Mercurial > hg > documentViewer
annotate documentViewer.py @ 123:000529eb4058
pureXml
author | abukhman |
---|---|
date | Tue, 01 Jun 2010 15:28:35 +0200 |
parents | f1fc821f88a9 |
children | 10d10e0db919 |
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 |
198 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) | |
199 | |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
200 if viewMode=="auto": # automodus gewaehlt |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
201 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
|
202 viewMode="text" |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
203 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
204 viewMode="images" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
205 |
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 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
224 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
225 def getStyle(self, idx, selected, style=""): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
226 """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
|
227 #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
|
228 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
229 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
230 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
231 return style |
74 | 232 |
25 | 233 def getLink(self,param=None,val=None): |
234 """link to documentviewer with parameter param set to val""" | |
35 | 235 params=self.REQUEST.form.copy() |
25 | 236 if param is not None: |
31 | 237 if val is None: |
238 if params.has_key(param): | |
239 del params[param] | |
25 | 240 else: |
35 | 241 params[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
242 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
243 if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
78 | 244 params["mode"] = "imagepath" |
245 params["url"] = getParentDir(params["url"]) | |
31 | 246 |
35 | 247 # quote values and assemble into query string |
248 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
249 url=self.REQUEST['URL1']+"?"+ps | |
25 | 250 return url |
251 | |
68 | 252 def getLinkAmp(self,param=None,val=None): |
253 """link to documentviewer with parameter param set to val""" | |
254 params=self.REQUEST.form.copy() | |
255 if param is not None: | |
256 if val is None: | |
257 if params.has_key(param): | |
258 del params[param] | |
259 else: | |
260 params[param] = str(val) | |
261 | |
262 # quote values and assemble into query string | |
263 logging.info("XYXXXXX: %s"%repr(params.items())) | |
264 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
265 url=self.REQUEST['URL1']+"?"+ps | |
266 return url | |
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
267 |
57 | 268 def getInfo_xml(self,url,mode): |
269 """returns info about the document as XML""" | |
270 | |
271 if not self.digilibBaseUrl: | |
272 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
273 | |
274 docinfo = self.getDocinfo(mode=mode,url=url) | |
275 pt = getattr(self.template, 'info_xml') | |
276 return pt(docinfo=docinfo) | |
277 | |
0 | 278 |
35 | 279 def isAccessible(self, docinfo): |
32 | 280 """returns if access to the resource is granted""" |
281 access = docinfo.get('accessType', None) | |
52 | 282 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
45 | 283 if access is not None and access == 'free': |
52 | 284 logger("documentViewer (accessOK)", logging.INFO, "access is free") |
32 | 285 return True |
45 | 286 elif access is None or access in self.authgroups: |
35 | 287 # only local access -- only logged in users |
288 user = getSecurityManager().getUser() | |
289 if user is not None: | |
290 #print "user: ", user | |
291 return (user.getUserName() != "Anonymous User") | |
292 else: | |
293 return False | |
32 | 294 |
52 | 295 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
32 | 296 return False |
35 | 297 |
32 | 298 |
73 | 299 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
29 | 300 """gibt param von dlInfo aus""" |
40 | 301 num_retries = 3 |
31 | 302 if docinfo is None: |
303 docinfo = {} | |
73 | 304 |
305 for x in range(cut): | |
78 | 306 |
73 | 307 path=getParentDir(path) |
78 | 308 |
40 | 309 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 310 |
52 | 311 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
29 | 312 |
40 | 313 for cnt in range(num_retries): |
35 | 314 try: |
40 | 315 # dom = NonvalidatingReader.parseUri(imageUrl) |
316 txt=urllib.urlopen(infoUrl).read() | |
317 dom = Parse(txt) | |
35 | 318 break |
319 except: | |
52 | 320 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
35 | 321 else: |
40 | 322 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
29 | 323 |
37 | 324 sizes=dom.xpath("//dir/size") |
52 | 325 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
29 | 326 |
37 | 327 if sizes: |
328 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
31 | 329 else: |
330 docinfo['numPages'] = 0 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
331 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
332 # TODO: produce and keep list of image names and numbers |
31 | 333 |
334 return docinfo | |
32 | 335 |
29 | 336 |
35 | 337 def getIndexMeta(self, url): |
338 """returns dom of index.meta document at url""" | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
339 num_retries = 3 |
35 | 340 dom = None |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
341 metaUrl = None |
35 | 342 if url.startswith("http://"): |
343 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
344 metaUrl = url |
35 | 345 else: |
346 # online path | |
347 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 348 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 349 if not metaUrl.endswith("index.meta"): |
