Mercurial > hg > documentViewer
annotate documentViewer.py @ 95:db6d594aa4d9
Last update with search function (getSearch)
author | abukhman |
---|---|
date | Mon, 19 Apr 2010 15:13:13 +0200 |
parents | 6a4a72033d58 |
children | a679c8c7148d |
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 |
95 | 105 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,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') |
95 | 166 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=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) |
95 | 172 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, search) |
173 @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph) | |
22 | 174 ''' |
0 | 175 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
176 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
22 | 177 |
178 if not hasattr(self, 'template'): | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
179 # this won't work |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
180 logging.error("template folder missing!") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
181 return "ERROR: template folder missing!" |
22 | 182 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
183 if not getattr(self, 'digilibBaseUrl', None): |
22 | 184 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
185 | |
25 | 186 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
|
187 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
|
188 if tocMode != "thumbs": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
189 # get table of contents |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
190 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
|
191 |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
192 if viewMode=="auto": # automodus gewaehlt |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
193 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
|
194 viewMode="text" |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
195 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
196 viewMode="images" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
197 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
198 pt = getattr(self.template, 'viewer_main') |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
199 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
0 | 200 |
74 | 201 def generateMarks(self,mk): |
202 ret="" | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
203 if mk is None: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
204 return "" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
205 if type(mk) is not ListType: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
206 mk=[mk] |
74 | 207 for m in mk: |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
208 ret+="mk=%s"%m |
74 | 209 return ret |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
210 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
211 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
212 def findDigilibUrl(self): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
213 """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
|
214 url = self.template.zogilib.getDLBaseUrl() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
215 return url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
216 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
217 def getStyle(self, idx, selected, style=""): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
218 """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
|
219 #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
|
220 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
221 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
222 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
223 return style |
74 | 224 |
25 | 225 def getLink(self,param=None,val=None): |
226 """link to documentviewer with parameter param set to val""" | |
35 | 227 params=self.REQUEST.form.copy() |
25 | 228 if param is not None: |
31 | 229 if val is None: |
230 if params.has_key(param): | |
231 del params[param] | |
25 | 232 else: |
35 | 233 params[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
234 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
235 if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
78 | 236 params["mode"] = "imagepath" |
237 params["url"] = getParentDir(params["url"]) | |
31 | 238 |
35 | 239 # quote values and assemble into query string |
240 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
241 url=self.REQUEST['URL1']+"?"+ps | |
25 | 242 return url |
243 | |
68 | 244 def getLinkAmp(self,param=None,val=None): |
245 """link to documentviewer with parameter param set to val""" | |
246 params=self.REQUEST.form.copy() | |
247 if param is not None: | |
248 if val is None: | |
249 if params.has_key(param): | |
250 del params[param] | |
251 else: | |
252 params[param] = str(val) | |
253 | |
254 # quote values and assemble into query string | |
255 logging.info("XYXXXXX: %s"%repr(params.items())) | |
256 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
257 url=self.REQUEST['URL1']+"?"+ps | |
258 return url | |
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
259 |
57 | 260 def getInfo_xml(self,url,mode): |
261 """returns info about the document as XML""" | |
262 | |
263 if not self.digilibBaseUrl: | |
264 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
265 | |
266 docinfo = self.getDocinfo(mode=mode,url=url) | |
267 pt = getattr(self.template, 'info_xml') | |
268 return pt(docinfo=docinfo) | |
269 | |
0 | 270 |
35 | 271 def isAccessible(self, docinfo): |
32 | 272 """returns if access to the resource is granted""" |
273 access = docinfo.get('accessType', None) | |
52 | 274 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
45 | 275 if access is not None and access == 'free': |
52 | 276 logger("documentViewer (accessOK)", logging.INFO, "access is free") |
32 | 277 return True |
45 | 278 elif access is None or access in self.authgroups: |
35 | 279 # only local access -- only logged in users |
280 user = getSecurityManager().getUser() | |
281 if user is not None: | |
282 #print "user: ", user | |
283 return (user.getUserName() != "Anonymous User") | |
284 else: | |
285 return False | |
32 | 286 |
52 | 287 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
32 | 288 return False |
35 | 289 |
32 | 290 |
73 | 291 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
29 | 292 """gibt param von dlInfo aus""" |
40 | 293 num_retries = 3 |
31 | 294 if docinfo is None: |
295 docinfo = {} | |
73 | 296 |
297 for x in range(cut): | |
78 | 298 |
73 | 299 path=getParentDir(path) |
78 | 300 |
40 | 301 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 302 |
52 | 303 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
29 | 304 |
40 | 305 for cnt in range(num_retries): |
35 | 306 try: |
40 | 307 # dom = NonvalidatingReader.parseUri(imageUrl) |
308 txt=urllib.urlopen(infoUrl).read() | |
309 dom = Parse(txt) | |
35 | 310 break |
311 except: | |
52 | 312 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
35 | 313 else: |
40 | 314 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
29 | 315 |
37 | 316 sizes=dom.xpath("//dir/size") |
52 | 317 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
29 | 318 |
37 | 319 if sizes: |
320 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
31 | 321 else: |
322 docinfo['numPages'] = 0 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
