Mercurial > hg > documentViewer
annotate documentViewer.py @ 13:3e570be16eea modularisierung
fixed oopsie
author | casties |
---|---|
date | Wed, 16 Jun 2010 20:48:34 +0200 |
parents | 3626bbda5a2d |
children | 38e4af417f34 |
rev | line source |
---|---|
0 | 1 |
2 from OFS.Folder import Folder | |
3 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate | |
2 | 4 from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
0 | 5 from AccessControl import ClassSecurityInfo |
2 | 6 from AccessControl import getSecurityManager |
0 | 7 from Globals import package_home |
8 | |
2 | 9 from Ft.Xml import EMPTY_NAMESPACE, Parse |
13 | 10 from Ft.Xml.Domlette import PrettyPrint, Print |
0 | 11 import os.path |
2 | 12 import sys |
0 | 13 import urllib |
8 | 14 import urllib2 |
2 | 15 import logging |
10 | 16 import math |
17 import urlparse | |
12 | 18 import cStringIO |
2 | 19 |
20 def logger(txt,method,txt2): | |
21 """logging""" | |
22 logging.info(txt+ txt2) | |
23 | |
24 | |
25 def getInt(number, default=0): | |
26 """returns always an int (0 in case of problems)""" | |
27 try: | |
28 return int(number) | |
29 except: | |
30 return int(default) | |
0 | 31 |
32 def getTextFromNode(nodename): | |
2 | 33 """get the cdata content of a node""" |
34 if nodename is None: | |
35 return "" | |
0 | 36 nodelist=nodename.childNodes |
37 rc = "" | |
38 for node in nodelist: | |
39 if node.nodeType == node.TEXT_NODE: | |
40 rc = rc + node.data | |
41 return rc | |
42 | |
2 | 43 def serializeNode(node, encoding='utf-8'): |
44 """returns a string containing node as XML""" | |
45 buf = cStringIO.StringIO() | |
46 Print(node, stream=buf, encoding=encoding) | |
47 s = buf.getvalue() | |
48 buf.close() | |
49 return s | |
50 | |
51 | |
52 def getParentDir(path): | |
53 """returns pathname shortened by one""" | |
54 return '/'.join(path.split('/')[0:-1]) | |
55 | |
56 | |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
57 def getHttpData(url, data=None, num_tries=3, timeout=10): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
58 """returns result from url+data HTTP request""" |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
59 # we do GET (by appending data to url) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
60 if isinstance(data, str) or isinstance(data, unicode): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
61 # if data is string then append |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
62 url = "%s?%s"%(url,data) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
63 elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
64 # urlencode |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
65 url = "%s?%s"%(url,urllib.urlencode(data)) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
66 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
67 response = None |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
68 errmsg = None |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
69 for cnt in range(num_tries): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
70 try: |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
71 logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
72 if sys.version_info < (2, 6): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
73 # set timeout on socket -- ugly :-( |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
74 import socket |
11 | 75 socket.setdefaulttimeout(float(timeout)) |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
76 response = urllib2.urlopen(url) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
77 else: |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
78 response = urllib2.urlopen(url,timeout=float(timeout)) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
79 # check result? |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
80 break |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
81 except urllib2.HTTPError, e: |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
82 logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
83 errmsg = str(e) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
84 # stop trying |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
85 break |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
86 except urllib2.URLError, e: |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
87 logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
88 errmsg = str(e) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
89 # stop trying |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
90 #break |
0 | 91 |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
92 if response is not None: |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
