Mercurial > hg > documentViewer
annotate documentViewer.py @ 57:7cdb0fc34a92
added getInfo_xml method
| author | casties |
|---|---|
| date | Fri, 04 May 2007 15:17:02 +0200 |
| parents | ba8917b93c84 |
| children | 996b61d71351 |
| rev | line source |
|---|---|
| 46 | 1 |
| 2 | |
| 0 | 3 from OFS.Folder import Folder |
| 4 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate | |
| 52 | 5 from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
| 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 |
| 14 import Ft.Xml.XPath | |
| 15 | |
| 16 import os.path | |
| 31 | 17 import sys |
| 0 | 18 import cgi |
| 19 import urllib | |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
20 import logging |
| 52 | 21 |
| 46 | 22 import urlparse |
| 0 | 23 |
| 52 | 24 def logger(txt,method,txt2): |
| 25 """logging""" | |
| 26 logging.info(txt+ txt2) | |
| 27 | |
| 28 | |
| 25 | 29 def getInt(number, default=0): |
| 30 """returns always an int (0 in case of problems)""" | |
| 31 try: | |
| 32 return int(number) | |
| 33 except: | |
| 34 return default | |
| 35 | |
| 0 | 36 def getTextFromNode(nodename): |
| 46 | 37 """get the cdata content of a node""" |
| 32 | 38 if nodename is None: |
| 39 return "" | |
| 0 | 40 nodelist=nodename.childNodes |
| 41 rc = "" | |
| 42 for node in nodelist: | |
| 43 if node.nodeType == node.TEXT_NODE: | |
| 44 rc = rc + node.data | |
| 45 return rc | |
| 46 | |
| 35 | 47 |
| 48 def getParentDir(path): | |
| 49 """returns pathname shortened by one""" | |
| 50 return '/'.join(path.split('/')[0:-1]) | |
| 51 | |
| 52 | |
| 0 | 53 import socket |
| 54 | |
| 32 | 55 def urlopen(url,timeout=2): |
| 0 | 56 """urlopen mit timeout""" |
| 32 | 57 socket.setdefaulttimeout(timeout) |
| 0 | 58 ret=urllib.urlopen(url) |
| 59 socket.setdefaulttimeout(5) | |
| 60 return ret | |
| 61 | |
| 62 | |
| 22 | 63 ## |
| 64 ## documentViewer class | |
| 65 ## | |
| 66 class documentViewer(Folder): | |
| 0 | 67 """document viewer""" |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
68 #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" |
| 46 | 69 |
| 0 | 70 meta_type="Document viewer" |
| 71 | |
| 72 security=ClassSecurityInfo() | |
| 22 | 73 manage_options=Folder.manage_options+( |
| 0 | 74 {'label':'main config','action':'changeDocumentViewerForm'}, |
| 75 ) | |
| 76 | |
| 22 | 77 # templates and forms |
| 78 viewer_main = PageTemplateFile('zpt/viewer_main', globals()) | |
| 79 thumbs_main = PageTemplateFile('zpt/thumbs_main', globals()) | |
| 80 image_main = PageTemplateFile('zpt/image_main', globals()) | |
| 81 head_main = PageTemplateFile('zpt/head_main', globals()) | |
| 82 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
| 57 | 83 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
| 22 | 84 |
| 85 security.declareProtected('View management screens','changeDocumentViewerForm') | |
| 86 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 87 | |
| 0 | 88 |
| 46 | 89 def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): |
| 0 | 90 """init document viewer""" |
| 91 self.id=id | |
| 92 self.title=title | |
| 93 self.imageViewerUrl=imageViewerUrl | |
| 46 | 94 self.textViewerUrl=textViewerUrl |
| 95 | |
| 25 | 96 if not digilibBaseUrl: |
| 22 | 97 self.digilibBaseUrl = self.findDigilibUrl() |
| 25 | 98 else: |
| 99 self.digilibBaseUrl = digilibBaseUrl | |
| 100 self.thumbcols = thumbcols | |
| 101 self.thumbrows = thumbrows | |
| 32 | 102 # authgroups is list of authorized groups (delimited by ,) |
| 103 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | |
| 22 | 104 # add template folder so we can always use template.something |
| 105 self.manage_addFolder('template') | |
| 106 | |
| 107 | |
| 108 security.declareProtected('View','index_html') | |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
109 def index_html(self,mode,url,viewMode="auto",start=None,pn=1): |
| 22 | 110 ''' |
| 111 view it | |
| 57 | 112 @param mode: defines how to access the document behind url |
| 22 | 113 @param url: url which contains display information |
| 57 | 114 @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
| 46 | 115 |
| 22 | 116 ''' |
| 0 | 117 |
| 52 | 118 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| 22 | 119 |
| 120 if not hasattr(self, 'template'): | |
| 121 # create template folder if it doesn't exist | |
| 122 self.manage_addFolder('template') | |
| 123 | |
| 124 if not self.digilibBaseUrl: | |
| 125 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 126 | |
| 25 | 127 docinfo = self.getDocinfo(mode=mode,url=url) |
| 128 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
