Mercurial > hg > documentViewer
annotate documentViewer.py @ 99:4738a696d265
Search function update
author | abukhman |
---|---|
date | Fri, 30 Apr 2010 16:36:00 +0200 |
parents | 2b8fd19432fb |
children | 137459e3b378 |
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 |
97 | 13 from xml.dom.minidom import parse, parseString |
14 | |
15 | |
83 | 16 |
0 | 17 import Ft.Xml.XPath |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
18 import cStringIO |
83 | 19 import xmlrpclib |
0 | 20 import os.path |
31 | 21 import sys |
0 | 22 import cgi |
23 import urllib | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
24 import logging |
61 | 25 import math |
52 | 26 |
46 | 27 import urlparse |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
28 from types import * |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
29 |
52 | 30 def logger(txt,method,txt2): |
31 """logging""" | |
32 logging.info(txt+ txt2) | |
33 | |
34 | |
25 | 35 def getInt(number, default=0): |
36 """returns always an int (0 in case of problems)""" | |
37 try: | |
38 return int(number) | |
39 except: | |
62 | 40 return int(default) |
25 | 41 |
0 | 42 def getTextFromNode(nodename): |
46 | 43 """get the cdata content of a node""" |
32 | 44 if nodename is None: |
45 return "" | |
0 | 46 nodelist=nodename.childNodes |
47 rc = "" | |
48 for node in nodelist: | |
49 if node.nodeType == node.TEXT_NODE: | |
50 rc = rc + node.data | |
51 return rc | |
52 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
53 def serializeNode(node, encoding='utf-8'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
54 """returns a string containing node as XML""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
55 buf = cStringIO.StringIO() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
56 Print(node, stream=buf, encoding=encoding) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
57 s = buf.getvalue() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
58 buf.close() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
59 return s |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
60 |
35 | 61 |
62 def getParentDir(path): | |
63 """returns pathname shortened by one""" | |
64 return '/'.join(path.split('/')[0:-1]) | |
65 | |
66 | |
0 | 67 import socket |
68 | |
32 | 69 def urlopen(url,timeout=2): |
0 | 70 """urlopen mit timeout""" |
32 | 71 socket.setdefaulttimeout(timeout) |
0 | 72 ret=urllib.urlopen(url) |
73 socket.setdefaulttimeout(5) | |
74 return ret | |
75 | |
76 | |
22 | 77 ## |
78 ## documentViewer class | |
79 ## | |
80 class documentViewer(Folder): | |
0 | 81 """document viewer""" |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
82 #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" |
46 | 83 |
0 | 84 meta_type="Document viewer" |
85 | |
86 security=ClassSecurityInfo() | |
22 | 87 manage_options=Folder.manage_options+( |
0 | 88 {'label':'main config','action':'changeDocumentViewerForm'}, |
89 ) | |
90 | |
22 | 91 # templates and forms |
92 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
|
93 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
|
94 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
|
95 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
|
96 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
|
97 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
|
98 page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
99 | 99 page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) |
22 | 100 head_main = PageTemplateFile('zpt/head_main', globals()) |
101 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
57 | 102 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
22 | 103 |
68 | 104 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
22 | 105 security.declareProtected('View management screens','changeDocumentViewerForm') |
106 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
107 | |
0 | 108 |
95 | 109 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
0 | 110 """init document viewer""" |
111 self.id=id | |
112 self.title=title | |
25 | 113 self.thumbcols = thumbcols |
114 self.thumbrows = thumbrows | |
32 | 115 # authgroups is list of authorized groups (delimited by ,) |
116 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
|
117 # 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
|
118 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
119 templateFolder = Folder('template') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
120 #self['template'] = templateFolder # Zope-2.12 style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
121 self._setObject('template',templateFolder) # old style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
122 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
123 from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
124 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
|
125 #templateFolder['fulltextclient'] = xmlRpcClient |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
126 templateFolder._setObject('fulltextclient',xmlRpcClient) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
127 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
128 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
|
129 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
130 from Products.zogiLib.zogiLib import zogiLib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
131 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
|
132 #templateFolder['zogilib'] = zogilib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
133 templateFolder._setObject('zogilib',zogilib) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
134 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
135 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
|
136 |
22 | 137 |
68 | 138 security.declareProtected('View','thumbs_rss') |
139 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
