| 1 | |
|---|
| 2 | genericDigilib="http://nausikaa2.rz-berlin.mpg.de/digitallibrary/" |
|---|
| 3 | |
|---|
| 4 | from OFS.Folder import Folder |
|---|
| 5 | from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate |
|---|
| 6 | from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
|---|
| 7 | from AccessControl import ClassSecurityInfo |
|---|
| 8 | from Globals import package_home |
|---|
| 9 | |
|---|
| 10 | from Ft.Xml.Domlette import NonvalidatingReader |
|---|
| 11 | from Ft.Xml.Domlette import PrettyPrint, Print |
|---|
| 12 | from Ft.Xml import EMPTY_NAMESPACE |
|---|
| 13 | |
|---|
| 14 | import Ft.Xml.XPath |
|---|
| 15 | |
|---|
| 16 | import os.path |
|---|
| 17 | import cgi |
|---|
| 18 | import urllib |
|---|
| 19 | import zLOG |
|---|
| 20 | |
|---|
| 21 | def getInt(number, default=0): |
|---|
| 22 | """returns always an int (0 in case of problems)""" |
|---|
| 23 | try: |
|---|
| 24 | return int(number) |
|---|
| 25 | except: |
|---|
| 26 | return default |
|---|
| 27 | |
|---|
| 28 | |
|---|
| 29 | def getTextFromNode(nodename): |
|---|
| 30 | nodelist=nodename.childNodes |
|---|
| 31 | rc = "" |
|---|
| 32 | for node in nodelist: |
|---|
| 33 | if node.nodeType == node.TEXT_NODE: |
|---|
| 34 | rc = rc + node.data |
|---|
| 35 | return rc |
|---|
| 36 | |
|---|
| 37 | import socket |
|---|
| 38 | |
|---|
| 39 | def urlopen(url): |
|---|
| 40 | """urlopen mit timeout""" |
|---|
| 41 | socket.setdefaulttimeout(2) |
|---|
| 42 | ret=urllib.urlopen(url) |
|---|
| 43 | socket.setdefaulttimeout(5) |
|---|
| 44 | return ret |
|---|
| 45 | |
|---|
| 46 | def getParamFromDigilib(path,param): |
|---|
| 47 | """gibt param von dlInfo aus""" |
|---|
| 48 | imageUrl=genericDigilib+"/dirInfo-xml.jsp?mo=dir&fn="+path |
|---|
| 49 | |
|---|
| 50 | zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo (%s) from %s"%(param,imageUrl)) |
|---|
| 51 | |
|---|
| 52 | try: |
|---|
| 53 | dom = NonvalidatingReader.parseUri(imageUrl) |
|---|
| 54 | except: |
|---|
| 55 | return None |
|---|
| 56 | |
|---|
| 57 | params=dom.xpath("//dir/%s"%param) |
|---|
| 58 | zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:%s"%params) |
|---|
| 59 | |
|---|
| 60 | if params: |
|---|
| 61 | return getTextFromNode(params[0]) |
|---|
| 62 | |
|---|
| 63 | |
|---|
| 64 | |
|---|
| 65 | |
|---|
| 66 | ## |
|---|
| 67 | ## documentViewer class |
|---|
| 68 | ## |
|---|
| 69 | class documentViewer(Folder): |
|---|
| 70 | """document viewer""" |
|---|
| 71 | |
|---|
| 72 | meta_type="Document viewer" |
|---|
| 73 | |
|---|
| 74 | security=ClassSecurityInfo() |
|---|
| 75 | manage_options=Folder.manage_options+( |
|---|
| 76 | {'label':'main config','action':'changeDocumentViewerForm'}, |
|---|
| 77 | ) |
|---|
| 78 | |
|---|
| 79 | # templates and forms |
|---|
| 80 | viewer_main = PageTemplateFile('zpt/viewer_main', globals()) |
|---|
| 81 | thumbs_main = PageTemplateFile('zpt/thumbs_main', globals()) |
|---|
| 82 | image_main = PageTemplateFile('zpt/image_main', globals()) |
|---|
| 83 | head_main = PageTemplateFile('zpt/head_main', globals()) |
|---|
| 84 | docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) |
|---|
| 85 | |
|---|
| 86 | security.declareProtected('View management screens','changeDocumentViewerForm') |
|---|
| 87 | changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
|---|
| 88 | |
|---|
| 89 | |
|---|
