Mercurial > hg > documentViewer
annotate documentViewer.py @ 128:4db49915d825 Root_modularisierung
Last lemma
author | abukhman |
---|---|
date | Fri, 11 Jun 2010 12:34:24 +0200 |
parents | 49f381f896d0 |
children | 5c779d7b5f71 |
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 |
101 | 5 from Products.PythonScripts.standard import url_quote |
0 | 6 from AccessControl import ClassSecurityInfo |
32 | 7 from AccessControl import getSecurityManager |
0 | 8 from Globals import package_home |
9 | |
10 from Ft.Xml.Domlette import NonvalidatingReader | |
11 from Ft.Xml.Domlette import PrettyPrint, Print | |
38 | 12 from Ft.Xml import EMPTY_NAMESPACE, Parse |
0 | 13 |
97 | 14 from xml.dom.minidom import parse, parseString |
15 | |
16 | |
83 | 17 |
0 | 18 import Ft.Xml.XPath |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
19 import cStringIO |
83 | 20 import xmlrpclib |
0 | 21 import os.path |
31 | 22 import sys |
0 | 23 import cgi |
24 import urllib | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
25 import logging |
61 | 26 import math |
52 | 27 |
46 | 28 import urlparse |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
29 from types import * |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
30 |
52 | 31 def logger(txt,method,txt2): |
32 """logging""" | |
33 logging.info(txt+ txt2) | |
34 | |
35 | |
25 | 36 def getInt(number, default=0): |
37 """returns always an int (0 in case of problems)""" | |
38 try: | |
39 return int(number) | |
40 except: | |
62 | 41 return int(default) |
25 | 42 |
0 | 43 def getTextFromNode(nodename): |
46 | 44 """get the cdata content of a node""" |
32 | 45 if nodename is None: |
46 return "" | |
0 | 47 nodelist=nodename.childNodes |
48 rc = "" | |
49 for node in nodelist: | |
50 if node.nodeType == node.TEXT_NODE: | |
51 rc = rc + node.data | |
52 return rc | |
53 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
54 def serializeNode(node, encoding='utf-8'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
55 """returns a string containing node as XML""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
56 buf = cStringIO.StringIO() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
57 Print(node, stream=buf, encoding=encoding) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
58 s = buf.getvalue() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
59 buf.close() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
60 return s |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
61 |
35 | 62 |
63 def getParentDir(path): | |
64 """returns pathname shortened by one""" | |
65 return '/'.join(path.split('/')[0:-1]) | |
66 | |
67 | |
0 | 68 import socket |
69 | |
32 | 70 def urlopen(url,timeout=2): |
0 | 71 """urlopen mit timeout""" |
32 | 72 socket.setdefaulttimeout(timeout) |
0 | 73 ret=urllib.urlopen(url) |
74 socket.setdefaulttimeout(5) | |
75 return ret | |
76 | |
77 | |
22 | 78 ## |
79 ## documentViewer class | |
80 ## | |
81 class documentViewer(Folder): | |
0 | 82 """document viewer""" |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
83 #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" |
46 | 84 |
0 | 85 meta_type="Document viewer" |
86 | |
87 security=ClassSecurityInfo() | |
22 | 88 manage_options=Folder.manage_options+( |
0 | 89 {'label':'main config','action':'changeDocumentViewerForm'}, |
90 ) | |
91 | |
22 | 92 # templates and forms |
93 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
|
94 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
|
95 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
|
96 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
|
97 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
|
98 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
|
99 page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
99 | 100 page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) |
22 | 101 head_main = PageTemplateFile('zpt/head_main', globals()) |
102 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
57 | 103 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
22 | 104 |
68 | 105 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
22 | 106 security.declareProtected('View management screens','changeDocumentViewerForm') |
107 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
108 | |
0 | 109 |
95 | 110 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
0 | 111 """init document viewer""" |
112 self.id=id | |
113 self.title=title | |
25 | 114 self.thumbcols = thumbcols |
115 self.thumbrows = thumbrows | |
32 | 116 # authgroups is list of authorized groups (delimited by ,) |
117 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
|
118 # 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
|
119 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
120 templateFolder = Folder('template') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
121 #self['template'] = templateFolder # Zope-2.12 style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
122 self._setObject('template',templateFolder) # old style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
123 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
124 from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
125 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
|
126 #templateFolder['fulltextclient'] = xmlRpcClient |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
127 templateFolder._setObject('fulltextclient',xmlRpcClient) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
128 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
129 logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e)) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
130 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
131 from Products.zogiLib.zogiLib import zogiLib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
132 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
|
133 #templateFolder['zogilib'] = zogilib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
134 templateFolder._setObject('zogilib',zogilib) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
135 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