| 22 | 129 pt = getattr(self.template, 'viewer_main') |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
130 |
|
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
131 if viewMode=="auto": # automodus gewaehlt |
|
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
132 if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert |
|
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
133 viewMode="text" |
|
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
134 else: |
|
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
135 viewMode="images" |
| 52 | 136 |
| 46 | 137 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
| 0 | 138 |
| 139 | |
| 25 | 140 def getLink(self,param=None,val=None): |
| 141 """link to documentviewer with parameter param set to val""" | |
| 35 | 142 params=self.REQUEST.form.copy() |
| 25 | 143 if param is not None: |
| 31 | 144 if val is None: |
| 145 if params.has_key(param): | |
| 146 del params[param] | |
| 25 | 147 else: |
| 35 | 148 params[param] = str(val) |
| 31 | 149 |
| 35 | 150 # quote values and assemble into query string |
| 151 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
| 152 url=self.REQUEST['URL1']+"?"+ps | |
| 25 | 153 return url |
| 154 | |
| 57 | 155 |
| 156 def getInfo_xml(self,url,mode): | |
| 157 """returns info about the document as XML""" | |
| 158 | |
| 159 if not self.digilibBaseUrl: | |
| 160 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 161 | |
| 162 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 163 pt = getattr(self.template, 'info_xml') | |
| 164 return pt(docinfo=docinfo) | |
| 165 | |
| 0 | 166 |
| 22 | 167 def getStyle(self, idx, selected, style=""): |
| 25 | 168 """returns a string with the given style and append 'sel' if path == selected.""" |
| 52 | 169 #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
| 22 | 170 if idx == selected: |
| 171 return style + 'sel' | |
| 172 else: | |
| 35 | 173 return style |
| 57 | 174 |
| 35 | 175 |
| 176 def isAccessible(self, docinfo): | |
| 32 | 177 """returns if access to the resource is granted""" |
| 178 access = docinfo.get('accessType', None) | |
| 52 | 179 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
| 45 | 180 if access is not None and access == 'free': |
| 52 | 181 logger("documentViewer (accessOK)", logging.INFO, "access is free") |
| 32 | 182 return True |
| 45 | 183 elif access is None or access in self.authgroups: |
| 35 | 184 # only local access -- only logged in users |
| 185 user = getSecurityManager().getUser() | |
| 186 if user is not None: | |
| 187 #print "user: ", user | |
| 188 return (user.getUserName() != "Anonymous User") | |
| 189 else: | |
| 190 return False | |
| 32 | 191 |
| 52 | 192 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
| 32 | 193 return False |
| 35 | 194 |
| 32 | 195 |
| 31 | 196 def getDirinfoFromDigilib(self,path,docinfo=None): |
| 29 | 197 """gibt param von dlInfo aus""" |
| 40 | 198 num_retries = 3 |
| 31 | 199 if docinfo is None: |
| 200 docinfo = {} | |
| 201 | |
| 40 | 202 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
| 29 | 203 |
| 52 | 204 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
| 29 | 205 |
| 40 | 206 for cnt in range(num_retries): |
| 35 | 207 try: |
| 40 | 208 # dom = NonvalidatingReader.parseUri(imageUrl) |
| 209 txt=urllib.urlopen(infoUrl).read() | |
| 210 dom = Parse(txt) | |
| 35 | 211 break |
| 212 except: | |
| 52 | 213 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
| 35 | 214 else: |
| 40 | 215 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
| 29 | 216 |
| 37 | 217 sizes=dom.xpath("//dir/size") |
| 52 | 218 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
| 29 | 219 |
| 37 | 220 if sizes: |
| 221 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
| 31 | 222 else: |
| 223 docinfo['numPages'] = 0 | |
| 224 | |
| 225 return docinfo | |
| 32 | 226 |
| 29 | 227 |
| 35 | 228 def getIndexMeta(self, url): |
| 229 """returns dom of index.meta document at url""" | |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
230 num_retries = 3 |
| 35 | 231 dom = None |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
232 metaUrl = None |
| 35 | 233 if url.startswith("http://"): |
| 234 # real URL | |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
235 metaUrl = url |
| 35 | 236 else: |
| 237 # online path | |
| 238 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 40 | 239 metaUrl=server+url.replace("/mpiwg/online","") |
| 35 | 240 if not metaUrl.endswith("index.meta"): |
| 241 metaUrl += "/index.meta" | |
| 46 | 242 print metaUrl |
| 40 | 243 for cnt in range(num_retries): |