| 90 | def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10): |
|---|
| 91 | """init document viewer""" |
|---|
| 92 | self.id=id |
|---|
| 93 | self.title=title |
|---|
| 94 | self.imageViewerUrl=imageViewerUrl |
|---|
| 95 | if not digilibBaseUrl: |
|---|
| 96 | self.digilibBaseUrl = self.findDigilibUrl() |
|---|
| 97 | else: |
|---|
| 98 | self.digilibBaseUrl = digilibBaseUrl |
|---|
| 99 | self.thumbcols = thumbcols |
|---|
| 100 | self.thumbrows = thumbrows |
|---|
| 101 | # add template folder so we can always use template.something |
|---|
| 102 | self.manage_addFolder('template') |
|---|
| 103 | |
|---|
| 104 | |
|---|
| 105 | security.declareProtected('View','index_html') |
|---|
| 106 | def index_html(self,mode,url,start=None,pn=1): |
|---|
| 107 | ''' |
|---|
| 108 | view it |
|---|
| 109 | @param mode: defines which type of document is behind url |
|---|
| 110 | @param url: url which contains display information |
|---|
| 111 | ''' |
|---|
| 112 | |
|---|
| 113 | zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
|---|
| 114 | print "dlbaseurl:", self.digilibBaseUrl |
|---|
| 115 | |
|---|
| 116 | if not hasattr(self, 'template'): |
|---|
| 117 | # create template folder if it doesn't exist |
|---|
| 118 | print "no template folder -- creating" |
|---|
| 119 | self.manage_addFolder('template') |
|---|
| 120 | |
|---|
| 121 | if not self.digilibBaseUrl: |
|---|
| 122 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
|---|
| 123 | |
|---|
| 124 | docinfo = self.getDocinfo(mode=mode,url=url) |
|---|
| 125 | pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
|---|
| 126 | pt = getattr(self.template, 'viewer_main') |
|---|
| 127 | return pt(docinfo=docinfo,pageinfo=pageinfo) |
|---|
| 128 | |
|---|
| 129 | |
|---|
| 130 | def getLink(self,param=None,val=None): |
|---|
| 131 | """link to documentviewer with parameter param set to val""" |
|---|
| 132 | params=cgi.parse_qs(self.REQUEST['QUERY_STRING']) |
|---|
| 133 | if param is not None: |
|---|
| 134 | if val is None and params.has_key(param): |
|---|
| 135 | del params[param] |
|---|
| 136 | else: |
|---|
| 137 | params[param] = val |
|---|
| 138 | |
|---|
| 139 | url=self.REQUEST['URL']+"?"+urllib.urlencode(params, doseq=True) |
|---|
| 140 | return url |
|---|
| 141 | |
|---|
| 142 | |
|---|
| 143 | def getStyle(self, idx, selected, style=""): |
|---|
| 144 | """returns a string with the given style and append 'sel' if path == selected.""" |
|---|
| 145 | #zLOG.LOG("documentViewer (getstyle)", zLOG.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
|---|
| 146 | if idx == selected: |
|---|
| 147 | return style + 'sel' |
|---|
| 148 | else: |
|---|
| 149 | return style |
|---|
| 150 | |
|---|
| 151 | |
|---|
| 152 | def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None): |
|---|
| 153 | """gets bibliographical info from the index.meta file at url or given by dom""" |
|---|
| 154 | zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path)) |
|---|
| 155 | |
|---|
| 156 | if docinfo is None: |
|---|
| 157 | docinfo = {} |
|---|
| 158 | |
|---|
| 159 | if dom is None: |
|---|
| 160 | server="http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary/servlet/Texter?fn=" |
|---|
| 161 | path="/".join(path.split("/")[0:-1]) |
|---|
| 162 | metaUrl=server+path+"/index.meta" |
|---|
| 163 | try: |
|---|
| 164 | dom = NonvalidatingReader.parseUri(metaUrl) |
|---|
| 165 | except: |
|---|
| 166 | return docinfo |