350 metaUrl += "/index.meta" | |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
351 logging.debug("METAURL: %s"%metaUrl) |
40 | 352 for cnt in range(num_retries): |
35 | 353 try: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
354 # patch dirk encoding fehler treten dann nicht mehr auf |
38 | 355 # dom = NonvalidatingReader.parseUri(metaUrl) |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
356 txt=urllib.urlopen(metaUrl).read() |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
357 dom = Parse(txt) |
40 | 358 break |
35 | 359 except: |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
360 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
|
361 |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
362 if dom is None: |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
363 raise IOError("Unable to read index meta from %s"%(url)) |
35 | 364 |
365 return dom | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
366 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
367 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
368 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
369 num_retries = 3 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
370 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
371 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
372 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
373 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
374 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
375 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
376 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
377 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
378 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
379 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
380 for cnt in range(num_retries): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
381 try: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
382 # patch dirk encoding fehler treten dann nicht mehr auf |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
383 # dom = NonvalidatingReader.parseUri(metaUrl) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
384 txt=urllib.urlopen(metaUrl).read() |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
385 dom = Parse(txt) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
386 break |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
387 except: |
52 | 388 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
|
389 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
390 if dom is None: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
391 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
392 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
393 return dom |
35 | 394 |
395 | |
70 | 396 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 397 """gets authorization info from the index.meta file at path or given by dom""" |
52 | 398 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
32 | 399 |
400 access = None | |
401 | |
402 if docinfo is None: | |
403 docinfo = {} | |
404 | |
405 if dom is None: | |
78 | 406 for x in range(cut): |
70 | 407 path=getParentDir(path) |
408 dom = self.getIndexMeta(path) | |
46 | 409 |
32 | 410 acctype = dom.xpath("//access-conditions/access/@type") |
411 if acctype and (len(acctype)>0): | |
412 access=acctype[0].value | |
35 | 413 if access in ['group', 'institution']: |
32 | 414 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
415 | |
416 docinfo['accessType'] = access | |
417 return docinfo | |
29 | 418 |
32 | 419 |
70 | 420 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 421 """gets bibliographical info from the index.meta file at path or given by dom""" |
59 | 422 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 423 |
22 | 424 if docinfo is None: |
425 docinfo = {} | |
78 | 426 |
22 | 427 if dom is None: |
78 | 428 for x in range(cut): |
70 | 429 path=getParentDir(path) |
430 dom = self.getIndexMeta(path) | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
431 |
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
432 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
59 | 433 # put in all raw bib fields as dict "bib" |
434 bib = dom.xpath("//bib/*") | |
435 if bib and len(bib)>0: | |
436 bibinfo = {} | |
437 for e in bib: | |
438 bibinfo[e.localName] = getTextFromNode(e) | |
439 docinfo['bib'] = bibinfo | |
440 | |
441 # extract some fields (author, title, year) according to their mapping | |
25 | 442 metaData=self.metadata.main.meta.bib |
443 bibtype=dom.xpath("//bib/@type") | |
444 if bibtype and (len(bibtype)>0): | |
445 bibtype=bibtype[0].value | |
20 | 446 else: |
25 | 447 bibtype="generic" |
59 | 448 |
25 | 449 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
59 | 450 docinfo['bib_type'] = bibtype |
25 | 451 bibmap=metaData.generateMappingForType(bibtype) |
32 | 452 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
31 | 453 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
63 | 454 try: |
455 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
456 except: pass | |
457 try: | |
458 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
459 except: pass | |
460 try: | |
461 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
462 except: pass | |
59 | 463 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
52 | 464 try: |
465 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
466 except: | |
467 docinfo['lang']='' | |
59 | 468 |
22 | 469 return docinfo |
83 | 470 |
471 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
472 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
|
473 """parse texttool tag in index meta""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
474 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