| 35 | 244 try: |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
245 # patch dirk encoding fehler treten dann nicht mehr auf |
| 38 | 246 # dom = NonvalidatingReader.parseUri(metaUrl) |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
247 txt=urllib.urlopen(metaUrl).read() |
|
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
248 dom = Parse(txt) |
| 40 | 249 break |
| 35 | 250 except: |
| 52 | 251 logger("ERROR documentViewer (getIndexMata)", 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
|
252 |
|
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
253 if dom is None: |
|
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
254 raise IOError("Unable to read index meta from %s"%(url)) |
| 35 | 255 |
| 256 return dom | |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
257 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
258 def getPresentationInfoXML(self, url): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
259 """returns dom of info.xml document at url""" |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
260 num_retries = 3 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
261 dom = None |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
262 metaUrl = None |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
263 if url.startswith("http://"): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
264 # real URL |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
265 metaUrl = url |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
266 else: |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
267 # online path |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
268 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
269 metaUrl=server+url.replace("/mpiwg/online","") |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
270 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
271 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
272 for cnt in range(num_retries): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
273 try: |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
274 # patch dirk encoding fehler treten dann nicht mehr auf |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
275 # dom = NonvalidatingReader.parseUri(metaUrl) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
276 txt=urllib.urlopen(metaUrl).read() |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
277 dom = Parse(txt) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
278 break |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
279 except: |
| 52 | 280 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
|
281 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
282 if dom is None: |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
283 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
284 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
285 return dom |
| 35 | 286 |
| 287 | |
| 32 | 288 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None): |
| 35 | 289 """gets authorization info from the index.meta file at path or given by dom""" |
| 52 | 290 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
| 32 | 291 |
| 292 access = None | |
| 293 | |
| 294 if docinfo is None: | |
| 295 docinfo = {} | |
| 296 | |
| 297 if dom is None: | |
| 35 | 298 dom = self.getIndexMeta(getParentDir(path)) |
| 46 | 299 |
| 32 | 300 acctype = dom.xpath("//access-conditions/access/@type") |
| 301 if acctype and (len(acctype)>0): | |
| 302 access=acctype[0].value | |
| 35 | 303 if access in ['group', 'institution']: |
| 32 | 304 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
| 305 | |
| 306 docinfo['accessType'] = access | |
| 307 return docinfo | |
| 29 | 308 |
| 32 | 309 |
| 22 | 310 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None): |
| 35 | 311 """gets bibliographical info from the index.meta file at path or given by dom""" |
| 52 | 312 logger("documentViewer (getbibinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
| 20 | 313 |
| 22 | 314 if docinfo is None: |
| 315 docinfo = {} | |
| 316 | |
| 317 if dom is None: | |
| 35 | 318 dom = self.getIndexMeta(getParentDir(path)) |
| 319 | |
| 25 | 320 metaData=self.metadata.main.meta.bib |
| 321 bibtype=dom.xpath("//bib/@type") | |
| 322 if bibtype and (len(bibtype)>0): | |
| 323 bibtype=bibtype[0].value | |
| 20 | 324 else: |
| 25 | 325 bibtype="generic" |
| 326 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) | |
| 327 bibmap=metaData.generateMappingForType(bibtype) | |
| 35 | 328 #print "bibmap: ", bibmap, " for: ", bibtype |
| 32 | 329 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