|---|
| 167 | |
|---|
| 168 | metaData=self.metadata.main.meta.bib |
|---|
| 169 | bibtype=dom.xpath("//bib/@type") |
|---|
| 170 | if bibtype and (len(bibtype)>0): |
|---|
| 171 | bibtype=bibtype[0].value |
|---|
| 172 | else: |
|---|
| 173 | bibtype="generic" |
|---|
| 174 | bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
|---|
| 175 | bibmap=metaData.generateMappingForType(bibtype) |
|---|
| 176 | if len(bibmap) > 0: |
|---|
| 177 | docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) |
|---|
| 178 | docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) |
|---|
| 179 | docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) |
|---|
| 180 | |
|---|
| 181 | return docinfo |
|---|
| 182 | |
|---|
| 183 | |
|---|
| 184 | def getDocinfoFromTextTool(self,url,docinfo=None): |
|---|
| 185 | """parse texttool tag in index meta""" |
|---|
| 186 | zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url)) |
|---|
| 187 | if docinfo is None: |
|---|
| 188 | docinfo = {} |
|---|
| 189 | |
|---|
| 190 | try: |
|---|
| 191 | dom = NonvalidatingReader.parseUri(url) |
|---|
| 192 | except: |
|---|
| 193 | zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
|---|
| 194 | return docinfo |
|---|
| 195 | |
|---|
| 196 | archivePaths=dom.xpath("//resource/archive-path") |
|---|
| 197 | |
|---|
| 198 | if archivePaths and (len(archivePaths)>0): |
|---|
| 199 | archivePath=getTextFromNode(archivePaths[0]) |
|---|
| 200 | else: |
|---|
| 201 | archivePath=None |
|---|
| 202 | |
|---|
| 203 | images=dom.xpath("//texttool/image") |
|---|
| 204 | |
|---|
| 205 | if images and (len(images)>0): |
|---|
| 206 | image=getTextFromNode(images[0]) |
|---|
| 207 | else: |
|---|
| 208 | image=None |
|---|
| 209 | |
|---|
| 210 | if image and archivePath: |
|---|
| 211 | image=os.path.join(archivePath,image) |
|---|
| 212 | image=image.replace("/mpiwg/online",'') |
|---|
| 213 | pt=getParamFromDigilib(image,'size') |
|---|
| 214 | docinfo['imagePath'] = image |
|---|
| 215 | docinfo['numPages'] = pt |
|---|
| 216 | |
|---|
| 217 | viewerUrls=dom.xpath("//texttool/digiliburlprefix") |
|---|
| 218 | |
|---|
| 219 | if viewerUrls and (len(viewerUrls)>0): |
|---|
| 220 | viewerUrl=getTextFromNode(viewerUrls[0]) |
|---|
| 221 | docinfo['imageURL'] = viewerURL |
|---|
| 222 | |
|---|
| 223 | textUrls=dom.xpath("//texttool/text") |
|---|
| 224 | |
|---|
| 225 | if textUrls and (len(textUrls)>0): |
|---|
| 226 | textUrl=getTextFromNode(textUrls[0]) |
|---|
| 227 | docinfo['textURL'] = textURL |
|---|
| 228 | |
|---|
| 229 | docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) |
|---|
| 230 | return docinfo |
|---|
| 231 | |
|---|
| 232 | |
|---|
| 233 | def getDocinfoFromImagePath(self,path,docinfo=None): |
|---|
| 234 | """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
|---|
| 235 | zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path)) |
|---|
| 236 | if docinfo is None: |
|---|
| 237 | docinfo = {} |
|---|
| 238 | docinfo['imagePath'] = path |
|---|
| 239 | path=path.replace("/mpiwg/online","") |
|---|
| 240 | pt=getParamFromDigilib(path,'size') |
|---|
| 241 | docinfo['numPages'] = pt |
|---|
| 242 | imageUrl=genericDigilib+"/servlet/Scaler?fn=%s"%path |
|---|
| 243 | docinfo['imageURL'] = imageUrl |
|---|
| 244 | |
|---|
| 245 | docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo) |
|---|
| 246 | return docinfo |
|---|
| 247 | |
|---|
| 248 | |