|
475 if docinfo is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
476 docinfo = {} |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
477 if docinfo.get('lang', None) is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
478 docinfo['lang'] = '' # default keine Sprache gesetzt |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
479 if dom is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
480 dom = self.getIndexMeta(url) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
481 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
482 archivePath = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
483 archiveName = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
484 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
485 archiveNames = dom.xpath("//resource/name") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
486 if archiveNames and (len(archiveNames) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
487 archiveName = getTextFromNode(archiveNames[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
488 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
489 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
|
490 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
491 archivePaths = dom.xpath("//resource/archive-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
492 if archivePaths and (len(archivePaths) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
493 archivePath = getTextFromNode(archivePaths[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
494 # clean up archive path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
495 if archivePath[0] != '/': |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
496 archivePath = '/' + archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
497 if archiveName and (not archivePath.endswith(archiveName)): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
498 archivePath += "/" + archiveName |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
499 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
500 # try to get archive-path from url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
501 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
|
502 if (not url.startswith('http')): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
503 archivePath = url.replace('index.meta', '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
504 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
505 if archivePath is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
506 # we balk without archive-path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
507 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
22 | 508 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
509 imageDirs = dom.xpath("//texttool/image") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
510 if imageDirs and (len(imageDirs) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
511 imageDir = getTextFromNode(imageDirs[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
512 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
513 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
514 # 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
|
515 #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
|
516 imageDir = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
517 #xquery="//pb" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
518 docinfo['imagePath'] = "" # keine Bilder |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
519 docinfo['imageURL'] = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
520 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
521 if imageDir and archivePath: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
522 #print "image: ", imageDir, " archivepath: ", archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
523 imageDir = os.path.join(archivePath, imageDir) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
524 imageDir = imageDir.replace("/mpiwg/online", '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
525 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
526 docinfo['imagePath'] = imageDir |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
527 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
528 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
|
529 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
530 viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
531 if viewerUrls and (len(viewerUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
532 viewerUrl = getTextFromNode(viewerUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
533 docinfo['viewerURL'] = viewerUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
534 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
535 textUrls = dom.xpath("//texttool/text") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
536 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
537 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
538 if urlparse.urlparse(textUrl)[0] == "": #keine url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
539 textUrl = os.path.join(archivePath, textUrl) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
540 # fix URLs starting with /mpiwg/online |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
541 if textUrl.startswith("/mpiwg/online"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
542 textUrl = textUrl.replace("/mpiwg/online", '', 1) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
543 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
544 docinfo['textURL'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
545 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
546 textUrls = dom.xpath("//texttool/text-url-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