| 31 | 330 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
| 25 | 331 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) |
| 332 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
| 333 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
| 52 | 334 |
| 335 logging.info("bla") | |
| 336 try: | |
| 337 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
| 338 except: | |
| 339 docinfo['lang']='' | |
| 22 | 340 return docinfo |
| 341 | |
| 342 | |
| 32 | 343 def getDocinfoFromTextTool(self,url,dom=None,docinfo=None): |
| 22 | 344 """parse texttool tag in index meta""" |
| 52 | 345 logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url)) |
| 22 | 346 if docinfo is None: |
| 347 docinfo = {} | |
| 348 | |
| 52 | 349 if docinfo.get('lang',None) is None: |
| 350 docinfo['lang']='' # default keine Sprache gesetzt | |
| 32 | 351 if dom is None: |
| 35 | 352 dom = self.getIndexMeta(url) |
| 32 | 353 |
|
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
354 archivePath = None |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
355 archiveName = None |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
356 |
| 32 | 357 archiveNames=dom.xpath("//resource/name") |
| 358 if archiveNames and (len(archiveNames)>0): | |
| 359 archiveName=getTextFromNode(archiveNames[0]) | |
|
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
360 else: |
| 52 | 361 logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url)) |
| 22 | 362 |
| 363 archivePaths=dom.xpath("//resource/archive-path") | |
| 364 if archivePaths and (len(archivePaths)>0): | |
| 365 archivePath=getTextFromNode(archivePaths[0]) | |
| 32 | 366 # clean up archive path |
| 367 if archivePath[0] != '/': | |
| 368 archivePath = '/' + archivePath | |
|
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
369 if archiveName and (not archivePath.endswith(archiveName)): |
| 32 | 370 archivePath += "/" + archiveName |
| 22 | 371 else: |
|
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
372 # try to get archive-path from url |
| 52 | 373 logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url)) |
|
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
374 if (not url.startswith('http')): |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
375 archivePath = url.replace('index.meta', '') |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
376 |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
377 if archivePath is None: |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
378 # we balk without archive-path |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
379 raise IOError("Missing archive-path (for text-tool) in %s"%(url)) |
| 22 | 380 |
| 35 | 381 imageDirs=dom.xpath("//texttool/image") |
| 382 if imageDirs and (len(imageDirs)>0): | |
| 383 imageDir=getTextFromNode(imageDirs[0]) | |
| 22 | 384 else: |
| 52 | 385 # we balk with no image tag / not necessary anymore because textmode is now standard |
| 386 #raise IOError("No text-tool info in %s"%(url)) | |
| 387 imageDir="" | |
| 388 docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht | |
| 389 | |
| 390 docinfo['imagePath'] = "" # keine Bilder | |
| 391 docinfo['imageURL'] = "" | |
| 392 | |
| 35 | 393 if imageDir and archivePath: |
| 394 #print "image: ", imageDir, " archivepath: ", archivePath | |
| 395 imageDir=os.path.join(archivePath,imageDir) | |
| 396 imageDir=imageDir.replace("/mpiwg/online",'') | |
| 397 docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo) | |
| 398 docinfo['imagePath'] = imageDir | |
| 399 docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir | |
| 22 | 400 |
| 401 viewerUrls=dom.xpath("//texttool/digiliburlprefix") | |
| 402 if viewerUrls and (len(viewerUrls)>0): | |
| 403 viewerUrl=getTextFromNode(viewerUrls[0]) | |
| 31 | 404 docinfo['viewerURL'] = viewerUrl |
| 22 | 405 |
| 406 textUrls=dom.xpath("//texttool/text") | |
| 407 if textUrls and (len(textUrls)>0): | |
| 408 textUrl=getTextFromNode(textUrls[0]) | |
|
49
a10fff6199b0
verbesserung f?r text unterst?tzung, text kann jetzt aus url kommen, sprache bisher nur deutsch
dwinter
parents:
46
diff
changeset
|
409 if urlparse.urlparse(textUrl)[0]=="": #keine url |
|
a10fff6199b0
verbesserung f?r text unterst?tzung, text kann jetzt aus url kommen, sprache bisher nur deutsch
dwinter
parents:
46
diff
changeset
|
410 textUrl=os.path.join(archivePath,textUrl) |
|
a10fff6199b0
verbesserung f?r text unterst?tzung, text kann jetzt aus url kommen, sprache bisher nur deutsch
dwinter
parents:
46
diff
changeset
|
411 |
| 31 | 412 docinfo['textURL'] = textUrl |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