140 ''' | |
141 view it | |
142 @param mode: defines how to access the document behind url | |
143 @param url: url which contains display information | |
144 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
145 | |
146 ''' | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
147 logging.debug("HHHHHHHHHHHHHH:load the rss") |
68 | 148 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
149 | |
150 if not hasattr(self, 'template'): | |
151 # create template folder if it doesn't exist | |
152 self.manage_addFolder('template') | |
153 | |
154 if not self.digilibBaseUrl: | |
155 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
156 | |
157 docinfo = self.getDocinfo(mode=mode,url=url) | |
158 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
159 pt = getattr(self.template, 'thumbs_main_rss') | |
160 | |
161 if viewMode=="auto": # automodus gewaehlt | |
162 if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert | |
163 viewMode="text" | |
164 else: | |
165 viewMode="images" | |
166 | |
167 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
168 | |
22 | 169 security.declareProtected('View','index_html') |
95 | 170 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None): |
22 | 171 ''' |
172 view it | |
57 | 173 @param mode: defines how to access the document behind url |
22 | 174 @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
|
175 @param viewMode: if images display images, if text display text, default is auto (text,images or auto) |
99 | 176 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
95 | 177 @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph) |
22 | 178 ''' |
0 | 179 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
180 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
22 | 181 |
182 if not hasattr(self, 'template'): | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
183 # this won't work |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
184 logging.error("template folder missing!") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
185 return "ERROR: template folder missing!" |
22 | 186 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
187 if not getattr(self, 'digilibBaseUrl', None): |
22 | 188 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
189 | |
25 | 190 docinfo = self.getDocinfo(mode=mode,url=url) |
97 | 191 |
192 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
193 if tocMode != "thumbs": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
194 # get table of contents |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
195 docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
97 | 196 |
197 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) | |
198 | |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
199 if viewMode=="auto": # automodus gewaehlt |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
200 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
|
201 viewMode="text" |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
202 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
203 viewMode="images" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
204 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
205 pt = getattr(self.template, 'viewer_main') |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
206 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
0 | 207 |
74 | 208 def generateMarks(self,mk): |
209 ret="" | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
210 if mk is None: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
211 return "" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
212 if type(mk) is not ListType: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
213 mk=[mk] |
74 | 214 for m in mk: |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
215 ret+="mk=%s"%m |
74 | 216 return ret |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
217 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
218 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
219 def findDigilibUrl(self): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
220 """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
|
221 url = self.template.zogilib.getDLBaseUrl() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
222 return url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
223 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
224 def getStyle(self, idx, selected, style=""): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
225 """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
|
226 #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
|
227 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
228 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
229 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
230 return style |
74 | 231 |
25 | 232 def getLink(self,param=None,val=None): |
233 """link to documentviewer with parameter param set to val""" | |
35 | 234 params=self.REQUEST.form.copy() |
25 | 235 if param is not None: |
31 | 236 if val is None: |
237 if params.has_key(param): | |
238 del params[param] | |
25 | 239 else: |
35 | 240 params[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
241 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
242 if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
78 | 243 params["mode"] = "imagepath" |
244 params["url"] = getParentDir(params["url"]) | |
31 | 245 |
35 | 246 # quote values and assemble into query string |
247 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
248 url=self.REQUEST['URL1']+"?"+ps | |
25 | 249 return url |
250 | |
68 | 251 def getLinkAmp(self,param=None,val=None): |
252 """link to documentviewer with parameter param set to val""" | |
253 params=self.REQUEST.form.copy() | |
254 if param is not None: | |
255 if val is None: | |
256 if params.has_key(param): | |
257 del params[param] | |
258 else: | |