136 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
|
137 |
22 | 138 |
68 | 139 security.declareProtected('View','thumbs_rss') |
140 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
141 ''' | |
142 view it | |
143 @param mode: defines how to access the document behind url | |
144 @param url: url which contains display information | |
145 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
146 | |
147 ''' | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
148 logging.debug("HHHHHHHHHHHHHH:load the rss") |
68 | 149 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
150 | |
151 if not hasattr(self, 'template'): | |
152 # create template folder if it doesn't exist | |
153 self.manage_addFolder('template') | |
154 | |
155 if not self.digilibBaseUrl: | |
156 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
157 | |
158 docinfo = self.getDocinfo(mode=mode,url=url) | |
159 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
160 pt = getattr(self.template, 'thumbs_main_rss') | |
161 | |
162 if viewMode=="auto": # automodus gewaehlt | |
163 if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert | |
164 viewMode="text" | |
165 else: | |
166 viewMode="images" | |
167 | |
168 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
169 | |
22 | 170 security.declareProtected('View','index_html') |
95 | 171 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None): |
22 | 172 ''' |
173 view it | |
57 | 174 @param mode: defines how to access the document behind url |
22 | 175 @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
|
176 @param viewMode: if images display images, if text display text, default is auto (text,images or auto) |
99 | 177 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
100 | 178 @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) |
22 | 179 ''' |
0 | 180 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
181 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
22 | 182 |
183 if not hasattr(self, 'template'): | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
184 # this won't work |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
185 logging.error("template folder missing!") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
186 return "ERROR: template folder missing!" |
22 | 187 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
188 if not getattr(self, 'digilibBaseUrl', None): |
22 | 189 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
190 | |
25 | 191 docinfo = self.getDocinfo(mode=mode,url=url) |
97 | 192 |
193 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
194 if tocMode != "thumbs": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
195 # get table of contents |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
196 docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
97 | 197 |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
198 if viewMode=="auto": # automodus gewaehlt |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
199 if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert |
127 | 200 viewMode="text_dict" |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
201 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
202 viewMode="images" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
203 |
127 | 204 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) |
205 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
206 pt = getattr(self.template, 'viewer_main') |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
207 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
0 | 208 |
74 | 209 def generateMarks(self,mk): |
210 ret="" | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
211 if mk is None: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
212 return "" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
213 if type(mk) is not ListType: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
214 mk=[mk] |
74 | 215 for m in mk: |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
216 ret+="mk=%s"%m |
74 | 217 return ret |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
218 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
219 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
220 def findDigilibUrl(self): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
221 """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
|
222 url = self.template.zogilib.getDLBaseUrl() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
223 return url |
126 | 224 |
225 def getDocumentViewerURL(self): | |
226 """returns the URL of this instance""" | |
227 return self.absolute_url() | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
228 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
229 def getStyle(self, idx, selected, style=""): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
230 """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
|
231 #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
|
232 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
233 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
234 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
235 return style |
74 | 236 |
25 | 237 def getLink(self,param=None,val=None): |
238 """link to documentviewer with parameter param set to val""" | |
35 | 239 params=self.REQUEST.form.copy() |
25 | 240 if param is not None: |
31 | 241 if val is None: |
242 if params.has_key(param): | |
243 del params[param] | |
25 | 244 else: |
35 | 245 params[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
246 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
247 if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
78 | 248 params["mode"] = "imagepath" |
249 params["url"] = getParentDir(params["url"]) | |
31 | 250 |
35 | 251 # quote values and assemble into query string |
252 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
253 url=self.REQUEST['URL1']+"?"+ps | |
25 | 254 return url |
255 | |
68 | 256 def getLinkAmp(self,param=None,val=None): |
257 """link to documentviewer with parameter param set to val""" | |
258 params=self.REQUEST.form.copy() | |
259 if param is not None: | |
260 if val is None: | |
261 if params.has_key(param): | |