547 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
548 textUrl = getTextFromNode(textUrls[0]) |
102 | 549 docinfo['textURLPath'] = textUrl |
550 if not docinfo['imagePath']: | |
551 # text-only, no page images | |
552 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
|
553 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
554 presentationUrls = dom.xpath("//texttool/presentation") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
555 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
|
556 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
557 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
|
558 # 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
|
559 # 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
|
560 presentationPath = getTextFromNode(presentationUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
561 if url.endswith("index.meta"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
562 presentationUrl = url.replace('index.meta', presentationPath) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
563 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
564 presentationUrl = url + "/" + presentationPath |
102 | 565 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
566 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
|
567 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
568 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
|
569 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
570 return docinfo |
22 | 571 |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
572 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
573 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
574 """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
|
575 """ |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
576 dom=self.getPresentationInfoXML(url) |
62 | 577 try: |
578 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
579 except: | |
580 pass | |
581 try: | |
582 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
583 except: | |
584 pass | |
585 try: | |
586 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
587 except: | |
588 pass | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
589 return docinfo |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
590 |
70 | 591 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
22 | 592 """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
52 | 593 logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
22 | 594 if docinfo is None: |
595 docinfo = {} | |
29 | 596 path=path.replace("/mpiwg/online","") |
22 | 597 docinfo['imagePath'] = path |
73 | 598 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
78 | 599 |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
600 pathorig=path |
78 | 601 for x in range(cut): |
602 path=getParentDir(path) | |
603 logging.error("PATH:"+path) | |
31 | 604 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
22 | 605 docinfo['imageURL'] = imageUrl |
606 | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
607 #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
|
608 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
|
609 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
22 | 610 return docinfo |
20 | 611 |
22 | 612 |
613 def getDocinfo(self, mode, url): | |
614 """returns docinfo depending on mode""" | |
52 | 615 logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
22 | 616 # look for cached docinfo in session |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
617 if self.REQUEST.SESSION.has_key('docinfo'): |
22 | 618 docinfo = self.REQUEST.SESSION['docinfo'] |
619 # check if its still current | |
620 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
52 | 621 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
22 | 622 return docinfo |
623 # new docinfo | |
624 docinfo = {'mode': mode, 'url': url} | |
625 if mode=="texttool": #index.meta with texttool information | |
626 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
627 elif mode=="imagepath": | |
628 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
70 | 629 elif mode=="filepath": |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
630 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
22 | 631 else: |
52 | 632 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
|
633 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
37 | 634 |
52 | 635 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
22 | 636 self.REQUEST.SESSION['docinfo'] = docinfo |
637 return docinfo | |
20 | 638 |
639 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
640 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): |
22 | 641 """returns pageinfo with the given parameters""" |
642 pageinfo = {} | |
25 | 643 current = getInt(current) |
644 pageinfo['current'] = current | |
645 rows = int(rows or self.thumbrows) | |
646 pageinfo['rows'] = rows | |
647 cols = int(cols or self.thumbcols) | |
648 pageinfo['cols'] = cols | |
649 grpsize = cols * rows | |
650 pageinfo['groupsize'] = grpsize | |
61 | 651 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
652 # int(current / grpsize) * grpsize +1)) | |
22 | 653 pageinfo['start'] = start |
25 | 654 pageinfo['end'] = start + grpsize |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
655 if (docinfo is not None) and ('numPages' in docinfo): |
25 | 656 np = int(docinfo['numPages']) |
657 pageinfo['end'] = min(pageinfo['end'], np) | |
658 pageinfo['numgroups'] = int(np / grpsize) | |
659 if np % grpsize > 0: | |
660 pageinfo['numgroups'] += 1 | |
99 | 661 |
112 | 662 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
663 pageinfo['viewMode'] = viewMode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