259 params[param] = str(val) | |
260 | |
261 # quote values and assemble into query string | |
262 logging.info("XYXXXXX: %s"%repr(params.items())) | |
263 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
264 url=self.REQUEST['URL1']+"?"+ps | |
265 return url | |
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
266 |
57 | 267 def getInfo_xml(self,url,mode): |
268 """returns info about the document as XML""" | |
269 | |
270 if not self.digilibBaseUrl: | |
271 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
272 | |
273 docinfo = self.getDocinfo(mode=mode,url=url) | |
274 pt = getattr(self.template, 'info_xml') | |
275 return pt(docinfo=docinfo) | |
276 | |
0 | 277 |
35 | 278 def isAccessible(self, docinfo): |
32 | 279 """returns if access to the resource is granted""" |
280 access = docinfo.get('accessType', None) | |
52 | 281 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
45 | 282 if access is not None and access == 'free': |
52 | 283 logger("documentViewer (accessOK)", logging.INFO, "access is free") |
32 | 284 return True |
45 | 285 elif access is None or access in self.authgroups: |
35 | 286 # only local access -- only logged in users |
287 user = getSecurityManager().getUser() | |
288 if user is not None: | |
289 #print "user: ", user | |
290 return (user.getUserName() != "Anonymous User") | |
291 else: | |
292 return False | |
32 | 293 |
52 | 294 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
32 | 295 return False |
35 | 296 |
32 | 297 |
73 | 298 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
29 | 299 """gibt param von dlInfo aus""" |
40 | 300 num_retries = 3 |
31 | 301 if docinfo is None: |
302 docinfo = {} | |
73 | 303 |
304 for x in range(cut): | |
78 | 305 |
73 | 306 path=getParentDir(path) |
78 | 307 |
40 | 308 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 309 |
52 | 310 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
29 | 311 |
40 | 312 for cnt in range(num_retries): |
35 | 313 try: |
40 | 314 # dom = NonvalidatingReader.parseUri(imageUrl) |
315 txt=urllib.urlopen(infoUrl).read() | |
316 dom = Parse(txt) | |
35 | 317 break |
318 except: | |
52 | 319 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
35 | 320 else: |
40 | 321 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
29 | 322 |
37 | 323 sizes=dom.xpath("//dir/size") |
52 | 324 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
29 | 325 |
37 | 326 if sizes: |
327 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
31 | 328 else: |
329 docinfo['numPages'] = 0 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
330 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
331 # TODO: produce and keep list of image names and numbers |
31 | 332 |
333 return docinfo | |
32 | 334 |
29 | 335 |
35 | 336 def getIndexMeta(self, url): |
337 """returns dom of index.meta document at url""" | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
338 num_retries = 3 |
35 | 339 dom = None |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
340 metaUrl = None |
35 | 341 if url.startswith("http://"): |
342 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
343 metaUrl = url |
35 | 344 else: |
345 # online path | |
346 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 347 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 348 if not metaUrl.endswith("index.meta"): |
349 metaUrl += "/index.meta" | |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
350 logging.debug("METAURL: %s"%metaUrl) |
40 | 351 for cnt in range(num_retries): |
35 | 352 try: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
353 # patch dirk encoding fehler treten dann nicht mehr auf |
38 | 354 # dom = NonvalidatingReader.parseUri(metaUrl) |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
355 txt=urllib.urlopen(metaUrl).read() |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
356 dom = Parse(txt) |
40 | 357 break |
35 | 358 except: |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
359 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
|
360 |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
361 if dom is None: |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
362 raise IOError("Unable to read index meta from %s"%(url)) |
35 | 363 |
364 return dom | |
50
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 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
367 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
368 num_retries = 3 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
369 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
370 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
371 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
372 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
373 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
374 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
375 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
376 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
377 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
378 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
379 for cnt in range(num_retries): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
380 try: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
381 # patch dirk encoding fehler treten dann nicht mehr auf |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
382 # dom = NonvalidatingReader.parseUri(metaUrl) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
383 txt=urllib.urlopen(metaUrl).read() |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
384 dom = Parse(txt) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
385 break |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
386 except: |
52 | 387 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
|
388 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
389 if dom is None: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