262 del params[param] | |
263 else: | |
264 params[param] = str(val) | |
265 | |
266 # quote values and assemble into query string | |
267 logging.info("XYXXXXX: %s"%repr(params.items())) | |
268 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
269 url=self.REQUEST['URL1']+"?"+ps | |
270 return url | |
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
271 |
57 | 272 def getInfo_xml(self,url,mode): |
273 """returns info about the document as XML""" | |
274 | |
275 if not self.digilibBaseUrl: | |
276 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
277 | |
278 docinfo = self.getDocinfo(mode=mode,url=url) | |
279 pt = getattr(self.template, 'info_xml') | |
280 return pt(docinfo=docinfo) | |
281 | |
0 | 282 |
35 | 283 def isAccessible(self, docinfo): |
32 | 284 """returns if access to the resource is granted""" |
285 access = docinfo.get('accessType', None) | |
52 | 286 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
45 | 287 if access is not None and access == 'free': |
52 | 288 logger("documentViewer (accessOK)", logging.INFO, "access is free") |
32 | 289 return True |
45 | 290 elif access is None or access in self.authgroups: |
35 | 291 # only local access -- only logged in users |
292 user = getSecurityManager().getUser() | |
293 if user is not None: | |
294 #print "user: ", user | |
295 return (user.getUserName() != "Anonymous User") | |
296 else: | |
297 return False | |
32 | 298 |
52 | 299 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
32 | 300 return False |
35 | 301 |
32 | 302 |
73 | 303 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
29 | 304 """gibt param von dlInfo aus""" |
40 | 305 num_retries = 3 |
31 | 306 if docinfo is None: |
307 docinfo = {} | |
73 | 308 |
309 for x in range(cut): | |
78 | 310 |
73 | 311 path=getParentDir(path) |
78 | 312 |
40 | 313 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 314 |
52 | 315 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
29 | 316 |
40 | 317 for cnt in range(num_retries): |
35 | 318 try: |
40 | 319 # dom = NonvalidatingReader.parseUri(imageUrl) |
320 txt=urllib.urlopen(infoUrl).read() | |
321 dom = Parse(txt) | |
35 | 322 break |
323 except: | |
52 | 324 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
35 | 325 else: |
40 | 326 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
29 | 327 |
37 | 328 sizes=dom.xpath("//dir/size") |
52 | 329 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
29 | 330 |
37 | 331 if sizes: |
332 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
31 | 333 else: |
334 docinfo['numPages'] = 0 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
335 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
336 # TODO: produce and keep list of image names and numbers |
31 | 337 |
338 return docinfo | |
32 | 339 |
29 | 340 |
35 | 341 def getIndexMeta(self, url): |
342 """returns dom of index.meta document at url""" | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
343 num_retries = 3 |
35 | 344 dom = None |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
345 metaUrl = None |
35 | 346 if url.startswith("http://"): |
347 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
348 metaUrl = url |
35 | 349 else: |
350 # online path | |
351 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 352 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 353 if not metaUrl.endswith("index.meta"): |
354 metaUrl += "/index.meta" | |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
355 logging.debug("METAURL: %s"%metaUrl) |
40 | 356 for cnt in range(num_retries): |
35 | 357 try: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
358 # patch dirk encoding fehler treten dann nicht mehr auf |
38 | 359 # dom = NonvalidatingReader.parseUri(metaUrl) |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
360 txt=urllib.urlopen(metaUrl).read() |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
361 dom = Parse(txt) |
40 | 362 break |
35 | 363 except: |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
364 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
|
365 |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
366 if dom is None: |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
367 raise IOError("Unable to read index meta from %s"%(url)) |
35 | 368 |
369 return dom | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
370 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
371 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
372 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
373 num_retries = 3 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
374 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
375 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
376 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
377 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
378 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
379 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
380 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
381 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
382 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
383 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
384 for cnt in range(num_retries): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
385 try: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
386 # patch dirk encoding fehler treten dann nicht mehr auf |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
387 # dom = NonvalidatingReader.parseUri(metaUrl) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
388 txt=urllib.urlopen(metaUrl).read() |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
389 dom = Parse(txt) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
390 break |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
391 except: |
52 | 392 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
|
393 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
394 if dom is None: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
395 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
396 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
397 return dom |
35 | 398 |
399 | |