93 data = response.read() |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
94 response.close() |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
95 return data |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
96 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
97 raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
98 #return None |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
99 |
0 | 100 |
101 | |
2 | 102 ## |
103 ## documentViewer class | |
104 ## | |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
105 class documentViewer(Folder): |
0 | 106 """document viewer""" |
107 meta_type="Document viewer" | |
108 | |
109 security=ClassSecurityInfo() | |
2 | 110 manage_options=Folder.manage_options+( |
0 | 111 {'label':'main config','action':'changeDocumentViewerForm'}, |
112 ) | |
113 | |
2 | 114 # templates and forms |
115 viewer_main = PageTemplateFile('zpt/viewer_main', globals()) | |
116 toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) | |
117 toc_text = PageTemplateFile('zpt/toc_text', globals()) | |
118 toc_figures = PageTemplateFile('zpt/toc_figures', globals()) | |
119 page_main_images = PageTemplateFile('zpt/page_main_images', globals()) | |
120 page_main_text = PageTemplateFile('zpt/page_main_text', globals()) | |
121 page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) | |
122 page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) | |
123 head_main = PageTemplateFile('zpt/head_main', globals()) | |
124 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
125 info_xml = PageTemplateFile('zpt/info_xml', globals()) | |
0 | 126 |
2 | 127 |
128 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) | |
129 security.declareProtected('View management screens','changeDocumentViewerForm') | |
130 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
131 | |
132 | |
133 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): | |
0 | 134 """init document viewer""" |
135 self.id=id | |
136 self.title=title | |
2 | 137 self.thumbcols = thumbcols |
138 self.thumbrows = thumbrows | |
139 # authgroups is list of authorized groups (delimited by ,) | |
140 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | |
141 # create template folder so we can always use template.something | |
0 | 142 |
2 | 143 templateFolder = Folder('template') |
144 #self['template'] = templateFolder # Zope-2.12 style | |
145 self._setObject('template',templateFolder) # old style | |
146 try: | |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
147 import MpdlXmlTextServer |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
148 textServer = MpdlXmlTextServer(id='fulltextclient') |
2 | 149 #templateFolder['fulltextclient'] = xmlRpcClient |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
150 templateFolder._setObject('fulltextclient',textServer) |
2 | 151 except Exception, e: |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
152 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
2 | 153 try: |
154 from Products.zogiLib.zogiLib import zogiLib | |
155 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") | |
156 #templateFolder['zogilib'] = zogilib | |
157 templateFolder._setObject('zogilib',zogilib) | |
158 except Exception, e: | |
159 logging.error("Unable to create zogiLib for zogilib: "+str(e)) | |
160 | |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
161 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
162 # proxy text server methods to fulltextclient |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
163 def getTextPage(self, **args): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
164 """get page""" |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
165 return self.template.fulltextclient.getTextPage(**args) |
2 | 166 |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
167 def getQuery(self, **args): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
168 """get query""" |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
169 return self.template.fulltextclient.getQuery(**args) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
170 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
171 def getSearch(self, **args): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
172 """get search""" |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
173 return self.template.fulltextclient.getSearch(**args) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
174 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
175 def getNumPages(self, **args): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
176 """get numpages""" |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
177 return self.template.fulltextclient.getNumPages(**args) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