390 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
391 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
392 return dom |
35 | 393 |
394 | |
70 | 395 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 396 """gets authorization info from the index.meta file at path or given by dom""" |
52 | 397 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
32 | 398 |
399 access = None | |
400 | |
401 if docinfo is None: | |
402 docinfo = {} | |
403 | |
404 if dom is None: | |
78 | 405 for x in range(cut): |
70 | 406 path=getParentDir(path) |
407 dom = self.getIndexMeta(path) | |
46 | 408 |
32 | 409 acctype = dom.xpath("//access-conditions/access/@type") |
410 if acctype and (len(acctype)>0): | |
411 access=acctype[0].value | |
35 | 412 if access in ['group', 'institution']: |
32 | 413 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
414 | |
415 docinfo['accessType'] = access | |
416 return docinfo | |
29 | 417 |
32 | 418 |
70 | 419 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 420 """gets bibliographical info from the index.meta file at path or given by dom""" |
59 | 421 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 422 |
22 | 423 if docinfo is None: |
424 docinfo = {} | |
78 | 425 |
22 | 426 if dom is None: |
78 | 427 for x in range(cut): |
70 | 428 path=getParentDir(path) |
429 dom = self.getIndexMeta(path) | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
430 |
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
431 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
59 | 432 # put in all raw bib fields as dict "bib" |
433 bib = dom.xpath("//bib/*") | |
434 if bib and len(bib)>0: | |
435 bibinfo = {} | |
436 for e in bib: | |
437 bibinfo[e.localName] = getTextFromNode(e) | |
438 docinfo['bib'] = bibinfo | |
439 | |
440 # extract some fields (author, title, year) according to their mapping | |
25 | 441 metaData=self.metadata.main.meta.bib |
442 bibtype=dom.xpath("//bib/@type") | |
443 if bibtype and (len(bibtype)>0): | |
444 bibtype=bibtype[0].value | |
20 | 445 else: |
25 | 446 bibtype="generic" |
59 | 447 |
25 | 448 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
59 | 449 docinfo['bib_type'] = bibtype |
25 | 450 bibmap=metaData.generateMappingForType(bibtype) |
32 | 451 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
31 | 452 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
63 | 453 try: |
454 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
455 except: pass | |
456 try: | |
457 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
458 except: pass | |
459 try: | |
460 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
461 except: pass | |
59 | 462 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
52 | 463 try: |
464 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
465 except: | |
466 docinfo['lang']='' | |
59 | 467 |
22 | 468 return docinfo |
83 | 469 |
470 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
471 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
|
472 """parse texttool tag in index meta""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
473 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
|
474 if docinfo is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
475 docinfo = {} |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
476 if docinfo.get('lang', None) is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
477 docinfo['lang'] = '' # default keine Sprache gesetzt |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
478 if dom is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
479 dom = self.getIndexMeta(url) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
480 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
481 archivePath = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
482 archiveName = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
483 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
484 archiveNames = dom.xpath("//resource/name") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
485 if archiveNames and (len(archiveNames) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
486 archiveName = getTextFromNode(archiveNames[0]) |
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 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
|
489 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
490 archivePaths = dom.xpath("//resource/archive-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
491 if archivePaths and (len(archivePaths) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
492 archivePath = getTextFromNode(archivePaths[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
493 # clean up archive path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
494 if archivePath[0] != '/': |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
495 archivePath = '/' + archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
496 if archiveName and (not archivePath.endswith(archiveName)): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
497 archivePath += "/" + archiveName |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
498 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
499 # try to get archive-path from url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
500 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
|
501 if (not url.startswith('http')): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
502 archivePath = url.replace('index.meta', '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
503 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
504 if archivePath is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
505 # we balk without archive-path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
506 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
22 | 507 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