70 | 400 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 401 """gets authorization info from the index.meta file at path or given by dom""" |
52 | 402 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
32 | 403 |
404 access = None | |
405 | |
406 if docinfo is None: | |
407 docinfo = {} | |
408 | |
409 if dom is None: | |
78 | 410 for x in range(cut): |
70 | 411 path=getParentDir(path) |
412 dom = self.getIndexMeta(path) | |
46 | 413 |
32 | 414 acctype = dom.xpath("//access-conditions/access/@type") |
415 if acctype and (len(acctype)>0): | |
416 access=acctype[0].value | |
35 | 417 if access in ['group', 'institution']: |
32 | 418 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
419 | |
420 docinfo['accessType'] = access | |
421 return docinfo | |
29 | 422 |
32 | 423 |
70 | 424 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 425 """gets bibliographical info from the index.meta file at path or given by dom""" |
59 | 426 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 427 |
22 | 428 if docinfo is None: |
429 docinfo = {} | |
78 | 430 |
22 | 431 if dom is None: |
78 | 432 for x in range(cut): |
70 | 433 path=getParentDir(path) |
434 dom = self.getIndexMeta(path) | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
435 |
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
436 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
59 | 437 # put in all raw bib fields as dict "bib" |
438 bib = dom.xpath("//bib/*") | |
439 if bib and len(bib)>0: | |
440 bibinfo = {} | |
441 for e in bib: | |
442 bibinfo[e.localName] = getTextFromNode(e) | |
443 docinfo['bib'] = bibinfo | |
444 | |
445 # extract some fields (author, title, year) according to their mapping | |
25 | 446 metaData=self.metadata.main.meta.bib |
447 bibtype=dom.xpath("//bib/@type") | |
448 if bibtype and (len(bibtype)>0): | |
449 bibtype=bibtype[0].value | |
20 | 450 else: |
25 | 451 bibtype="generic" |
59 | 452 |
25 | 453 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
59 | 454 docinfo['bib_type'] = bibtype |
25 | 455 bibmap=metaData.generateMappingForType(bibtype) |
32 | 456 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
31 | 457 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
63 | 458 try: |
459 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
460 except: pass | |
461 try: | |
462 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
463 except: pass | |
464 try: | |
465 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
466 except: pass | |
59 | 467 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
52 | 468 try: |
469 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
470 except: | |
471 docinfo['lang']='' | |
59 | 472 |
22 | 473 return docinfo |
83 | 474 |
475 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
476 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
|
477 """parse texttool tag in index meta""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
478 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
|
479 if docinfo is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
480 docinfo = {} |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
481 if docinfo.get('lang', None) is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
482 docinfo['lang'] = '' # default keine Sprache gesetzt |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
483 if dom is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
484 dom = self.getIndexMeta(url) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
485 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
486 archivePath = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
487 archiveName = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
488 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
489 archiveNames = dom.xpath("//resource/name") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
490 if archiveNames and (len(archiveNames) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
491 archiveName = getTextFromNode(archiveNames[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
492 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
493 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
|
494 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
495 archivePaths = dom.xpath("//resource/archive-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
496 if archivePaths and (len(archivePaths) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
497 archivePath = getTextFromNode(archivePaths[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
498 # clean up archive path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
499 if archivePath[0] != '/': |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
500 archivePath = '/' + archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
501 if archiveName and (not archivePath.endswith(archiveName)): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
502 archivePath += "/" + archiveName |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
503 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
504 # try to get archive-path from url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
505 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
|
506 if (not url.startswith('http')): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
507 archivePath = url.replace('index.meta', '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
508 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
509 if archivePath is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
510 # we balk without archive-path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
511 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
22 | 512 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
513 imageDirs = dom.xpath("//texttool/image") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
514 if imageDirs and (len(imageDirs) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
515 imageDir = getTextFromNode(imageDirs[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
516 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
517 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