178 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
179 def getTranslate(self, **args): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
180 """get translate""" |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
181 return self.template.fulltextclient.getTranslate(**args) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
182 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
183 def getLemma(self, **args): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
184 """get lemma""" |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
185 return self.template.fulltextclient.getLemma(**args) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
186 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
187 def getToc(self, **args): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
188 """get toc""" |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
189 return self.template.fulltextclient.getToc(**args) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
190 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
191 def getTocPage(self, **args): |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
192 """get tocpage""" |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
193 return self.template.fulltextclient.getTocPage(**args) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
194 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
195 |
2 | 196 security.declareProtected('View','thumbs_rss') |
197 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
198 ''' | |
199 view it | |
200 @param mode: defines how to access the document behind url | |
201 @param url: url which contains display information | |
202 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
203 | |
204 ''' | |
205 logging.debug("HHHHHHHHHHHHHH:load the rss") | |
206 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) | |
0 | 207 |
2 | 208 if not hasattr(self, 'template'): |
209 # create template folder if it doesn't exist | |
210 self.manage_addFolder('template') | |
211 | |
212 if not self.digilibBaseUrl: | |
213 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
214 | |
215 docinfo = self.getDocinfo(mode=mode,url=url) | |
216 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
217 pt = getattr(self.template, 'thumbs_main_rss') | |
218 | |
219 if viewMode=="auto": # automodus gewaehlt | |
220 if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert | |
221 viewMode="text" | |
222 else: | |
223 viewMode="images" | |
224 | |
225 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
226 | |
227 security.declareProtected('View','index_html') | |
228 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None): | |
229 ''' | |
230 view it | |
231 @param mode: defines how to access the document behind url | |
232 @param url: url which contains display information | |
233 @param viewMode: if images display images, if text display text, default is auto (text,images or auto) | |
234 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) | |
235 @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) | |
236 ''' | |
237 | |
238 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) | |
239 | |
240 if not hasattr(self, 'template'): | |
241 # this won't work | |
242 logging.error("template folder missing!") | |
243 return "ERROR: template folder missing!" | |
244 | |
245 if not getattr(self, 'digilibBaseUrl', None): | |
246 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
247 | |
248 docinfo = self.getDocinfo(mode=mode,url=url) | |
0 | 249 |
250 | |
2 | 251 if tocMode != "thumbs": |
252 # get table of contents | |
253 docinfo = self.getToc(mode=tocMode, docinfo=docinfo) | |
254 | |
255 if viewMode=="auto": # automodus gewaehlt | |
256 if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert | |
257 viewMode="text_dict" | |
258 else: | |
259 viewMode="images" | |
260 | |
261 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) | |
262 | |
263 pt = getattr(self.template, 'viewer_main') | |
264 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) | |
265 | |
266 def generateMarks(self,mk): | |
0 | 267 ret="" |
2 | 268 if mk is None: |
269 return "" | |
270 if type(mk) is not ListType: | |
271 mk=[mk] | |
272 for m in mk: | |
273 ret+="mk=%s"%m | |
274 return ret | |
0 | 275 |
276 | |
2 | 277 def findDigilibUrl(self): |
278 """try to get the digilib URL from zogilib""" | |
279 url = self.template.zogilib.getDLBaseUrl() | |
280 return url | |
281 | |
282 def getDocumentViewerURL(self): | |
283 """returns the URL of this instance""" | |
284 return self.absolute_url() | |
285 | |
286 def getStyle(self, idx, selected, style=""): | |
287 """returns a string with the given style and append 'sel' if path == selected.""" | |