508 imageDirs = dom.xpath("//texttool/image") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
509 if imageDirs and (len(imageDirs) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
510 imageDir = getTextFromNode(imageDirs[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
511 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
512 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
513 # 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
|
514 #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
|
515 imageDir = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
516 #xquery="//pb" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
517 docinfo['imagePath'] = "" # keine Bilder |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
518 docinfo['imageURL'] = "" |
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 if imageDir and archivePath: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
521 #print "image: ", imageDir, " archivepath: ", archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
522 imageDir = os.path.join(archivePath, imageDir) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
523 imageDir = imageDir.replace("/mpiwg/online", '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
524 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
525 docinfo['imagePath'] = imageDir |
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 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
|
528 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
529 viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
530 if viewerUrls and (len(viewerUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
531 viewerUrl = getTextFromNode(viewerUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
532 docinfo['viewerURL'] = viewerUrl |
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") |
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 if urlparse.urlparse(textUrl)[0] == "": #keine url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
538 textUrl = os.path.join(archivePath, textUrl) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
539 # fix URLs starting with /mpiwg/online |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
540 if textUrl.startswith("/mpiwg/online"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
541 textUrl = textUrl.replace("/mpiwg/online", '', 1) |
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 docinfo['textURL'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
544 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
545 textUrls = dom.xpath("//texttool/text-url-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
546 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
547 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
548 docinfo['textURLPath'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
549 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
550 presentationUrls = dom.xpath("//texttool/presentation") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
551 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
|
552 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
553 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
|
554 # 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
|
555 # 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
|
556 presentationPath = getTextFromNode(presentationUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
557 if url.endswith("index.meta"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
558 presentationUrl = url.replace('index.meta', presentationPath) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
559 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
560 presentationUrl = url + "/" + presentationPath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
561 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
|
562 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
|
563 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
564 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
|
565 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
566 return docinfo |
22 | 567 |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
568 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
569 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
570 """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
|
571 """ |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
572 dom=self.getPresentationInfoXML(url) |
62 | 573 try: |
574 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
575 except: | |
576 pass | |
577 try: | |
578 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
579 except: | |
580 pass | |
581 try: | |
582 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
583 except: | |
584 pass | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
585 return docinfo |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
586 |
70 | 587 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
22 | 588 """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
52 | 589 logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
22 | 590 if docinfo is None: |
591 docinfo = {} | |
29 | 592 path=path.replace("/mpiwg/online","") |
22 | 593 docinfo['imagePath'] = path |
73 | 594 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
78 | 595 |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
596 pathorig=path |
78 | 597 for x in range(cut): |
598 path=getParentDir(path) | |
599 logging.error("PATH:"+path) | |
31 | 600 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
22 | 601 docinfo['imageURL'] = imageUrl |
602 | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
603 #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
|
604 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
|
605 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
22 | 606 return docinfo |
20 | 607 |
22 | 608 |