413 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
414 presentationUrls=dom.xpath("//texttool/presentation") |
| 52 | 415 docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag |
| 416 | |
| 417 if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen | |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
418 # presentation url ergiebt sich ersetzen von index.meta in der url der fŸr die Metadaten |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
419 # durch den relativen Pfad auf die presentation infos |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
420 presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0])) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
421 docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom) |
| 52 | 422 |
|
55
ba8917b93c84
fixed bug in fix for missing getauthinfo in getdocinfofromtexttool
casties
parents:
54
diff
changeset
|
423 docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info |
| 22 | 424 return docinfo |
| 425 | |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
426 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
427 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
428 """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
|
429 """ |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
430 dom=self.getPresentationInfoXML(url) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
431 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
432 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
433 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
434 return docinfo |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
435 |
| 22 | 436 def getDocinfoFromImagePath(self,path,docinfo=None): |
| 437 """path ist the path to the images it assumes that the index.meta file is one level higher.""" | |
| 52 | 438 logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
| 22 | 439 if docinfo is None: |
| 440 docinfo = {} | |
| 29 | 441 path=path.replace("/mpiwg/online","") |
| 22 | 442 docinfo['imagePath'] = path |
| 31 | 443 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo) |
| 444 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path | |
| 22 | 445 docinfo['imageURL'] = imageUrl |
| 446 | |
| 447 docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo) | |
| 32 | 448 docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo) |
| 22 | 449 return docinfo |
| 20 | 450 |
| 22 | 451 |
| 452 def getDocinfo(self, mode, url): | |
| 453 """returns docinfo depending on mode""" | |
| 52 | 454 logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
| 22 | 455 # look for cached docinfo in session |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
456 if self.REQUEST.SESSION.has_key('docinfo'): |
| 22 | 457 docinfo = self.REQUEST.SESSION['docinfo'] |
| 458 # check if its still current | |
| 459 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
| 52 | 460 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
| 22 | 461 return docinfo |
| 462 # new docinfo | |
| 463 docinfo = {'mode': mode, 'url': url} | |
| 464 if mode=="texttool": #index.meta with texttool information | |
| 465 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
| 466 elif mode=="imagepath": | |
| 467 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
| 468 else: | |
| 52 | 469 logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
| 37 | 470 raise ValueError("Unknown mode %s"%(mode)) |
| 471 | |
| 52 | 472 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
| 22 | 473 self.REQUEST.SESSION['docinfo'] = docinfo |
| 474 return docinfo | |
| 20 | 475 |
| 476 | |
| 25 | 477 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None): |
| 22 | 478 """returns pageinfo with the given parameters""" |
| 479 pageinfo = {} | |
| 25 | 480 current = getInt(current) |
| 481 pageinfo['current'] = current | |
| 482 rows = int(rows or self.thumbrows) | |
| 483 pageinfo['rows'] = rows | |
| 484 cols = int(cols or self.thumbcols) | |
| 485 pageinfo['cols'] = cols | |
| 486 grpsize = cols * rows | |
| 487 pageinfo['groupsize'] = grpsize | |
| 488 start = getInt(start, default=(int(current / grpsize) * grpsize +1)) | |
| 22 | 489 pageinfo['start'] = start |
| 25 | 490 pageinfo['end'] = start + grpsize |
| 491 if docinfo is not None: | |
| 492 np = int(docinfo['numPages']) | |
| 493 pageinfo['end'] = min(pageinfo['end'], np) | |
| 494 pageinfo['numgroups'] = int(np / grpsize) | |
| 495 if np % grpsize > 0: | |
| 496 pageinfo['numgroups'] += 1 | |
| 497 | |
| 22 | 498 return pageinfo |
| 499 | |
| 0 | 500 def text(self,mode,url,pn): |