288 #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) | |
289 if idx == selected: | |
290 return style + 'sel' | |
291 else: | |
292 return style | |
293 | |
294 def getLink(self,param=None,val=None): | |
295 """link to documentviewer with parameter param set to val""" | |
296 params=self.REQUEST.form.copy() | |
297 if param is not None: | |
298 if val is None: | |
299 if params.has_key(param): | |
300 del params[param] | |
0 | 301 else: |
2 | 302 params[param] = str(val) |
303 | |
304 if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath | |
305 params["mode"] = "imagepath" | |
306 params["url"] = getParentDir(params["url"]) | |
307 | |
308 # quote values and assemble into query string | |
309 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
310 url=self.REQUEST['URL1']+"?"+ps | |
311 return url | |
312 | |
313 def getLinkAmp(self,param=None,val=None): | |
314 """link to documentviewer with parameter param set to val""" | |
315 params=self.REQUEST.form.copy() | |
316 if param is not None: | |
317 if val is None: | |
318 if params.has_key(param): | |
319 del params[param] | |
320 else: | |
321 params[param] = str(val) | |
322 | |
323 # quote values and assemble into query string | |
4 | 324 logging.debug("XYXXXXX: %s"%repr(params.items())) |
2 | 325 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
326 url=self.REQUEST['URL1']+"?"+ps | |
327 return url | |
328 | |
329 def getInfo_xml(self,url,mode): | |
330 """returns info about the document as XML""" | |
331 | |
332 if not self.digilibBaseUrl: | |
333 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
0 | 334 |
2 | 335 docinfo = self.getDocinfo(mode=mode,url=url) |
336 pt = getattr(self.template, 'info_xml') | |
337 return pt(docinfo=docinfo) | |
338 | |
339 | |
340 def isAccessible(self, docinfo): | |
341 """returns if access to the resource is granted""" | |
342 access = docinfo.get('accessType', None) | |
4 | 343 logging.debug("documentViewer (accessOK) access type %s"%access) |
2 | 344 if access is not None and access == 'free': |
4 | 345 logging.debug("documentViewer (accessOK) access is free") |
2 | 346 return True |
347 elif access is None or access in self.authgroups: | |
348 # only local access -- only logged in users | |
349 user = getSecurityManager().getUser() | |
350 if user is not None: | |
351 #print "user: ", user | |
352 return (user.getUserName() != "Anonymous User") | |
353 else: | |
354 return False | |
0 | 355 |
4 | 356 logging.debug("documentViewer (accessOK) unknown access type %s"%access) |
2 | 357 return False |
0 | 358 |
2 | 359 |
360 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): | |
361 """gibt param von dlInfo aus""" | |
362 if docinfo is None: | |
363 docinfo = {} | |
0 | 364 |
2 | 365 for x in range(cut): |
366 | |
367 path=getParentDir(path) | |
368 | |
369 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path | |
0 | 370 |
4 | 371 logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) |
0 | 372 |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
373 txt = getHttpData(infoUrl) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
374 if txt is None: |
2 | 375 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
376 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
377 dom = Parse(txt) |
2 | 378 sizes=dom.xpath("//dir/size") |
4 | 379 logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) |
0 | 380 |
2 | 381 if sizes: |
382 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
383 else: | |
384 docinfo['numPages'] = 0 | |
385 | |
386 # TODO: produce and keep list of image names and numbers | |
387 | |
388 return docinfo | |
389 | |
390 | |
391 def getIndexMeta(self, url): | |
392 """returns dom of index.meta document at url""" | |
393 dom = None | |
394 metaUrl = None | |
395 if url.startswith("http://"): | |
396 # real URL | |
397 metaUrl = url | |
398 else: | |
399 # online path | |
400 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
401 metaUrl=server+url.replace("/mpiwg/online","") | |
402 if not metaUrl.endswith("index.meta"): | |
403 metaUrl += "/index.meta" | |
404 | |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
405 logging.debug("(getIndexMeta): METAURL: %s"%metaUrl) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
406 txt=getHttpData(metaUrl) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
407 if txt is None: |
2 | 408 raise IOError("Unable to read index meta from %s"%(url)) |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
409 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
410 dom = Parse(txt) |
2 | 411 return dom |
412 | |
413 def getPresentationInfoXML(self, url): | |