518 # 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
|
519 #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
|
520 imageDir = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
521 #xquery="//pb" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
522 docinfo['imagePath'] = "" # keine Bilder |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
523 docinfo['imageURL'] = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
524 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
525 if imageDir and archivePath: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
526 #print "image: ", imageDir, " archivepath: ", archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
527 imageDir = os.path.join(archivePath, imageDir) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
528 imageDir = imageDir.replace("/mpiwg/online", '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
529 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
530 docinfo['imagePath'] = imageDir |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
531 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
532 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir |
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 viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
535 if viewerUrls and (len(viewerUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
536 viewerUrl = getTextFromNode(viewerUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
537 docinfo['viewerURL'] = viewerUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
538 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
539 textUrls = dom.xpath("//texttool/text") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
540 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
541 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
542 if urlparse.urlparse(textUrl)[0] == "": #keine url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
543 textUrl = os.path.join(archivePath, textUrl) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
544 # fix URLs starting with /mpiwg/online |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
545 if textUrl.startswith("/mpiwg/online"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
546 textUrl = textUrl.replace("/mpiwg/online", '', 1) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
547 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
548 docinfo['textURL'] = 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 textUrls = dom.xpath("//texttool/text-url-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
551 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
552 textUrl = getTextFromNode(textUrls[0]) |
102 | 553 docinfo['textURLPath'] = textUrl |
554 if not docinfo['imagePath']: | |
555 # text-only, no page images | |
556 docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
557 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
558 presentationUrls = dom.xpath("//texttool/presentation") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
559 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
|
560 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
561 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
|
562 # 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
|
563 # 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
|
564 presentationPath = getTextFromNode(presentationUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
565 if url.endswith("index.meta"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
566 presentationUrl = url.replace('index.meta', presentationPath) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
567 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
568 presentationUrl = url + "/" + presentationPath |
102 | 569 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
570 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
|
571 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
572 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
|
573 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
574 return docinfo |
22 | 575 |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
576 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
577 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
578 """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
|
579 """ |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
580 dom=self.getPresentationInfoXML(url) |
62 | 581 try: |
582 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
583 except: | |
584 pass | |
585 try: | |
586 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
587 except: | |
588 pass | |
589 try: | |
590 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
591 except: | |
592 pass | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
593 return docinfo |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
594 |
70 | 595 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
22 | 596 """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
52 | 597 logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
22 | 598 if docinfo is None: |
599 docinfo = {} | |
29 | 600 path=path.replace("/mpiwg/online","") |
22 | 601 docinfo['imagePath'] = path |
73 | 602 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
78 | 603 |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
604 pathorig=path |
78 | 605 for x in range(cut): |
606 path=getParentDir(path) | |
607 logging.error("PATH:"+path) | |
31 | 608 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
22 | 609 docinfo['imageURL'] = imageUrl |
610 | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
611 #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
|
612 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
|
613 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
22 | 614 return docinfo |
20 | 615 |
22 | 616 |
617 def getDocinfo(self, mode, url): | |
618 """returns docinfo depending on mode""" | |
52 | 619 logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
22 | 620 # look for cached docinfo in session |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
621 if self.REQUEST.SESSION.has_key('docinfo'): |
22 | 622 docinfo = self.REQUEST.SESSION['docinfo'] |