323 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
324 # TODO: produce and keep list of image names and numbers |
31 | 325 |
326 return docinfo | |
32 | 327 |
29 | 328 |
35 | 329 def getIndexMeta(self, url): |
330 """returns dom of index.meta document at url""" | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
331 num_retries = 3 |
35 | 332 dom = None |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
333 metaUrl = None |
35 | 334 if url.startswith("http://"): |
335 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
336 metaUrl = url |
35 | 337 else: |
338 # online path | |
339 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 340 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 341 if not metaUrl.endswith("index.meta"): |
342 metaUrl += "/index.meta" | |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
343 logging.debug("METAURL: %s"%metaUrl) |
40 | 344 for cnt in range(num_retries): |
35 | 345 try: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
346 # patch dirk encoding fehler treten dann nicht mehr auf |
38 | 347 # dom = NonvalidatingReader.parseUri(metaUrl) |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
348 txt=urllib.urlopen(metaUrl).read() |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
349 dom = Parse(txt) |
40 | 350 break |
35 | 351 except: |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
352 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
|
353 |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
354 if dom is None: |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
355 raise IOError("Unable to read index meta from %s"%(url)) |
35 | 356 |
357 return dom | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
358 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
359 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
360 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
361 num_retries = 3 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
362 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
363 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
364 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
365 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
366 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
367 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
368 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
369 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
370 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
371 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
372 for cnt in range(num_retries): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
373 try: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
374 # patch dirk encoding fehler treten dann nicht mehr auf |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
375 # dom = NonvalidatingReader.parseUri(metaUrl) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
376 txt=urllib.urlopen(metaUrl).read() |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
377 dom = Parse(txt) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
378 break |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
379 except: |
52 | 380 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
|
381 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
382 if dom is None: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
383 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
384 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
385 return dom |
35 | 386 |
387 | |
70 | 388 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 389 """gets authorization info from the index.meta file at path or given by dom""" |
52 | 390 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
32 | 391 |
392 access = None | |
393 | |
394 if docinfo is None: | |
395 docinfo = {} | |
396 | |
397 if dom is None: | |
78 | 398 for x in range(cut): |
70 | 399 path=getParentDir(path) |
400 dom = self.getIndexMeta(path) | |
46 | 401 |
32 | 402 acctype = dom.xpath("//access-conditions/access/@type") |
403 if acctype and (len(acctype)>0): | |
404 access=acctype[0].value | |
35 | 405 if access in ['group', 'institution']: |
32 | 406 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
407 | |
408 docinfo['accessType'] = access | |
409 return docinfo | |
29 | 410 |
32 | 411 |
70 | 412 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 413 """gets bibliographical info from the index.meta file at path or given by dom""" |
59 | 414 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 415 |
22 | 416 if docinfo is None: |
417 docinfo = {} | |
78 | 418 |
22 | 419 if dom is None: |
78 | 420 for x in range(cut): |
70 | 421 path=getParentDir(path) |
422 dom = self.getIndexMeta(path) | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
423 |
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
424 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
59 | 425 # put in all raw bib fields as dict "bib" |
426 bib = dom.xpath("//bib/*") | |
427 if bib and len(bib)>0: | |
428 bibinfo = {} | |
429 for e in bib: | |
430 bibinfo[e.localName] = getTextFromNode(e) | |
431 docinfo['bib'] = bibinfo | |
432 | |
433 # extract some fields (author, title, year) according to their mapping | |
25 | 434 metaData=self.metadata.main.meta.bib |
435 bibtype=dom.xpath("//bib/@type") | |
436 if bibtype and (len(bibtype)>0): | |
437 bibtype=bibtype[0].value | |
20 | 438 else: |
25 | 439 bibtype="generic" |
59 | 440 |
25 | 441 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
59 | 442 docinfo['bib_type'] = bibtype |
25 | 443 bibmap=metaData.generateMappingForType(bibtype) |
32 | 444 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
31 | 445 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
63 | 446 try: |
447 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
448 except: pass | |
449 try: | |
450 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
451 except: pass | |
452 try: | |
453 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
454 except: pass | |
59 | 455 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
52 | 456 try: |
457 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
458 except: | |
459 docinfo['lang']='' | |
59 | 460 |
22 | 461 return docinfo |
83 | 462 |
463 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
464 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
|
465 """parse texttool tag in index meta""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
466 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
|
467 if docinfo is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
468 docinfo = {} |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
469 if docinfo.get('lang', None) is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
470 docinfo['lang'] = '' # default keine Sprache gesetzt |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
471 if dom is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
472 dom = self.getIndexMeta(url) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
473 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
474 archivePath = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
475 archiveName = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
476 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
477 archiveNames = dom.xpath("//resource/name") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