664 pageinfo['tocMode'] = tocMode |
95 | 665 pageinfo['query'] = self.REQUEST.get('query',' ') |
666 pageinfo['queryType'] = self.REQUEST.get('queryType',' ') | |
667 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') | |
99 | 668 pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
106 | 669 pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
95 | 670 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
105 | 671 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
|
672 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
99 | 673 toc = int (pageinfo['tocPN']) |
674 pageinfo['textPages'] =int (toc) | |
675 | |
676 if 'tocSize_%s'%tocMode in docinfo: | |
677 tocSize = int(docinfo['tocSize_%s'%tocMode]) | |
678 tocPageSize = int(pageinfo['tocPageSize']) | |
97 | 679 # cached toc |
99 | 680 |
681 if tocSize%tocPageSize>0: | |
682 tocPages=tocSize/tocPageSize+1 | |
683 else: | |
684 tocPages=tocSize/tocPageSize | |
685 pageinfo['tocPN'] = min (tocPages,toc) | |
686 | |
95 | 687 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
112 | 688 pageinfo['sn'] =self.REQUEST.get('sn','') |
78 | 689 |
22 | 690 return pageinfo |
691 | |
95 | 692 def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None): |
693 """get search list""" | |
694 docpath = docinfo['textURLPath'] | |
101 | 695 url = docinfo['url'] |
696 logging.debug("documentViewer (gettoc) docpath: %s"%(docpath)) | |
697 logging.debug("documentViewer (gettoc) url: %s"%(url)) | |
95 | 698 pagesize = pageinfo['queryPageSize'] |
699 pn = pageinfo['searchPN'] | |
700 sn = pageinfo['sn'] | |
106 | 701 highlightQuery = pageinfo['highlightQuery'] |
95 | 702 query =pageinfo['query'] |
703 queryType =pageinfo['queryType'] | |
96 | 704 viewMode= pageinfo['viewMode'] |
705 tocMode = pageinfo['tocMode'] | |
706 tocPN = pageinfo['tocPN'] | |
100 | 707 selfurl = self.absolute_url() |
107 | 708 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 | 709 pagexml = page.replace('?document=%s'%str(docpath),'?url=%s'%url) |
95 | 710 pagedom = Parse(pagexml) |
100 | 711 if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"): |
712 pagedivs = pagedom.xpath("//div[@class='queryResultPage']") | |
713 if len(pagedivs)>0: | |
714 pagenode=pagedivs[0] | |
715 links=pagenode.xpath("//a") | |
716 for l in links: | |
717 hrefNode = l.getAttributeNodeNS(None, u"href") | |
718 if hrefNode: | |
719 href = hrefNode.nodeValue | |
720 if href.startswith('page-fragment.xql'): | |
112 | 721 selfurl = self.absolute_url() |
100 | 722 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 | 723 hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
100 | 724 return serializeNode(pagenode) |
97 | 725 |
100 | 726 if (queryType=="fulltextMorph"): |
727 pagedivs = pagedom.xpath("//div[@class='queryResult']") | |
728 if len(pagedivs)>0: | |
729 pagenode=pagedivs[0] | |
730 links=pagenode.xpath("//a") | |
731 for l in links: | |
732 hrefNode = l.getAttributeNodeNS(None, u"href") | |
733 if hrefNode: | |
734 href = hrefNode.nodeValue | |
735 if href.startswith('page-fragment.xql'): | |
736 selfurl = self.absolute_url() | |
737 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)) | |
738 hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) | |
739 if href.startswith('../lt/lemma.xql'): | |
117 | 740 |
741 hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl) | |
100 | 742 l.setAttributeNS(None, 'target', '_blank') |
743 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") | |
117 | 744 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
745 pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']") | |
100 | 746 return serializeNode(pagenode) |
97 | 747 |
99 | 748 if (queryType=="ftIndex")or(queryType=="ftIndexMorph"): |
749 pagedivs= pagedom.xpath("//div[@class='queryResultPage']") | |
750 if len(pagedivs)>0: | |
751 pagenode=pagedivs[0] | |
752 links=pagenode.xpath("//a") | |
753 for l in links: | |
754 hrefNode = l.getAttributeNodeNS(None, u"href") | |
755 if hrefNode: | |
756 href = hrefNode.nodeValue | |
100 | 757 hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn)) |
758 | |
99 | 759 if href.startswith('../lt/lex.xql'): |
106 | 760 hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl) |
99 | 761 l.setAttributeNS(None, 'target', '_blank') |
100 | 762 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") |
99 | 763 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
764 if href.startswith('../lt/lemma.xql'): | |
106 | 765 hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl) |
99 | 766 l.setAttributeNS(None, 'target', '_blank') |
100 | 767 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") |
99 | 768 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
100 | 769 return serializeNode(pagenode) |
101 | 770 return "no text here" |
97 | 771 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
772 def getNumPages(self,docinfo=None): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
773 """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
|
774 xquery = '//pb' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
775 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
|
776 # 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
|
777 docinfo['numPages'] = text.count("<pb ") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
778 return docinfo |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
779 |
120 | 780 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
|
781 """returns single page from fulltext""" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
782 docpath = docinfo['textURLPath'] |
112 | 783 path = docinfo['textURLPath'] |
784 url = docinfo['url'] | |
785 viewMode= pageinfo['viewMode'] | |
786 tocMode = pageinfo['tocMode'] | |
787 tocPN = pageinfo['tocPN'] | |