| 501 """give text""" | |
| 502 if mode=="texttool": #index.meta with texttool information | |
| 503 (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) | |
| 504 | |
| 35 | 505 #print textpath |
| 0 | 506 try: |
| 507 dom = NonvalidatingReader.parseUri(textpath) | |
| 508 except: | |
| 509 return None | |
| 510 | |
| 511 list=[] | |
| 512 nodes=dom.xpath("//pb") | |
| 513 | |
| 514 node=nodes[int(pn)-1] | |
| 515 | |
| 516 p=node | |
| 517 | |
| 518 while p.tagName!="p": | |
| 519 p=p.parentNode | |
| 520 | |
| 521 | |
| 522 endNode=nodes[int(pn)] | |
| 523 | |
| 524 | |
| 525 e=endNode | |
| 526 | |
| 527 while e.tagName!="p": | |
| 528 e=e.parentNode | |
| 529 | |
| 530 | |
| 531 next=node.parentNode | |
| 532 | |
| 533 #sammle s | |
| 534 while next and (next!=endNode.parentNode): | |
| 535 list.append(next) | |
| 536 next=next.nextSibling | |
| 537 list.append(endNode.parentNode) | |
| 538 | |
| 539 if p==e:# beide im selben paragraphen | |
| 20 | 540 pass |
| 541 # else: | |
| 542 # next=p | |
| 543 # while next!=e: | |
| 544 # print next,e | |
| 545 # list.append(next) | |
| 546 # next=next.nextSibling | |
| 547 # | |
| 548 # for x in list: | |
| 549 # PrettyPrint(x) | |
| 550 # | |
| 551 # return list | |
| 22 | 552 # |
| 553 | |
| 554 def findDigilibUrl(self): | |
| 555 """try to get the digilib URL from zogilib""" | |
| 556 url = self.imageViewerUrl[:-1] + "/getScalerUrl" | |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
557 #print urlparse.urlparse(url)[0] |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
558 #print urlparse.urljoin(self.absolute_url(),url) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
559 logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0]) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
560 logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url)) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
561 |
| 22 | 562 try: |
| 46 | 563 if urlparse.urlparse(url)[0]=='': #relative path |
| 564 url=urlparse.urljoin(self.absolute_url()+"/",url) | |
| 565 | |
| 22 | 566 scaler = urlopen(url).read() |
| 567 return scaler.replace("/servlet/Scaler?", "") | |
| 568 except: | |
| 569 return None | |
| 570 | |
| 46 | 571 def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): |
| 22 | 572 """init document viewer""" |
| 573 self.title=title | |
| 574 self.imageViewerUrl=imageViewerUrl | |
| 46 | 575 self.textViewerUrl=textViewerUrl |
| 22 | 576 self.digilibBaseUrl = digilibBaseUrl |
| 25 | 577 self.thumbrows = thumbrows |
| 578 self.thumbcols = thumbcols | |
| 32 | 579 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| 22 | 580 if RESPONSE is not None: |
| 581 RESPONSE.redirect('manage_main') | |
| 0 | 582 |
| 583 | |
| 584 | |
| 585 | |
| 586 # security.declareProtected('View management screens','renameImageForm') | |
| 587 | |
| 588 def manage_AddDocumentViewerForm(self): | |
| 589 """add the viewer form""" | |
| 22 | 590 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| 0 | 591 return pt() |
| 592 | |
| 46 | 593 def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None): |
| 0 | 594 """add the viewer""" |
| 46 | 595 newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl) |
| 0 | 596 self._setObject(id,newObj) |
| 597 | |
| 598 if RESPONSE is not None: | |
| 599 RESPONSE.redirect('manage_main') | |
| 22 | 600 |
| 601 | |
| 602 ## | |
| 603 ## DocumentViewerTemplate class | |
| 604 ## | |
| 605 class DocumentViewerTemplate(ZopePageTemplate): | |
| 606 """Template for document viewer""" | |
| 607 meta_type="DocumentViewer Template" | |
| 608 | |
| 609 | |
| 610 def manage_addDocumentViewerTemplateForm(self): | |
| 611 """Form for adding""" | |
| 612 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
| 613 return pt() | |
| 614 | |
| 615 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
| 616 REQUEST=None, submit=None): | |
| 617 "Add a Page Template with optional file content." | |
| 618 | |
| 619 self._setObject(id, DocumentViewerTemplate(id)) | |
| 620 ob = getattr(self, id) | |
|
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
621 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
|
622 logging.info("txt %s:"%txt) |
|
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
623 ob.pt_edit(txt,"text/html") |
| 22 | 624 if title: |
| 625 ob.pt_setTitle(title) | |
| 626 try: | |
| 627 u = self.DestinationURL() | |
| 628 except AttributeError: | |
| 629 u = REQUEST['URL1'] | |
| 630 | |
| 631 u = "%s/%s" % (u, urllib.quote(id)) | |
| 632 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
| 633 return '' | |
| 634 | |
| 635 | |
| 41 | 636 |