623 # check if its still current | |
624 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
52 | 625 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
22 | 626 return docinfo |
627 # new docinfo | |
628 docinfo = {'mode': mode, 'url': url} | |
629 if mode=="texttool": #index.meta with texttool information | |
630 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
631 elif mode=="imagepath": | |
632 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
70 | 633 elif mode=="filepath": |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
634 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
22 | 635 else: |
52 | 636 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
|
637 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
37 | 638 |
52 | 639 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
22 | 640 self.REQUEST.SESSION['docinfo'] = docinfo |
641 return docinfo | |
128 | 642 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
643 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): |
22 | 644 """returns pageinfo with the given parameters""" |
645 pageinfo = {} | |
25 | 646 current = getInt(current) |
647 pageinfo['current'] = current | |
648 rows = int(rows or self.thumbrows) | |
649 pageinfo['rows'] = rows | |
650 cols = int(cols or self.thumbcols) | |
651 pageinfo['cols'] = cols | |
652 grpsize = cols * rows | |
653 pageinfo['groupsize'] = grpsize | |
61 | 654 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
655 # int(current / grpsize) * grpsize +1)) | |
22 | 656 pageinfo['start'] = start |
25 | 657 pageinfo['end'] = start + grpsize |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
658 if (docinfo is not None) and ('numPages' in docinfo): |
25 | 659 np = int(docinfo['numPages']) |
660 pageinfo['end'] = min(pageinfo['end'], np) | |
661 pageinfo['numgroups'] = int(np / grpsize) | |
662 if np % grpsize > 0: | |
128 | 663 pageinfo['numgroups'] += 1 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
664 pageinfo['viewMode'] = viewMode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
665 pageinfo['tocMode'] = tocMode |
95 | 666 pageinfo['query'] = self.REQUEST.get('query',' ') |
667 pageinfo['queryType'] = self.REQUEST.get('queryType',' ') | |
668 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') | |
99 | 669 pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
106 | 670 pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
95 | 671 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
105 | 672 pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
673 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
99 | 674 toc = int (pageinfo['tocPN']) |
675 pageinfo['textPages'] =int (toc) | |
676 | |
677 if 'tocSize_%s'%tocMode in docinfo: | |
678 tocSize = int(docinfo['tocSize_%s'%tocMode]) | |
679 tocPageSize = int(pageinfo['tocPageSize']) | |
128 | 680 # cached toc |
99 | 681 if tocSize%tocPageSize>0: |
682 tocPages=tocSize/tocPageSize+1 | |
683 else: | |
684 tocPages=tocSize/tocPageSize | |
128 | 685 pageinfo['tocPN'] = min (tocPages,toc) |
95 | 686 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
112 | 687 pageinfo['sn'] =self.REQUEST.get('sn','') |
22 | 688 return pageinfo |
689 | |
128 | 690 def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None): |
95 | 691 """get search list""" |
692 docpath = docinfo['textURLPath'] | |
101 | 693 url = docinfo['url'] |
694 logging.debug("documentViewer (gettoc) docpath: %s"%(docpath)) | |
695 logging.debug("documentViewer (gettoc) url: %s"%(url)) | |
95 | 696 pagesize = pageinfo['queryPageSize'] |
697 pn = pageinfo['searchPN'] | |
698 sn = pageinfo['sn'] | |
106 | 699 highlightQuery = pageinfo['highlightQuery'] |
95 | 700 query =pageinfo['query'] |
701 queryType =pageinfo['queryType'] | |
96 | 702 viewMode= pageinfo['viewMode'] |
703 tocMode = pageinfo['tocMode'] | |
704 tocPN = pageinfo['tocPN'] | |
100 | 705 selfurl = self.absolute_url() |
107 | 706 page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False) |
101 | 707 pagexml = page.replace('?document=%s'%str(docpath),'?url=%s'%url) |
95 | 708 pagedom = Parse(pagexml) |
100 | 709 if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"): |
710 pagedivs = pagedom.xpath("//div[@class='queryResultPage']") | |
711 if len(pagedivs)>0: | |
712 pagenode=pagedivs[0] | |
713 links=pagenode.xpath("//a") | |
714 for l in links: | |
715 hrefNode = l.getAttributeNodeNS(None, u"href") | |
716 if hrefNode: | |
717 href = hrefNode.nodeValue | |
718 if href.startswith('page-fragment.xql'): | |
112 | 719 selfurl = self.absolute_url() |
100 | 720 pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN)) |
112 | 721 hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
128 | 722 return serializeNode(pagenode) |
100 | 723 if (queryType=="fulltextMorph"): |
724 pagedivs = pagedom.xpath("//div[@class='queryResult']") | |
725 if len(pagedivs)>0: | |
726 pagenode=pagedivs[0] | |
727 links=pagenode.xpath("//a") | |
728 for l in links: | |
729 hrefNode = l.getAttributeNodeNS(None, u"href") | |
730 if hrefNode: | |
731 href = hrefNode.nodeValue | |
732 if href.startswith('page-fragment.xql'): | |
733 selfurl = self.absolute_url() | |
734 pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN)) | |
735 hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) | |
736 if href.startswith('../lt/lemma.xql'): | |
128 | 737 hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl)) |
100 | 738 l.setAttributeNS(None, 'target', '_blank') |
739 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") | |
117 | 740 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
741 pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']") | |
128 | 742 return serializeNode(pagenode) |
99 | 743 if (queryType=="ftIndex")or(queryType=="ftIndexMorph"): |
744 pagedivs= pagedom.xpath("//div[@class='queryResultPage']") | |
745 if len(pagedivs)>0: | |
746 pagenode=pagedivs[0] | |
747 links=pagenode.xpath("//a") | |
748 for l in links: | |
749 hrefNode = l.getAttributeNodeNS(None, u"href") | |
750 if hrefNode: | |
751 href = hrefNode.nodeValue | |
128 | 752 hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn)) |