|---|
| 249 | def getDocinfo(self, mode, url): |
|---|
| 250 | """returns docinfo depending on mode""" |
|---|
| 251 | zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"mode: %s, url: %s"%(mode,url)) |
|---|
| 252 | # look for cached docinfo in session |
|---|
| 253 | if self.REQUEST.SESSION.has_key('docinfo'): |
|---|
| 254 | docinfo = self.REQUEST.SESSION['docinfo'] |
|---|
| 255 | # check if its still current |
|---|
| 256 | if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: |
|---|
| 257 | zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo) |
|---|
| 258 | return docinfo |
|---|
| 259 | # new docinfo |
|---|
| 260 | docinfo = {'mode': mode, 'url': url} |
|---|
| 261 | if mode=="texttool": #index.meta with texttool information |
|---|
| 262 | docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) |
|---|
| 263 | elif mode=="imagepath": |
|---|
| 264 | docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) |
|---|
| 265 | else: |
|---|
| 266 | zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!") |
|---|
| 267 | zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo) |
|---|
| 268 | self.REQUEST.SESSION['docinfo'] = docinfo |
|---|
| 269 | return docinfo |
|---|
| 270 | |
|---|
| 271 | |
|---|
| 272 | def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None): |
|---|
| 273 | """returns pageinfo with the given parameters""" |
|---|
| 274 | pageinfo = {} |
|---|
| 275 | current = getInt(current) |
|---|
| 276 | pageinfo['current'] = current |
|---|
| 277 | rows = int(rows or self.thumbrows) |
|---|
| 278 | pageinfo['rows'] = rows |
|---|
| 279 | cols = int(cols or self.thumbcols) |
|---|
| 280 | pageinfo['cols'] = cols |
|---|
| 281 | grpsize = cols * rows |
|---|
| 282 | pageinfo['groupsize'] = grpsize |
|---|
| 283 | start = getInt(start, default=(int(current / grpsize) * grpsize +1)) |
|---|
| 284 | print "start3:", start |
|---|
| 285 | pageinfo['start'] = start |
|---|
| 286 | pageinfo['end'] = start + grpsize |
|---|
| 287 | if docinfo is not None: |
|---|
| 288 | np = int(docinfo['numPages']) |
|---|
| 289 | pageinfo['end'] = min(pageinfo['end'], np) |
|---|
| 290 | pageinfo['numgroups'] = int(np / grpsize) |
|---|
| 291 | if np % grpsize > 0: |
|---|
| 292 | pageinfo['numgroups'] += 1 |
|---|
| 293 | |
|---|
| 294 | return pageinfo |
|---|
| 295 | |
|---|
| 296 | def text(self,mode,url,pn): |
|---|
| 297 | """give text""" |
|---|
| 298 | if mode=="texttool": #index.meta with texttool information |
|---|
| 299 | (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) |
|---|
| 300 | |
|---|
| 301 | print textpath |
|---|
| 302 | try: |
|---|
| 303 | dom = NonvalidatingReader.parseUri(textpath) |
|---|
| 304 | except: |
|---|
| 305 | return None |
|---|
| 306 | |
|---|
| 307 | list=[] |
|---|
| 308 | nodes=dom.xpath("//pb") |
|---|
| 309 | |
|---|
| 310 | node=nodes[int(pn)-1] |
|---|
| 311 | |
|---|
| 312 | p=node |
|---|
| 313 | |
|---|
| 314 | while p.tagName!="p": |
|---|
| 315 | p=p.parentNode |
|---|
| 316 | |
|---|
| 317 | |
|---|
| 318 | endNode=nodes[int(pn)] |
|---|
| 319 | |
|---|
| 320 | |
|---|
| 321 | e=endNode |
|---|
| 322 | |
|---|
| 323 | while e.tagName!="p": |
|---|
| 324 | e=e.parentNode |
|---|
| 325 | |
|---|
| 326 | |
|---|
| 327 | next=node.parentNode |
|---|
| 328 | |
|---|
| 329 | #sammle s |
|---|
| 330 | while next and (next!=endNode.parentNode): |
|---|
| 331 | list.append(next) |
|---|