478 if archiveNames and (len(archiveNames) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
479 archiveName = getTextFromNode(archiveNames[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
480 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
481 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
|
482 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
483 archivePaths = dom.xpath("//resource/archive-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
484 if archivePaths and (len(archivePaths) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
485 archivePath = getTextFromNode(archivePaths[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
486 # clean up archive path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
487 if archivePath[0] != '/': |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
488 archivePath = '/' + archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
489 if archiveName and (not archivePath.endswith(archiveName)): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
490 archivePath += "/" + archiveName |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
491 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
492 # try to get archive-path from url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
493 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
|
494 if (not url.startswith('http')): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
495 archivePath = url.replace('index.meta', '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
496 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
497 if archivePath is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
498 # we balk without archive-path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
499 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
22 | 500 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
501 imageDirs = dom.xpath("//texttool/image") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
502 if imageDirs and (len(imageDirs) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
503 imageDir = getTextFromNode(imageDirs[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
504 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
505 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
506 # 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
|
507 #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
|
508 imageDir = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
509 #xquery="//pb" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
510 docinfo['imagePath'] = "" # keine Bilder |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
511 docinfo['imageURL'] = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
512 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
513 if imageDir and archivePath: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
514 #print "image: ", imageDir, " archivepath: ", archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
515 imageDir = os.path.join(archivePath, imageDir) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
516 imageDir = imageDir.replace("/mpiwg/online", '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
517 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
518 docinfo['imagePath'] = imageDir |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
519 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
520 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
|
521 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
522 viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
523 if viewerUrls and (len(viewerUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
524 viewerUrl = getTextFromNode(viewerUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
525 docinfo['viewerURL'] = viewerUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
526 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
527 textUrls = dom.xpath("//texttool/text") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
528 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
529 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
530 if urlparse.urlparse(textUrl)[0] == "": #keine url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
531 textUrl = os.path.join(archivePath, textUrl) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
532 # fix URLs starting with /mpiwg/online |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
533 if textUrl.startswith("/mpiwg/online"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
534 textUrl = textUrl.replace("/mpiwg/online", '', 1) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
535 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
536 docinfo['textURL'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
537 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
538 textUrls = dom.xpath("//texttool/text-url-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
539 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
540 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
541 docinfo['textURLPath'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
542 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
543 presentationUrls = dom.xpath("//texttool/presentation") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
544 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
|
545 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
546 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
|
547 # 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
|
548 # 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
|
549 presentationPath = getTextFromNode(presentationUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
550 if url.endswith("index.meta"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
551 presentationUrl = url.replace('index.meta', presentationPath) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
552 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
553 presentationUrl = url + "/" + presentationPath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
554 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
|
555 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
|
556 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
557 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
|
558 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
559 return docinfo |
22 | 560 |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
561 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
562 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
563 """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
|
564 """ |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
565 dom=self.getPresentationInfoXML(url) |
62 | 566 try: |
567 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
568 except: | |
569 pass | |
570 try: | |
571 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
572 except: | |
573 pass | |
574 try: | |
575 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
576 except: | |
577 pass | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
578 return docinfo |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
579 |
70 | 580 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
22 | 581 """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
52 | 582 logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
22 | 583 if docinfo is None: |
584 docinfo = {} | |
