| 1 | |
|---|
| 2 | |
|---|
| 3 | from OFS.Folder import Folder |
|---|
| 4 | from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate |
|---|
| 5 | from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
|---|
| 6 | from AccessControl import ClassSecurityInfo |
|---|
| 7 | from AccessControl import getSecurityManager |
|---|
| 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, Parse |
|---|
| 13 | |
|---|
| 14 | import Ft.Xml.XPath |
|---|
| 15 | |
|---|
| 16 | import os.path |
|---|
| 17 | import sys |
|---|
| 18 | import cgi |
|---|
| 19 | import urllib |
|---|
| 20 | import logging |
|---|
| 21 | import math |
|---|
| 22 | |
|---|
| 23 | import urlparse |
|---|
| 24 | |
|---|
| 25 | def logger(txt,method,txt2): |
|---|
| 26 | """logging""" |
|---|
| 27 | logging.info(txt+ txt2) |
|---|
| 28 | |
|---|
| 29 | |
|---|
| 30 | def getInt(number, default=0): |
|---|
| 31 | """returns always an int (0 in case of problems)""" |
|---|
| 32 | try: |
|---|
| 33 | return int(number) |
|---|
| 34 | except: |
|---|
| 35 | return int(default) |
|---|
| 36 | |
|---|
| 37 | def getTextFromNode(nodename): |
|---|
| 38 | """get the cdata content of a node""" |
|---|
| 39 | if nodename is None: |
|---|
| 40 | return "" |
|---|
| 41 | nodelist=nodename.childNodes |
|---|
| 42 | rc = "" |
|---|
| 43 | for node in nodelist: |
|---|
| 44 | if node.nodeType == node.TEXT_NODE: |
|---|
| 45 | rc = rc + node.data |
|---|
| 46 | return rc |
|---|
| 47 | |
|---|
| 48 | |
|---|
| 49 | def getParentDir(path): |
|---|
| 50 | """returns pathname shortened by one""" |
|---|
| 51 | return '/'.join(path.split('/')[0:-1]) |
|---|
| 52 | |
|---|
| 53 | |
|---|
| 54 | import socket |
|---|
| 55 | |
|---|
| 56 | def urlopen(url,timeout=2): |
|---|
| 57 | """urlopen mit timeout""" |
|---|
| 58 | socket.setdefaulttimeout(timeout) |
|---|
| 59 | ret=urllib.urlopen(url) |
|---|
| 60 | socket.setdefaulttimeout(5) |
|---|
| 61 | return ret |
|---|
| 62 | |
|---|
| 63 | |
|---|
| 64 | ## |
|---|
| 65 | ## documentViewer class |
|---|
| 66 | ## |
|---|
| 67 | class documentViewer(Folder): |
|---|
| 68 | """document viewer""" |
|---|
| 69 | #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" |
|---|
| 70 | |
|---|
| 71 | meta_type="Document viewer" |
|---|
| 72 | |
|---|
| 73 | security=ClassSecurityInfo() |
|---|
| 74 | manage_options=Folder.manage_options+( |
|---|
| 75 | {'label':'main config','action':'changeDocumentViewerForm'}, |
|---|
| 76 | ) |
|---|
| 77 | |
|---|
| 78 | # templates and forms |
|---|
| 79 | viewer_main = PageTemplateFile('zpt/viewer_main', globals()) |
|---|
| 80 | thumbs_main = PageTemplateFile('zpt/thumbs_main', globals()) |
|---|
| 81 | image_main = PageTemplateFile('zpt/image_main', globals()) |
|---|
| 82 | head_main = PageTemplateFile('zpt/head_main', globals()) |
|---|
| 83 | docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) |
|---|
| 84 | info_xml = PageTemplateFile('zpt/info_xml', globals()) |
|---|
| 85 | |
|---|
| 86 | thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
|---|
| 87 | security.declareProtected('View management screens','changeDocumentViewerForm') |
|---|
| 88 | changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
|---|
| 89 | |
|---|
| 90 | |
|---|
| 91 | def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): |
|---|
| 92 | """init document viewer""" |
|---|
| 93 | self.id=id |
|---|
| 94 | self.title=title |
|---|
| 95 | self.imageViewerUrl=imageViewerUrl |
|---|
| 96 | self.textViewerUrl=textViewerUrl |
|---|
| 97 | |
|---|
| 98 | if not digilibBaseUrl: |
|---|
| 99 | self.digilibBaseUrl = self.findDigilibUrl() |
|---|
| 100 | else: |
|---|
| 101 | self.digilibBaseUrl = digilibBaseUrl |
|---|
| 102 | self.thumbcols = thumbcols |
|---|
| 103 | self.thumbrows = thumbrows |
|---|
| 104 | # authgroups is list of authorized groups (delimited by ,) |
|---|