| 332 | next=next.nextSibling |
|---|
| 333 | list.append(endNode.parentNode) |
|---|
| 334 | |
|---|
| 335 | if p==e:# beide im selben paragraphen |
|---|
| 336 | pass |
|---|
| 337 | # else: |
|---|
| 338 | # next=p |
|---|
| 339 | # while next!=e: |
|---|
| 340 | # print next,e |
|---|
| 341 | # list.append(next) |
|---|
| 342 | # next=next.nextSibling |
|---|
| 343 | # |
|---|
| 344 | # for x in list: |
|---|
| 345 | # PrettyPrint(x) |
|---|
| 346 | # |
|---|
| 347 | # return list |
|---|
| 348 | # |
|---|
| 349 | |
|---|
| 350 | def findDigilibUrl(self): |
|---|
| 351 | """try to get the digilib URL from zogilib""" |
|---|
| 352 | url = self.imageViewerUrl[:-1] + "/getScalerUrl" |
|---|
| 353 | try: |
|---|
| 354 | scaler = urlopen(url).read() |
|---|
| 355 | return scaler.replace("/servlet/Scaler?", "") |
|---|
| 356 | except: |
|---|
| 357 | return None |
|---|
| 358 | |
|---|
| 359 | def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,RESPONSE=None): |
|---|
| 360 | """init document viewer""" |
|---|
| 361 | self.title=title |
|---|
| 362 | self.imageViewerUrl=imageViewerUrl |
|---|
| 363 | self.digilibBaseUrl = digilibBaseUrl |
|---|
| 364 | self.thumbrows = thumbrows |
|---|
| 365 | self.thumbcols = thumbcols |
|---|
| 366 | |
|---|
| 367 | if RESPONSE is not None: |
|---|
| 368 | RESPONSE.redirect('manage_main') |
|---|
| 369 | |
|---|
| 370 | |
|---|
| 371 | |
|---|
| 372 | |
|---|
| 373 | # security.declareProtected('View management screens','renameImageForm') |
|---|
| 374 | |
|---|
| 375 | def manage_AddDocumentViewerForm(self): |
|---|
| 376 | """add the viewer form""" |
|---|
| 377 | pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
|---|
| 378 | return pt() |
|---|
| 379 | |
|---|
| 380 | def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None): |
|---|
| 381 | """add the viewer""" |
|---|
| 382 | newObj=documentViewer(id,imageViewerUrl,title) |
|---|
| 383 | self._setObject(id,newObj) |
|---|
| 384 | |
|---|
| 385 | if RESPONSE is not None: |
|---|
| 386 | RESPONSE.redirect('manage_main') |
|---|
| 387 | |
|---|
| 388 | |
|---|
| 389 | ## |
|---|
| 390 | ## DocumentViewerTemplate class |
|---|
| 391 | ## |
|---|
| 392 | class DocumentViewerTemplate(ZopePageTemplate): |
|---|
| 393 | """Template for document viewer""" |
|---|
| 394 | meta_type="DocumentViewer Template" |
|---|
| 395 | |
|---|
| 396 | |
|---|
| 397 | def manage_addDocumentViewerTemplateForm(self): |
|---|
| 398 | """Form for adding""" |
|---|
| 399 | pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) |
|---|
| 400 | return pt() |
|---|
| 401 | |
|---|
| 402 | def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, |
|---|
| 403 | REQUEST=None, submit=None): |
|---|
| 404 | "Add a Page Template with optional file content." |
|---|
| 405 | |
|---|
| 406 | self._setObject(id, DocumentViewerTemplate(id)) |
|---|
| 407 | ob = getattr(self, id) |
|---|
| 408 | ob.pt_edit(open(os.path.join(package_home(globals()),'zpt/viewer_main.zpt')).read(),None) |
|---|
| 409 | if title: |
|---|
| 410 | ob.pt_setTitle(title) |
|---|
| 411 | try: |
|---|
| 412 | u = self.DestinationURL() |
|---|
| 413 | except AttributeError: |
|---|
| 414 | u = REQUEST['URL1'] |
|---|
| 415 | |
|---|
| 416 | u = "%s/%s" % (u, urllib.quote(id)) |
|---|
| 417 | REQUEST.RESPONSE.redirect(u+'/manage_main') |
|---|
| 418 | return '' |
|---|
| 419 | |
|---|
| 420 | |
|---|
| 421 | |
|---|