29 | 585 path=path.replace("/mpiwg/online","") |
22 | 586 docinfo['imagePath'] = path |
73 | 587 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
78 | 588 |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
589 pathorig=path |
78 | 590 for x in range(cut): |
591 path=getParentDir(path) | |
592 logging.error("PATH:"+path) | |
31 | 593 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
22 | 594 docinfo['imageURL'] = imageUrl |
595 | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
596 #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
|
597 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
|
598 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
22 | 599 return docinfo |
20 | 600 |
22 | 601 |
602 def getDocinfo(self, mode, url): | |
603 """returns docinfo depending on mode""" | |
52 | 604 logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
22 | 605 # look for cached docinfo in session |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
606 if self.REQUEST.SESSION.has_key('docinfo'): |
22 | 607 docinfo = self.REQUEST.SESSION['docinfo'] |
608 # check if its still current | |
609 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
52 | 610 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
22 | 611 return docinfo |
612 # new docinfo | |
613 docinfo = {'mode': mode, 'url': url} | |
614 if mode=="texttool": #index.meta with texttool information | |
615 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
616 elif mode=="imagepath": | |
617 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
70 | 618 elif mode=="filepath": |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
619 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
22 | 620 else: |
52 | 621 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
|
622 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
37 | 623 |
52 | 624 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
22 | 625 self.REQUEST.SESSION['docinfo'] = docinfo |
626 return docinfo | |
20 | 627 |
628 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
629 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): |
22 | 630 """returns pageinfo with the given parameters""" |
631 pageinfo = {} | |
25 | 632 current = getInt(current) |
633 pageinfo['current'] = current | |
634 rows = int(rows or self.thumbrows) | |
635 pageinfo['rows'] = rows | |
636 cols = int(cols or self.thumbcols) | |
637 pageinfo['cols'] = cols | |
638 grpsize = cols * rows | |
639 pageinfo['groupsize'] = grpsize | |
61 | 640 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
641 # int(current / grpsize) * grpsize +1)) | |
22 | 642 pageinfo['start'] = start |
25 | 643 pageinfo['end'] = start + grpsize |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
644 if (docinfo is not None) and ('numPages' in docinfo): |
25 | 645 np = int(docinfo['numPages']) |
646 pageinfo['end'] = min(pageinfo['end'], np) | |
647 pageinfo['numgroups'] = int(np / grpsize) | |
648 if np % grpsize > 0: | |
649 pageinfo['numgroups'] += 1 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
650 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
651 pageinfo['viewMode'] = viewMode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
652 pageinfo['tocMode'] = tocMode |
95 | 653 pageinfo['query'] = self.REQUEST.get('query',' ') |
654 pageinfo['queryType'] = self.REQUEST.get('queryType',' ') | |
655 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') | |
656 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') | |
657 pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '20') | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
658 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
95 | 659 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
660 pageinfo['sn'] =self.REQUEST.get('sn','1') | |
78 | 661 |
22 | 662 return pageinfo |
663 | |
95 | 664 def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None): |
665 """get search list""" | |
666 docpath = docinfo['textURLPath'] | |
667 pagesize = pageinfo['queryPageSize'] | |
668 pn = pageinfo['searchPN'] | |
669 sn = pageinfo['sn'] | |
670 query =pageinfo['query'] | |
671 queryType =pageinfo['queryType'] | |
672 | |
673 pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn) ,outputUnicode=False) | |
674 pagedom = Parse(pagexml) | |
675 #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") | |
676 | |
677 return pagexml | |
678 #if len(pagedivs) > 0: | |
679 # pagenode = pagedom[0] | |
680 # return serializeNode(pagenode) | |
681 #else: | |
682 # return "xaxa" | |
0 | 683 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
684 def getNumPages(self,docinfo=None): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
685 """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
|
686 xquery = '//pb' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
687 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
|
688 # 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
|
689 docinfo['numPages'] = text.count("<pb ") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
690 return docinfo |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
691 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
692 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
|
693 """returns single page from fulltext""" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
694 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
695 if mode == "text_dict": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
696 textmode = "textPollux" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
697 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
698 textmode = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
699 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
700 pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False) |
95 | 701 ####### |
702 #textpython = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','?url=/mpiwg/online/permanent/library/163127KK&tocMode='+str(tocMode)+'&queryResultPN='+str(queryResultPN)+'&viewMode='+str(viewMode)) | |
703 #textnew =textpython.replace('mode=text','mode=texttool') | |
704 ####### | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
705 # post-processing downloaded xml |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
706 pagedom = Parse(pagexml) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
707 # plain text mode |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
708 if mode == "text": |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
709 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
710 pagedivs = pagedom.xpath("/div") |
95 | 711 #queryResultPage |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
712 if len(pagedivs) > 0: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
713 pagenode = pagedivs[0] |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
714 return serializeNode(pagenode) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
715 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
716 # text-with-links mode |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
717 if mode == "text_dict": |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
718 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
719 pagedivs = pagedom.xpath("/div") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
720 if len(pagedivs) > 0: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
721 pagenode = pagedivs[0] |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