99 | 753 if href.startswith('../lt/lex.xql'): |
106 | 754 hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl) |
99 | 755 l.setAttributeNS(None, 'target', '_blank') |
100 | 756 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") |
99 | 757 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
758 if href.startswith('../lt/lemma.xql'): | |
106 | 759 hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl) |
99 | 760 l.setAttributeNS(None, 'target', '_blank') |
100 | 761 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") |
99 | 762 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
100 | 763 return serializeNode(pagenode) |
101 | 764 return "no text here" |
97 | 765 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
766 def getNumPages(self,docinfo=None): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
767 """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
|
768 xquery = '//pb' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
769 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
|
770 # 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
|
771 docinfo['numPages'] = text.count("<pb ") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
772 return docinfo |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
773 |
120 | 774 def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None): |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
775 """returns single page from fulltext""" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
776 docpath = docinfo['textURLPath'] |
112 | 777 path = docinfo['textURLPath'] |
778 url = docinfo['url'] | |
779 viewMode= pageinfo['viewMode'] | |
780 tocMode = pageinfo['tocMode'] | |
781 tocPN = pageinfo['tocPN'] | |
782 selfurl = self.absolute_url() | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
783 if mode == "text_dict": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
784 textmode = "textPollux" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
785 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
786 textmode = mode |
112 | 787 |
788 textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn) | |
789 if highlightQuery is not None: | |
128 | 790 textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn) |
112 | 791 pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
792 pagedom = Parse(pagexml) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
793 # plain text mode |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
794 if mode == "text": |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
795 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
796 pagedivs = pagedom.xpath("/div") |
112 | 797 if len(pagedivs) > 0: |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
798 pagenode = pagedivs[0] |
103 | 799 links = pagenode.xpath("//a") |
800 for l in links: | |
801 hrefNode = l.getAttributeNodeNS(None, u"href") | |
802 if hrefNode: | |
803 href= hrefNode.nodeValue | |
112 | 804 if href.startswith('#note-'): |
805 hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
806 return serializeNode(pagenode) |
99 | 807 if mode == "xml": |
808 # first div contains text | |
809 pagedivs = pagedom.xpath("/div") | |
810 if len(pagedivs) > 0: | |
811 pagenode = pagedivs[0] | |
812 return serializeNode(pagenode) | |
124 | 813 if mode == "pureXml": |
814 # first div contains text | |
815 pagedivs = pagedom.xpath("/div") | |
816 if len(pagedivs) > 0: | |
817 pagenode = pagedivs[0] | |
818 return serializeNode(pagenode) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
819 # text-with-links mode |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
820 if mode == "text_dict": |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
821 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
822 pagedivs = pagedom.xpath("/div") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
823 if len(pagedivs) > 0: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
824 pagenode = pagedivs[0] |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
825 # check all a-tags |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
826 links = pagenode.xpath("//a") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
827 for l in links: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
828 hrefNode = l.getAttributeNodeNS(None, u"href") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
829 if hrefNode: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
830 # is link with href |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
831 href = hrefNode.nodeValue |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
832 if href.startswith('lt/lex.xql'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
833 # is pollux link |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
834 selfurl = self.absolute_url() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
835 # change href |
96 | 836 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
|
837 # add target |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
838 l.setAttributeNS(None, 'target', '_blank') |
99 | 839 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") |
128 | 840 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
96 | 841 if href.startswith('lt/lemma.xql'): |
842 selfurl = self.absolute_url() | |
843 hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) | |
844 l.setAttributeNS(None, 'target', '_blank') | |
99 | 845 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") |
128 | 846 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
112 | 847 if href.startswith('#note-'): |
848 hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
849 return serializeNode(pagenode) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
850 return "no text here" |
22 | 851 |
96 | 852 def getTranslate(self, query=None, language=None): |
853 """translate into another languages""" | |
101 | 854 pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) |
96 | 855 return pagexml |
856 | |
97 | 857 def getLemma(self, lemma=None, language=None): |
99 | 858 """simular words lemma """ |
101 | 859 pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) |
128 | 860 return pagexml |