788 selfurl = self.absolute_url() | |
789 | |
790 #pn = pageinfo['searchPN'] | |
791 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
792 if mode == "text_dict": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
793 textmode = "textPollux" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
794 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
795 textmode = mode |
112 | 796 |
797 textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn) | |
798 if highlightQuery is not None: | |
799 textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn) | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
800 |
112 | 801 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
|
802 pagedom = Parse(pagexml) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
803 # plain text mode |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
804 if mode == "text": |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
805 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
806 pagedivs = pagedom.xpath("/div") |
95 | 807 #queryResultPage |
112 | 808 if len(pagedivs) > 0: |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
809 pagenode = pagedivs[0] |
103 | 810 links = pagenode.xpath("//a") |
811 for l in links: | |
812 hrefNode = l.getAttributeNodeNS(None, u"href") | |
112 | 813 |
103 | 814 if hrefNode: |
815 href= hrefNode.nodeValue | |
112 | 816 if href.startswith('#note-'): |
817 hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) | |
818 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
819 return serializeNode(pagenode) |
99 | 820 if mode == "xml": |
821 # first div contains text | |
822 pagedivs = pagedom.xpath("/div") | |
823 if len(pagedivs) > 0: | |
824 pagenode = pagedivs[0] | |
825 return serializeNode(pagenode) | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
826 # text-with-links mode |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
827 if mode == "text_dict": |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
828 # first div contains text |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
829 pagedivs = pagedom.xpath("/div") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
830 if len(pagedivs) > 0: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
831 pagenode = pagedivs[0] |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
832 # check all a-tags |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
833 links = pagenode.xpath("//a") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
834 for l in links: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
835 hrefNode = l.getAttributeNodeNS(None, u"href") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
836 if hrefNode: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
837 # is link with href |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
838 href = hrefNode.nodeValue |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
839 if href.startswith('lt/lex.xql'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
840 # is pollux link |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
841 selfurl = self.absolute_url() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
842 # change href |
96 | 843 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
|
844 # add target |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
845 l.setAttributeNS(None, 'target', '_blank') |
99 | 846 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") |
847 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
96 | 848 |
849 if href.startswith('lt/lemma.xql'): | |
850 selfurl = self.absolute_url() | |
851 hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) | |
852 l.setAttributeNS(None, 'target', '_blank') | |
99 | 853 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") |
854 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
112 | 855 |
856 if href.startswith('#note-'): | |
857 hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) | |
858 | |
859 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
860 return serializeNode(pagenode) |
0 | 861 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
862 return "no text here" |
22 | 863 |
96 | 864 def getTranslate(self, query=None, language=None): |
865 """translate into another languages""" | |
101 | 866 pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) |
96 | 867 return pagexml |
868 | |
97 | 869 def getLemma(self, lemma=None, language=None): |
99 | 870 """simular words lemma """ |
101 | 871 pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) |
872 #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False) | |
96 | 873 return pagexml |
874 | |
97 | 875 def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1): |
876 """number of""" | |
877 docpath = docinfo['textURLPath'] | |
878 pagesize = pageinfo['queryPageSize'] | |
879 pn = pageinfo['searchPN'] | |
880 query =pageinfo['query'] | |
881 queryType =pageinfo['queryType'] | |
882 | |
883 tocSearch = 0 | |
884 tocDiv = None | |
885 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) | |
886 | |
887 pagedom = Parse(pagexml) | |
888 numdivs = pagedom.xpath("//div[@class='queryResultHits']") | |
889 tocSearch = int(getTextFromNode(numdivs[0])) | |
105 | 890 tc=int((tocSearch/10)+1) |
97 | 891 logging.debug("documentViewer (gettoc) tc: %s"%(tc)) |
892 return tc | |
893 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
894 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
|
895 """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
|
896 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
|
897 if 'tocSize_%s'%mode in docinfo: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
898 # cached toc |
97 | 899 return docinfo |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