609 def getDocinfo(self, mode, url): | |
610 """returns docinfo depending on mode""" | |
52 | 611 logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
22 | 612 # look for cached docinfo in session |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
613 if self.REQUEST.SESSION.has_key('docinfo'): |
22 | 614 docinfo = self.REQUEST.SESSION['docinfo'] |
615 # check if its still current | |
616 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
52 | 617 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
22 | 618 return docinfo |
619 # new docinfo | |
620 docinfo = {'mode': mode, 'url': url} | |
621 if mode=="texttool": #index.meta with texttool information | |
622 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
623 elif mode=="imagepath": | |
624 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
70 | 625 elif mode=="filepath": |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
626 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
22 | 627 else: |
52 | 628 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
|
629 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
37 | 630 |
52 | 631 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
22 | 632 self.REQUEST.SESSION['docinfo'] = docinfo |
633 return docinfo | |
20 | 634 |
635 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
636 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): |
22 | 637 """returns pageinfo with the given parameters""" |
638 pageinfo = {} | |
25 | 639 current = getInt(current) |
640 pageinfo['current'] = current | |
641 rows = int(rows or self.thumbrows) | |
642 pageinfo['rows'] = rows | |
643 cols = int(cols or self.thumbcols) | |
644 pageinfo['cols'] = cols | |
645 grpsize = cols * rows | |
646 pageinfo['groupsize'] = grpsize | |
61 | 647 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
648 # int(current / grpsize) * grpsize +1)) | |
22 | 649 pageinfo['start'] = start |
25 | 650 pageinfo['end'] = start + grpsize |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
651 if (docinfo is not None) and ('numPages' in docinfo): |
25 | 652 np = int(docinfo['numPages']) |
653 pageinfo['end'] = min(pageinfo['end'], np) | |
654 pageinfo['numgroups'] = int(np / grpsize) | |
655 if np % grpsize > 0: | |
656 pageinfo['numgroups'] += 1 | |
99 | 657 |
658 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
659 pageinfo['viewMode'] = viewMode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
660 pageinfo['tocMode'] = tocMode |
95 | 661 pageinfo['query'] = self.REQUEST.get('query',' ') |
662 pageinfo['queryType'] = self.REQUEST.get('queryType',' ') | |
663 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') | |
99 | 664 |
665 pageinfo['textPN'] = self.REQUEST.get('textPN','1') | |
666 | |
95 | 667 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
668 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
|
669 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
99 | 670 toc = int (pageinfo['tocPN']) |
671 pageinfo['textPages'] =int (toc) | |
672 | |
673 if 'tocSize_%s'%tocMode in docinfo: | |
674 tocSize = int(docinfo['tocSize_%s'%tocMode]) | |
675 tocPageSize = int(pageinfo['tocPageSize']) | |
97 | 676 # cached toc |
99 | 677 |
678 if tocSize%tocPageSize>0: | |
679 tocPages=tocSize/tocPageSize+1 | |
680 else: | |
681 tocPages=tocSize/tocPageSize | |
682 pageinfo['tocPN'] = min (tocPages,toc) | |
683 | |
95 | 684 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
685 pageinfo['sn'] =self.REQUEST.get('sn','1') | |
78 | 686 |
22 | 687 return pageinfo |
688 | |
95 | 689 def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None): |
690 """get search list""" | |
691 docpath = docinfo['textURLPath'] | |
692 pagesize = pageinfo['queryPageSize'] | |
693 pn = pageinfo['searchPN'] | |
694 sn = pageinfo['sn'] | |
695 query =pageinfo['query'] | |
696 queryType =pageinfo['queryType'] | |
96 | 697 viewMode= pageinfo['viewMode'] |
698 tocMode = pageinfo['tocMode'] | |
699 tocPN = pageinfo['tocPN'] | |
99 | 700 |
701 page=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) | |
702 pagexm = page.replace('?document=/echo/la/Benedetti_1585.xml','?url=/mpiwg/online/permanent/library/163127KK') | |
703 pagexml=pagexm.replace('mode=text','mode=texttool') | |
95 | 704 pagedom = Parse(pagexml) |
97 | 705 |
99 | 706 if (queryType=="fulltext")or(queryType=="fulltextMorph")or(queryType=="xpath")or(queryType=="xquery"): |
707 pagedivs = pagedom.xpath("//div[@class='queryResultPage']") | |
708 selfurl = self.absolute_url() | |
709 page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s&query=%s&queryType=%s'%(selfurl, viewMode, tocMode, tocPN, query, queryType)) | |
710 text =page.replace('mode=text','mode=texttool') | |
711 return text | |
97 | 712 |
99 | 713 if (queryType=="ftIndex")or(queryType=="ftIndexMorph"): |
714 pagedivs= pagedom.xpath("//div[@class='queryResultPage']") | |
715 if len(pagedivs)>0: | |
716 pagenode=pagedivs[0] | |
717 links=pagenode.xpath("//a") | |
718 for l in links: | |
719 hrefNode = l.getAttributeNodeNS(None, u"href") | |
720 if hrefNode: | |
721 href = hrefNode.nodeValue | |
722 if href.startswith('../lt/lex.xql'): | |
723 selfurl = self.absolute_url() | |
724 hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl) | |
725 | |
726 | |
727 | |
728 l.setAttributeNS(None, 'target', '_blank') | |
729 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=200, scrollbars=1'); return false;") | |
730 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
731 if href.startswith('../lt/lemma.xql'): | |
732 selfurl = self.absolute_url() | |
733 hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) | |
734 l.setAttributeNS(None, 'target', '_blank') | |
735 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=200, scrollbars=1'); return false;") | |
736 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
737 return serializeNode(pagenode) | |