414 """returns dom of info.xml document at url""" | |
415 dom = None | |
416 metaUrl = None | |
417 if url.startswith("http://"): | |
418 # real URL | |
419 metaUrl = url | |
420 else: | |
421 # online path | |
422 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
423 metaUrl=server+url.replace("/mpiwg/online","") | |
0 | 424 |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
425 txt=getHttpData(metaUrl) |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
426 if txt is None: |
2 | 427 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
6
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
428 |
3c70a7d2f35b
made extraFunction into separate object MpdlXmlTextServer
casties
parents:
4
diff
changeset
|
429 dom = Parse(txt) |
2 | 430 return dom |
431 | |
0 | 432 |
2 | 433 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
434 """gets authorization info from the index.meta file at path or given by dom""" | |
4 | 435 logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) |
2 | 436 |
437 access = None | |
438 | |
439 if docinfo is None: | |
440 docinfo = {} | |
0 | 441 |
2 | 442 if dom is None: |
443 for x in range(cut): | |
444 path=getParentDir(path) | |
445 dom = self.getIndexMeta(path) | |
446 | |
447 acctype = dom.xpath("//access-conditions/access/@type") | |
448 if acctype and (len(acctype)>0): | |
449 access=acctype[0].value | |
450 if access in ['group', 'institution']: | |
451 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() | |
452 | |
453 docinfo['accessType'] = access | |
454 return docinfo | |
0 | 455 |
2 | 456 |
457 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): | |
458 """gets bibliographical info from the index.meta file at path or given by dom""" | |
459 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) | |
460 | |
461 if docinfo is None: | |
462 docinfo = {} | |
463 | |
464 if dom is None: | |
465 for x in range(cut): | |
466 path=getParentDir(path) | |
467 dom = self.getIndexMeta(path) | |
468 | |
469 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) | |
470 # put in all raw bib fields as dict "bib" | |
471 bib = dom.xpath("//bib/*") | |
472 if bib and len(bib)>0: | |
473 bibinfo = {} | |
474 for e in bib: | |
475 bibinfo[e.localName] = getTextFromNode(e) | |
476 docinfo['bib'] = bibinfo | |
0 | 477 |
2 | 478 # extract some fields (author, title, year) according to their mapping |
479 metaData=self.metadata.main.meta.bib | |
480 bibtype=dom.xpath("//bib/@type") | |
481 if bibtype and (len(bibtype)>0): | |
482 bibtype=bibtype[0].value | |
483 else: | |
484 bibtype="generic" | |
485 | |
486 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) | |
487 docinfo['bib_type'] = bibtype | |
488 bibmap=metaData.generateMappingForType(bibtype) | |
489 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) | |
490 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: | |
491 try: | |
492 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
493 except: pass | |
494 try: | |
495 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
496 except: pass | |
497 try: | |
498 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
499 except: pass | |
500 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) | |
501 try: | |
502 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
503 except: | |
504 docinfo['lang']='' | |
505 | |
506 return docinfo | |
0 | 507 |
508 | |
2 | 509 def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): |
510 """parse texttool tag in index meta""" | |
4 | 511 logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) |
2 | 512 if docinfo is None: |
513 docinfo = {} | |
514 if docinfo.get('lang', None) is None: | |
515 docinfo['lang'] = '' # default keine Sprache gesetzt | |
516 if dom is None: | |
517 dom = self.getIndexMeta(url) | |
518 | |
519 archivePath = None | |
520 archiveName = None | |
521 | |
522 archiveNames = dom.xpath("//resource/name") | |
523 if archiveNames and (len(archiveNames) > 0): | |
524 archiveName = getTextFromNode(archiveNames[0]) | |
525 else: | |
4 | 526 logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) |
2 | 527 |
528 archivePaths = dom.xpath("//resource/archive-path") | |
529 if archivePaths and (len(archivePaths) > 0): | |
530 archivePath = getTextFromNode(archivePaths[0]) | |
531 # clean up archive path | |
532 if archivePath[0] != '/': | |
533 archivePath = '/' + archivePath | |
534 if archiveName and (not archivePath.endswith(archiveName)): | |
535 archivePath += "/" + archiveName | |
536 else: | |
537 # try to get archive-path from url | |
4 | 538 logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url)) |
2 | 539 if (not url.startswith('http')): |
540 archivePath = url.replace('index.meta', '') | |
541 | |