900 docpath = docinfo['textURLPath'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
901 # 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
|
902 pagesize = 1000 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
903 pn = 1 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
904 if mode == "text": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
905 queryType = "toc" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
906 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
907 queryType = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
908 # number of entries in toc |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
909 tocSize = 0 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
910 tocDiv = None |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
911 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
|
912 # post-processing downloaded xml |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
913 pagedom = Parse(pagexml) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
914 # get number of entries |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
915 numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
916 if len(numdivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
917 tocSize = int(getTextFromNode(numdivs[0])) |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
918 # div contains text |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
919 #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
920 #if len(pagedivs) > 0: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
921 # tocDiv = pagedivs[0] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
922 |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
923 docinfo['tocSize_%s'%mode] = tocSize |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
924 #docinfo['tocDiv_%s'%mode] = tocDiv |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
925 return docinfo |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
926 |
95 | 927 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
|
928 """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
|
929 # 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
|
930 if mode == "text": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
931 queryType = "toc" |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
932 else: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
933 queryType = mode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
934 docpath = docinfo['textURLPath'] |
101 | 935 path = docinfo['textURLPath'] |
936 #logging.debug("documentViewer (gettoc) pathNomer: %s"%(pathNomer)) | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
937 pagesize = pageinfo['tocPageSize'] |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
938 pn = pageinfo['tocPN'] |
101 | 939 url = docinfo['url'] |
96 | 940 selfurl = self.absolute_url() |
941 viewMode= pageinfo['viewMode'] | |
942 tocMode = pageinfo['tocMode'] | |
943 tocPN = pageinfo['tocPN'] | |
944 | |
95 | 945 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 | 946 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 | 947 text = page.replace('mode=image','mode=texttool') |
948 return text | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
949 # post-processing downloaded xml |
96 | 950 #pagedom = Parse(text) |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
951 # div contains text |
96 | 952 #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
953 #if len(pagedivs) > 0: | |
954 # pagenode = pagedivs[0] | |
955 # return serializeNode(pagenode) | |
956 #else: | |
957 # return "No TOC!" | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
958 |
22 | 959 |
95 | 960 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
22 | 961 """init document viewer""" |
962 self.title=title | |
963 self.digilibBaseUrl = digilibBaseUrl | |
25 | 964 self.thumbrows = thumbrows |
965 self.thumbcols = thumbcols | |
32 | 966 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
22 | 967 if RESPONSE is not None: |
968 RESPONSE.redirect('manage_main') | |
0 | 969 |
970 | |
971 | |
972 def manage_AddDocumentViewerForm(self): | |
973 """add the viewer form""" | |
22 | 974 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 975 return pt() |
976 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
977 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 978 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
979 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 980 self._setObject(id,newObj) |
981 | |
982 if RESPONSE is not None: | |
983 RESPONSE.redirect('manage_main') | |
22 | 984 |
985 | |
986 ## | |
987 ## DocumentViewerTemplate class | |
988 ## | |
989 class DocumentViewerTemplate(ZopePageTemplate): | |
990 """Template for document viewer""" | |
991 meta_type="DocumentViewer Template" | |
992 | |
993 | |
994 def manage_addDocumentViewerTemplateForm(self): | |
995 """Form for adding""" | |
996 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
997 return pt() | |
998 | |
999 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
1000 REQUEST=None, submit=None): | |
1001 "Add a Page Template with optional file content." | |
1002 | |
1003 self._setObject(id, DocumentViewerTemplate(id)) | |
1004 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
1005 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
|
1006 logging.info("txt %s:"%txt) |
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
1007 ob.pt_edit(txt,"text/html") |
22 | 1008 if title: |
1009 ob.pt_setTitle(title) | |
1010 try: | |
1011 u = self.DestinationURL() | |
1012 except AttributeError: | |
1013 u = REQUEST['URL1'] | |
1014 | |
1015 u = "%s/%s" % (u, urllib.quote(id)) | |
1016 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
1017 return '' | |
1018 | |
1019 | |
41 | 1020 |