97 | 738 |
99 | 739 return "no text here" |
97 | 740 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
741 def getNumPages(self,docinfo=None): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
742 """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
|
743 xquery = '//pb' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
744 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
|
745 # 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
|
746 docinfo['numPages'] = text.count("<pb ") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
747 return docinfo |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
748 |
96 | 749 def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None,): |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
750 """returns single page from fulltext""" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
751 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
752 if mode == "text_dict": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
753 textmode = "textPollux" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
754 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
755 textmode = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
756 |
96 | 757 #selfurl = self.absolute_url() |
758 #viewMode= pageinfo['viewMode'] | |
759 #tocMode = pageinfo['tocMode'] | |
760 #tocPN = pageinfo['tocPN'] | |
761 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
762 pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
763 # post-processing downloaded xml |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
764 pagedom = Parse(pagexml) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
765 # plain text mode |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
766 if mode == "text": |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
767 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
768 pagedivs = pagedom.xpath("/div") |
95 | 769 #queryResultPage |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
770 if len(pagedivs) > 0: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
771 pagenode = pagedivs[0] |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
772 return serializeNode(pagenode) |
99 | 773 if mode == "xml": |
774 # first div contains text | |
775 pagedivs = pagedom.xpath("/div") | |
776 if len(pagedivs) > 0: | |
777 pagenode = pagedivs[0] | |
778 return serializeNode(pagenode) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
779 # text-with-links mode |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
780 if mode == "text_dict": |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
781 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
782 pagedivs = pagedom.xpath("/div") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
783 if len(pagedivs) > 0: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
784 pagenode = pagedivs[0] |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
785 # check all a-tags |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
786 links = pagenode.xpath("//a") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
787 for l in links: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
788 hrefNode = l.getAttributeNodeNS(None, u"href") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
789 if hrefNode: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
790 # is link with href |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
791 href = hrefNode.nodeValue |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
792 if href.startswith('lt/lex.xql'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
793 # is pollux link |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
794 selfurl = self.absolute_url() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
795 # change href |
96 | 796 hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
797 # add target |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
798 l.setAttributeNS(None, 'target', '_blank') |
99 | 799 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") |
800 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
96 | 801 |
802 if href.startswith('lt/lemma.xql'): | |
803 selfurl = self.absolute_url() | |
804 hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) | |
805 l.setAttributeNS(None, 'target', '_blank') | |
99 | 806 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") |
807 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
808 return serializeNode(pagenode) |
0 | 809 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
810 return "no text here" |
22 | 811 |
96 | 812 def getTranslate(self, query=None, language=None): |
813 """translate into another languages""" | |
814 pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","query=%s&language=%s"%(query,language),outputUnicode=False) | |
815 return pagexml | |
816 | |
97 | 817 def getLemma(self, lemma=None, language=None): |
99 | 818 """simular words lemma """ |
97 | 819 pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False) |
96 | 820 return pagexml |
821 | |
97 | 822 def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1): |
823 """number of""" | |
824 docpath = docinfo['textURLPath'] | |
825 pagesize = pageinfo['queryPageSize'] | |
826 pn = pageinfo['searchPN'] | |
827 query =pageinfo['query'] | |
828 queryType =pageinfo['queryType'] | |
829 | |
830 tocSearch = 0 | |
831 tocDiv = None | |
832 pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False) | |
833 | |
834 pagedom = Parse(pagexml) | |
835 numdivs = pagedom.xpath("//div[@class='queryResultHits']") | |
836 tocSearch = int(getTextFromNode(numdivs[0])) | |
837 tc=int((tocSearch/20)+1) | |
838 logging.debug("documentViewer (gettoc) tc: %s"%(tc)) | |
839 return tc | |
840 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
841 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
|
842 """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