861 | |
862 def getLemmaNew(self, query=None, language=None): | |
863 """simular words lemma """ | |
864 pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query))) | |
96 | 865 return pagexml |
866 | |
97 | 867 def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1): |
868 """number of""" | |
869 docpath = docinfo['textURLPath'] | |
870 pagesize = pageinfo['queryPageSize'] | |
871 pn = pageinfo['searchPN'] | |
872 query =pageinfo['query'] | |
873 queryType =pageinfo['queryType'] | |
874 tocSearch = 0 | |
875 tocDiv = None | |
876 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) | |
877 pagedom = Parse(pagexml) | |
878 numdivs = pagedom.xpath("//div[@class='queryResultHits']") | |
879 tocSearch = int(getTextFromNode(numdivs[0])) | |
105 | 880 tc=int((tocSearch/10)+1) |
97 | 881 logging.debug("documentViewer (gettoc) tc: %s"%(tc)) |
882 return tc | |
883 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
884 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
|
885 """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
|
886 logging.debug("documentViewer (gettoc) mode: %s"%(mode)) |
126 | 887 if mode == "none": |
128 | 888 return docinfo |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
889 if 'tocSize_%s'%mode in docinfo: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
890 # cached toc |
126 | 891 return docinfo |
892 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
893 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
894 # 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
|
895 pagesize = 1000 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
896 pn = 1 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
897 if mode == "text": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
898 queryType = "toc" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
899 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
900 queryType = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
901 # number of entries in toc |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
902 tocSize = 0 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
903 tocDiv = None |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
904 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
|
905 # post-processing downloaded xml |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
906 pagedom = Parse(pagexml) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
907 # get number of entries |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
908 numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
909 if len(numdivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
910 tocSize = int(getTextFromNode(numdivs[0])) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
911 docinfo['tocSize_%s'%mode] = tocSize |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
912 return docinfo |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
913 |
128 | 914 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
|
915 """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
|
916 # 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
|
917 if mode == "text": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
918 queryType = "toc" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
919 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
920 queryType = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
921 docpath = docinfo['textURLPath'] |
128 | 922 path = docinfo['textURLPath'] |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
923 pagesize = pageinfo['tocPageSize'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
924 pn = pageinfo['tocPN'] |
101 | 925 url = docinfo['url'] |
96 | 926 selfurl = self.absolute_url() |
927 viewMode= pageinfo['viewMode'] | |
928 tocMode = pageinfo['tocMode'] | |
128 | 929 tocPN = pageinfo['tocPN'] |
95 | 930 pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False) |
101 | 931 page = pagexml.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN)) |
96 | 932 text = page.replace('mode=image','mode=texttool') |
933 return text | |
22 | 934 |
128 | 935 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
22 | 936 """init document viewer""" |
937 self.title=title | |
938 self.digilibBaseUrl = digilibBaseUrl | |
25 | 939 self.thumbrows = thumbrows |
940 self.thumbcols = thumbcols | |
32 | 941 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
22 | 942 if RESPONSE is not None: |
943 RESPONSE.redirect('manage_main') | |
0 | 944 |
945 def manage_AddDocumentViewerForm(self): | |
946 """add the viewer form""" | |
22 | 947 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 948 return pt() |
949 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
950 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 951 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
952 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 953 self._setObject(id,newObj) |
954 | |
955 if RESPONSE is not None: | |
956 RESPONSE.redirect('manage_main') | |
22 | 957 |
958 ## DocumentViewerTemplate class | |
959 class DocumentViewerTemplate(ZopePageTemplate): | |
960 """Template for document viewer""" | |
961 meta_type="DocumentViewer Template" | |
962 | |
963 | |
964 def manage_addDocumentViewerTemplateForm(self): | |
965 """Form for adding""" | |
966 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
967 return pt() | |
968 | |
969 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
970 REQUEST=None, submit=None): | |
971 "Add a Page Template with optional file content." | |
972 | |
973 self._setObject(id, DocumentViewerTemplate(id)) | |
974 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
975 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
|
976 logging.info("txt %s:"%txt) |
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
977 ob.pt_edit(txt,"text/html") |
22 | 978 if title: |
979 ob.pt_setTitle(title) | |
980 try: | |
981 u = self.DestinationURL() | |
982 except AttributeError: | |
983 u = REQUEST['URL1'] | |
984 | |
985 u = "%s/%s" % (u, urllib.quote(id)) | |
986 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
987 return '' | |
988 | |
989 | |
41 | 990 |