542 if archivePath is None: | |
543 # we balk without archive-path | |
544 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) | |
0 | 545 |
2 | 546 imageDirs = dom.xpath("//texttool/image") |
547 if imageDirs and (len(imageDirs) > 0): | |
548 imageDir = getTextFromNode(imageDirs[0]) | |
549 | |
550 else: | |
551 # we balk with no image tag / not necessary anymore because textmode is now standard | |
552 #raise IOError("No text-tool info in %s"%(url)) | |
553 imageDir = "" | |
554 #xquery="//pb" | |
555 docinfo['imagePath'] = "" # keine Bilder | |
556 docinfo['imageURL'] = "" | |
557 | |
558 if imageDir and archivePath: | |
559 #print "image: ", imageDir, " archivepath: ", archivePath | |
560 imageDir = os.path.join(archivePath, imageDir) | |
561 imageDir = imageDir.replace("/mpiwg/online", '') | |
562 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) | |
563 docinfo['imagePath'] = imageDir | |
564 | |
565 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir | |
566 | |
567 viewerUrls = dom.xpath("//texttool/digiliburlprefix") | |
568 if viewerUrls and (len(viewerUrls) > 0): | |
569 viewerUrl = getTextFromNode(viewerUrls[0]) | |
570 docinfo['viewerURL'] = viewerUrl | |
571 | |
572 textUrls = dom.xpath("//texttool/text") | |
573 if textUrls and (len(textUrls) > 0): | |
574 textUrl = getTextFromNode(textUrls[0]) | |
575 if urlparse.urlparse(textUrl)[0] == "": #keine url | |
576 textUrl = os.path.join(archivePath, textUrl) | |
577 # fix URLs starting with /mpiwg/online | |
578 if textUrl.startswith("/mpiwg/online"): | |
579 textUrl = textUrl.replace("/mpiwg/online", '', 1) | |
580 | |
581 docinfo['textURL'] = textUrl | |
582 | |
583 textUrls = dom.xpath("//texttool/text-url-path") | |
584 if textUrls and (len(textUrls) > 0): | |
585 textUrl = getTextFromNode(textUrls[0]) | |
586 docinfo['textURLPath'] = textUrl | |
587 if not docinfo['imagePath']: | |
588 # text-only, no page images | |
589 docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht | |
590 | |
591 presentationUrls = dom.xpath("//texttool/presentation") | |
592 docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag | |
593 | |
594 if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen | |
595 # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten | |
596 # durch den relativen Pfad auf die presentation infos | |
597 presentationPath = getTextFromNode(presentationUrls[0]) | |
598 if url.endswith("index.meta"): | |
599 presentationUrl = url.replace('index.meta', presentationPath) | |
600 else: | |
601 presentationUrl = url + "/" + presentationPath | |
602 | |
603 docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) | |
0 | 604 |
2 | 605 docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info |
0 | 606 |
2 | 607 return docinfo |
608 | |
609 | |
610 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): | |
611 """gets the bibliographical information from the preseantion entry in texttools | |
612 """ | |
613 dom=self.getPresentationInfoXML(url) | |
614 try: | |
615 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
616 except: | |
617 pass | |
618 try: | |
619 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
620 except: | |
621 pass | |
622 try: | |
623 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
624 except: | |
625 pass | |
626 return docinfo | |
627 | |
628 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): | |
629 """path ist the path to the images it assumes that the index.meta file is one level higher.""" | |
4 | 630 logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) |
2 | 631 if docinfo is None: |
632 docinfo = {} | |
633 path=path.replace("/mpiwg/online","") | |
634 docinfo['imagePath'] = path | |
635 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) | |
636 | |
637 pathorig=path | |
638 for x in range(cut): | |
639 path=getParentDir(path) | |
4 | 640 logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) |
2 | 641 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
642 docinfo['imageURL'] = imageUrl | |
0 | 643 |
2 | 644 #path ist the path to the images it assumes that the index.meta file is one level higher. |
645 docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) | |
646 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) | |
647 return docinfo | |
648 | |
649 | |
650 def getDocinfo(self, mode, url): | |
651 """returns docinfo depending on mode""" | |
4 | 652 logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) |
2 | 653 # look for cached docinfo in session |
654 if self.REQUEST.SESSION.has_key('docinfo'): | |
655 docinfo = self.REQUEST.SESSION['docinfo'] | |
656 # check if its still current | |
657 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