|
843 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
|
844 if 'tocSize_%s'%mode in docinfo: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
845 # cached toc |
97 | 846 return docinfo |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
847 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
848 # 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
|
849 pagesize = 1000 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
850 pn = 1 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
851 if mode == "text": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
852 queryType = "toc" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
853 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
854 queryType = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
855 # number of entries in toc |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
856 tocSize = 0 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
857 tocDiv = None |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
858 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
|
859 # post-processing downloaded xml |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
860 pagedom = Parse(pagexml) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
861 # get number of entries |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
862 numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
863 if len(numdivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
864 tocSize = int(getTextFromNode(numdivs[0])) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
865 # div contains text |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
866 #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
867 #if len(pagedivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
868 # tocDiv = pagedivs[0] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
869 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
870 docinfo['tocSize_%s'%mode] = tocSize |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
871 #docinfo['tocDiv_%s'%mode] = tocDiv |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
872 return docinfo |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
873 |
95 | 874 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
|
875 """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
|
876 # 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
|
877 if mode == "text": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
878 queryType = "toc" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
879 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
880 queryType = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
881 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
882 pagesize = pageinfo['tocPageSize'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
883 pn = pageinfo['tocPN'] |
96 | 884 |
885 selfurl = self.absolute_url() | |
886 viewMode= pageinfo['viewMode'] | |
887 tocMode = pageinfo['tocMode'] | |
888 tocPN = pageinfo['tocPN'] | |
889 | |
95 | 890 pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False) |
96 | 891 page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl, viewMode, tocMode, tocPN)) |
892 text = page.replace('mode=image','mode=texttool') | |
893 return text | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
894 # post-processing downloaded xml |
96 | 895 #pagedom = Parse(text) |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
896 # div contains text |
96 | 897 #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
898 #if len(pagedivs) > 0: | |
899 # pagenode = pagedivs[0] | |
900 # return serializeNode(pagenode) | |
901 #else: | |
902 # return "No TOC!" | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
903 |
22 | 904 |
95 | 905 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
22 | 906 """init document viewer""" |
907 self.title=title | |
908 self.digilibBaseUrl = digilibBaseUrl | |
25 | 909 self.thumbrows = thumbrows |
910 self.thumbcols = thumbcols | |
32 | 911 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
22 | 912 if RESPONSE is not None: |
913 RESPONSE.redirect('manage_main') | |
0 | 914 |
915 | |
916 | |
917 def manage_AddDocumentViewerForm(self): | |
918 """add the viewer form""" | |
22 | 919 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 920 return pt() |
921 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
922 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 923 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
924 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 925 self._setObject(id,newObj) |
926 | |
927 if RESPONSE is not None: | |
928 RESPONSE.redirect('manage_main') | |
22 | 929 |
930 | |
931 ## | |
932 ## DocumentViewerTemplate class | |
933 ## | |
934 class DocumentViewerTemplate(ZopePageTemplate): | |
935 """Template for document viewer""" | |
936 meta_type="DocumentViewer Template" | |
937 | |
938 | |
939 def manage_addDocumentViewerTemplateForm(self): | |
940 """Form for adding""" | |
941 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
942 return pt() | |
943 | |
944 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
945 REQUEST=None, submit=None): | |
946 "Add a Page Template with optional file content." | |
947 | |
948 self._setObject(id, DocumentViewerTemplate(id)) | |
949 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
950 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
|
951 logging.info("txt %s:"%txt) |
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
952 ob.pt_edit(txt,"text/html") |
22 | 953 if title: |
954 ob.pt_setTitle(title) | |
955 try: | |
956 u = self.DestinationURL() | |
957 except AttributeError: | |
958 u = REQUEST['URL1'] | |
959 | |
960 u = "%s/%s" % (u, urllib.quote(id)) | |
961 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
962 return '' | |
963 | |
964 | |
41 | 965 |