722 # check all a-tags |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
723 links = pagenode.xpath("//a") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
724 for l in links: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
725 hrefNode = l.getAttributeNodeNS(None, u"href") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
726 if hrefNode: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
727 # is link with href |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
728 href = hrefNode.nodeValue |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
729 if href.startswith('lt/lex.xql'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
730 # is pollux link |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
731 selfurl = self.absolute_url() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
732 # change href |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
733 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
|
734 # add target |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
735 l.setAttributeNS(None, 'target', '_blank') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
736 return serializeNode(pagenode) |
0 | 737 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
738 return "no text here" |
22 | 739 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
740 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
|
741 """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
|
742 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
|
743 if 'tocSize_%s'%mode in docinfo: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
744 # cached toc |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
745 return docinfo |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
746 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
747 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
748 # 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
|
749 pagesize = 1000 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
750 pn = 1 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
751 if mode == "text": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
752 queryType = "toc" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
753 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
754 queryType = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
755 # number of entries in toc |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
756 tocSize = 0 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
757 tocDiv = None |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
758 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
|
759 # post-processing downloaded xml |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
760 pagedom = Parse(pagexml) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
761 # get number of entries |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
762 numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
763 if len(numdivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
764 tocSize = int(getTextFromNode(numdivs[0])) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
765 # div contains text |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
766 #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
767 #if len(pagedivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
768 # tocDiv = pagedivs[0] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
769 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
770 docinfo['tocSize_%s'%mode] = tocSize |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
771 #docinfo['tocDiv_%s'%mode] = tocDiv |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
772 return docinfo |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
773 |
95 | 774 def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None): |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
775 """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
|
776 # 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
|
777 if mode == "text": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
778 queryType = "toc" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
779 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
780 queryType = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
781 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
782 pagesize = pageinfo['tocPageSize'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
783 pn = pageinfo['tocPN'] |
95 | 784 pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False) |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
785 # post-processing downloaded xml |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
786 pagedom = Parse(pagexml) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
787 # div contains text |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
788 pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
789 if len(pagedivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
790 pagenode = pagedivs[0] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
791 return serializeNode(pagenode) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
792 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
793 return "No TOC!" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
794 |
22 | 795 |
95 | 796 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
22 | 797 """init document viewer""" |
798 self.title=title | |
799 self.digilibBaseUrl = digilibBaseUrl | |
25 | 800 self.thumbrows = thumbrows |
801 self.thumbcols = thumbcols | |
32 | 802 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
22 | 803 if RESPONSE is not None: |
804 RESPONSE.redirect('manage_main') | |
0 | 805 |
806 | |
807 | |
808 def manage_AddDocumentViewerForm(self): | |
809 """add the viewer form""" | |
22 | 810 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 811 return pt() |
812 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
813 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 814 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
815 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 816 self._setObject(id,newObj) |
817 | |
818 if RESPONSE is not None: | |
819 RESPONSE.redirect('manage_main') | |
22 | 820 |
821 | |
822 ## | |
823 ## DocumentViewerTemplate class | |
824 ## | |
825 class DocumentViewerTemplate(ZopePageTemplate): | |
826 """Template for document viewer""" | |
827 meta_type="DocumentViewer Template" | |
828 | |
829 | |
830 def manage_addDocumentViewerTemplateForm(self): | |
831 """Form for adding""" | |
832 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
833 return pt() | |
834 | |
835 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
836 REQUEST=None, submit=None): | |
837 "Add a Page Template with optional file content." | |
838 | |
839 self._setObject(id, DocumentViewerTemplate(id)) | |
840 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
841 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
|
842 logging.info("txt %s:"%txt) |
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
843 ob.pt_edit(txt,"text/html") |
22 | 844 if title: |
845 ob.pt_setTitle(title) | |
846 try: | |
847 u = self.DestinationURL() | |
848 except AttributeError: | |
849 u = REQUEST['URL1'] | |
850 | |
851 u = "%s/%s" % (u, urllib.quote(id)) | |
852 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
853 return '' | |
854 | |
855 | |
41 | 856 |