4 | 658 logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) |
2 | 659 return docinfo |
660 # new docinfo | |
661 docinfo = {'mode': mode, 'url': url} | |
662 if mode=="texttool": #index.meta with texttool information | |
663 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
664 elif mode=="imagepath": | |
665 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
666 elif mode=="filepath": | |
667 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) | |
668 else: | |
4 | 669 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
2 | 670 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
671 | |
4 | 672 logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
2 | 673 self.REQUEST.SESSION['docinfo'] = docinfo |
674 return docinfo | |
675 | |
676 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): | |
677 """returns pageinfo with the given parameters""" | |
678 pageinfo = {} | |
679 current = getInt(current) | |
680 pageinfo['current'] = current | |
681 rows = int(rows or self.thumbrows) | |
682 pageinfo['rows'] = rows | |
683 cols = int(cols or self.thumbcols) | |
684 pageinfo['cols'] = cols | |
685 grpsize = cols * rows | |
686 pageinfo['groupsize'] = grpsize | |
687 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) | |
688 # int(current / grpsize) * grpsize +1)) | |
689 pageinfo['start'] = start | |
690 pageinfo['end'] = start + grpsize | |
691 if (docinfo is not None) and ('numPages' in docinfo): | |
692 np = int(docinfo['numPages']) | |
693 pageinfo['end'] = min(pageinfo['end'], np) | |
694 pageinfo['numgroups'] = int(np / grpsize) | |
695 if np % grpsize > 0: | |
696 pageinfo['numgroups'] += 1 | |
697 pageinfo['viewMode'] = viewMode | |
698 pageinfo['tocMode'] = tocMode | |
699 pageinfo['query'] = self.REQUEST.get('query',' ') | |
700 pageinfo['queryType'] = self.REQUEST.get('queryType',' ') | |
701 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') | |
702 pageinfo['textPN'] = self.REQUEST.get('textPN','1') | |
703 pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') | |
704 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') | |
705 pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') | |
706 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') | |
707 toc = int (pageinfo['tocPN']) | |
708 pageinfo['textPages'] =int (toc) | |
0 | 709 |
2 | 710 if 'tocSize_%s'%tocMode in docinfo: |
711 tocSize = int(docinfo['tocSize_%s'%tocMode]) | |
712 tocPageSize = int(pageinfo['tocPageSize']) | |
713 # cached toc | |
714 if tocSize%tocPageSize>0: | |
715 tocPages=tocSize/tocPageSize+1 | |
716 else: | |
717 tocPages=tocSize/tocPageSize | |
718 pageinfo['tocPN'] = min (tocPages,toc) | |
719 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') | |
720 pageinfo['sn'] =self.REQUEST.get('sn','') | |
721 return pageinfo | |
722 | |
723 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): | |
724 """init document viewer""" | |
725 self.title=title | |
726 self.digilibBaseUrl = digilibBaseUrl | |
727 self.thumbrows = thumbrows | |
728 self.thumbcols = thumbcols | |
729 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | |
730 if RESPONSE is not None: | |
731 RESPONSE.redirect('manage_main') | |
732 | |
0 | 733 def manage_AddDocumentViewerForm(self): |
734 """add the viewer form""" | |
2 | 735 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 736 return pt() |
737 | |
2 | 738 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 739 """add the viewer""" |
2 | 740 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 741 self._setObject(id,newObj) |
742 | |
743 if RESPONSE is not None: | |
744 RESPONSE.redirect('manage_main') | |
2 | 745 |
746 ## DocumentViewerTemplate class | |
747 class DocumentViewerTemplate(ZopePageTemplate): | |
748 """Template for document viewer""" | |
749 meta_type="DocumentViewer Template" | |
750 | |
751 | |
752 def manage_addDocumentViewerTemplateForm(self): | |
753 """Form for adding""" | |
754 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
755 return pt() | |
756 | |
757 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
758 REQUEST=None, submit=None): | |
759 "Add a Page Template with optional file content." | |
760 | |
761 self._setObject(id, DocumentViewerTemplate(id)) | |
762 ob = getattr(self, id) | |
763 txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() | |
764 logging.info("txt %s:"%txt) | |
765 ob.pt_edit(txt,"text/html") | |
766 if title: | |
767 ob.pt_setTitle(title) | |
768 try: | |
769 u = self.DestinationURL() | |
770 except AttributeError: | |
771 u = REQUEST['URL1'] | |
772 | |
773 u = "%s/%s" % (u, urllib.quote(id)) | |
774 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
775 return '' | |
776 | |
777 | |
778 |