | 437 docinfo['bib_type'] = bibtype |
25 | 438 bibmap=metaData.generateMappingForType(bibtype) |
32 | 439 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
31 | 440 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
63 | 441 try: |
442 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
443 except: pass | |
444 try: | |
445 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
446 except: pass | |
447 try: | |
448 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
449 except: pass | |
59 | 450 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
52 | 451 try: |
452 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
453 except: | |
454 docinfo['lang']='' | |
59 | 455 |
22 | 456 return docinfo |
83 | 457 |
458 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
459 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
|
460 """parse texttool tag in index meta""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
461 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
|
462 if docinfo is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
463 docinfo = {} |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
464 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
465 if docinfo.get('lang', None) is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
466 docinfo['lang'] = '' # default keine Sprache gesetzt |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
467 if dom is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
468 dom = self.getIndexMeta(url) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
469 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
470 archivePath = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
471 archiveName = None |
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 archiveNames = dom.xpath("//resource/name") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
474 if archiveNames and (len(archiveNames) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
475 archiveName = getTextFromNode(archiveNames[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
476 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
477 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
|
478 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
479 archivePaths = dom.xpath("//resource/archive-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
480 if archivePaths and (len(archivePaths) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
481 archivePath = getTextFromNode(archivePaths[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
482 # clean up archive path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
483 if archivePath[0] != '/': |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
484 archivePath = '/' + archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
485 if archiveName and (not archivePath.endswith(archiveName)): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
486 archivePath += "/" + archiveName |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
487 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
488 # try to get archive-path from url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
489 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
|
490 if (not url.startswith('http')): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
491 archivePath = url.replace('index.meta', '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
492 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
493 if archivePath is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
494 # we balk without archive-path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
495 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
22 | 496 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
497 imageDirs = dom.xpath("//texttool/image") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
498 if imageDirs and (len(imageDirs) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
499 imageDir = getTextFromNode(imageDirs[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
500 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
501 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
502 # 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
|
503 #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
|
504 imageDir = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
505 #xquery="//pb" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
506 docinfo['imagePath'] = "" # keine Bilder |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
507 docinfo['imageURL'] = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
508 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
509 if imageDir and archivePath: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
510 #print "image: ", imageDir, " archivepath: ", archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
511 imageDir = os.path.join(archivePath, imageDir) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
512 imageDir = imageDir.replace("/mpiwg/online", '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
513 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
514 docinfo['imagePath'] = imageDir |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
515 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
516 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
|
517 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
518 viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
519 if viewerUrls and (len(viewerUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
520 viewerUrl = getTextFromNode(viewerUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
521 docinfo['viewerURL'] = viewerUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
522 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
523 textUrls = dom.xpath("//texttool/text") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
524 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
525 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
526 if urlparse.urlparse(textUrl)[0] == "": #keine url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
527 textUrl = os.path.join(archivePath, textUrl) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
528 # fix URLs starting with /mpiwg/online |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
529 if textUrl.startswith("/mpiwg/online"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
530 textUrl = textUrl.replace("/mpiwg/online", '', 1) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
531 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
532 docinfo['textURL'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
533 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
534 textUrls = dom.xpath("//texttool/text-url-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
535 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
536 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
537 docinfo['textURLPath'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
538 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
539 presentationUrls = dom.xpath("//texttool/presentation") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
540 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
|
541 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
542 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
|
543 # 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
|
544 # 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
|
545 presentationPath = getTextFromNode(presentationUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
546 if url.endswith("index.meta"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
547 presentationUrl = url.replace('index.meta', presentationPath) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
548 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
549 presentationUrl = url + "/" + presentationPath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
550 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
|
551 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
|
552 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
553 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
|
554 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
555 return docinfo |
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
556 |
52 | 557 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
558 |
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!") |
37 | 621 raise ValueError("Unknown mode %s"%(mode)) |
622 | |
52 | 623 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
22 | 624 self.REQUEST.SESSION['docinfo'] = docinfo |
625 return docinfo | |
20 | 626 |
627 | |
25 | 628 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=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 |
643 if docinfo is not None: | |
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 | |
78 | 649 |
22 | 650 return pageinfo |
651 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
652 |
0 | 653 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
654 def getNumPages(self,docinfo=None): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
655 """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
|
656 xquery = '//pb' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
657 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
|
658 # 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
|
659 docinfo['numPages'] = text.count("<pb ") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
660 return docinfo |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
661 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
662 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
|
663 """returns single page from fulltext""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
664 pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'],mode,pn), outputUnicode=False) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
665 # post-processing downloaded xml |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
666 pagedom = Parse(pagexml) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
667 # plain text mode |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
668 if mode == "text": |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
669 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
670 pagedivs = pagedom.xpath("/div") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
671 if len(pagedivs) > 0: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
672 pagenode = pagedivs[0] |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
673 return serializeNode(pagenode) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
674 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
675 # text-with-links mode |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
676 if mode == "textPollux": |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
677 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
678 pagedivs = pagedom.xpath("/div") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
679 if len(pagedivs) > 0: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
680 pagenode = pagedivs[0] |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
681 # check all a-tags |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
682 links = pagenode.xpath("//a") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
683 for l in links: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
684 hrefNode = l.getAttributeNodeNS(None, u"href") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
685 if hrefNode: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
686 # is link with href |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
687 href = hrefNode.nodeValue |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
688 if href.startswith('lt/lex.xql'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
689 # is pollux link |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
690 selfurl = self.absolute_url() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
691 # change href |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
692 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
|
693 # add target |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
694 l.setAttributeNS(None, 'target', '_blank') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
695 return serializeNode(pagenode) |
0 | 696 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
697 return "no text here" |
22 | 698 |
699 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
700 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): |
22 | 701 """init document viewer""" |
702 self.title=title | |
703 self.digilibBaseUrl = digilibBaseUrl | |
25 | 704 self.thumbrows = thumbrows |
705 self.thumbcols = thumbcols | |
32 | 706 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
22 | 707 if RESPONSE is not None: |
708 RESPONSE.redirect('manage_main') | |
0 | 709 |
710 | |
711 | |
712 def manage_AddDocumentViewerForm(self): | |
713 """add the viewer form""" | |
22 | 714 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 715 return pt() |
716 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
717 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 718 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
719 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 720 self._setObject(id,newObj) |
721 | |
722 if RESPONSE is not None: | |
723 RESPONSE.redirect('manage_main') | |
22 | 724 |
725 | |
726 ## | |
727 ## DocumentViewerTemplate class | |
728 ## | |
729 class DocumentViewerTemplate(ZopePageTemplate): | |
730 """Template for document viewer""" | |
731 meta_type="DocumentViewer Template" | |
732 | |
733 | |
734 def manage_addDocumentViewerTemplateForm(self): | |
735 """Form for adding""" | |
736 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
737 return pt() | |
738 | |
739 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
740 REQUEST=None, submit=None): | |
741 "Add a Page Template with optional file content." | |
742 | |
743 self._setObject(id, DocumentViewerTemplate(id)) | |
744 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
745 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
|
746 logging.info("txt %s:"%txt) |
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
747 ob.pt_edit(txt,"text/html") |
22 | 748 if title: |
749 ob.pt_setTitle(title) | |
750 try: | |
751 u = self.DestinationURL() | |
752 except AttributeError: | |
753 u = REQUEST['URL1'] | |
754 | |
755 u = "%s/%s" % (u, urllib.quote(id)) | |
756 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
757 return '' | |
758 | |
759 | |
41 | 760 |