| 105 | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
|---|
| 106 | # add template folder so we can always use template.something |
|---|
| 107 | self.manage_addFolder('template') |
|---|
| 108 | |
|---|
| 109 | |
|---|
| 110 | security.declareProtected('View','thumbs_rss') |
|---|
| 111 | def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): |
|---|
| 112 | ''' |
|---|
| 113 | view it |
|---|
| 114 | @param mode: defines how to access the document behind url |
|---|
| 115 | @param url: url which contains display information |
|---|
| 116 | @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
|---|
| 117 | |
|---|
| 118 | ''' |
|---|
| 119 | logging.info("HHHHHHHHHHHHHH:load the rss") |
|---|
| 120 | logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
|---|
| 121 | |
|---|
| 122 | if not hasattr(self, 'template'): |
|---|
| 123 | # create template folder if it doesn't exist |
|---|
| 124 | self.manage_addFolder('template') |
|---|
| 125 | |
|---|
| 126 | if not self.digilibBaseUrl: |
|---|
| 127 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
|---|
| 128 | |
|---|
| 129 | docinfo = self.getDocinfo(mode=mode,url=url) |
|---|
| 130 | pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
|---|
| 131 | pt = getattr(self.template, 'thumbs_main_rss') |
|---|
| 132 | |
|---|
| 133 | if viewMode=="auto": # automodus gewaehlt |
|---|
| 134 | if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert |
|---|
| 135 | viewMode="text" |
|---|
| 136 | else: |
|---|
| 137 | viewMode="images" |
|---|
| 138 | |
|---|
| 139 | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
|---|
| 140 | |
|---|
| 141 | security.declareProtected('View','index_html') |
|---|
| 142 | def index_html(self,mode,url,viewMode="auto",start=None,pn=1): |
|---|
| 143 | ''' |
|---|
| 144 | view it |
|---|
| 145 | @param mode: defines how to access the document behind url |
|---|
| 146 | @param url: url which contains display information |
|---|
| 147 | @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
|---|
| 148 | |
|---|
| 149 | ''' |
|---|
| 150 | |
|---|
| 151 | logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
|---|
| 152 | |
|---|
| 153 | if not hasattr(self, 'template'): |
|---|
| 154 | # create template folder if it doesn't exist |
|---|
| 155 | self.manage_addFolder('template') |
|---|
| 156 | |
|---|
| 157 | if not self.digilibBaseUrl: |
|---|
| 158 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
|---|
| 159 | |
|---|
| 160 | docinfo = self.getDocinfo(mode=mode,url=url) |
|---|
| 161 | pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
|---|
| 162 | pt = getattr(self.template, 'viewer_main') |
|---|
| 163 | |
|---|
| 164 | if viewMode=="auto": # automodus gewaehlt |
|---|
| 165 | if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert |
|---|
| 166 | viewMode="text" |
|---|
| 167 | else: |
|---|
| 168 | viewMode="images" |
|---|
| 169 | |
|---|
| 170 | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
|---|
| 171 | |
|---|
| 172 | |
|---|
| 173 | def getLink(self,param=None,val=None): |
|---|
| 174 | """link to documentviewer with parameter param set to val""" |
|---|
| 175 | params=self.REQUEST.form.copy() |
|---|
| 176 | if param is not None: |
|---|
| 177 | if val is None: |
|---|
| 178 | if params.has_key(param): |
|---|
| 179 | del params[param] |
|---|
| 180 | else: |
|---|
| 181 | params[param] = str(val) |
|---|
| 182 | |
|---|
| 183 | # quote values and assemble into query string |
|---|
| 184 | ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
|---|
| 185 | url=self.REQUEST['URL1']+"?"+ps |
|---|
| 186 | return url |
|---|
| 187 | |
|---|
| 188 | def getLinkAmp(self,param=None,val=None): |
|---|
| 189 | """link to documentviewer with parameter param set to val""" |
|---|
| 190 | params=self.REQUEST.form.copy() |
|---|
| 191 | if param is not None: |
|---|
| 192 | if val is None: |
|---|
| 193 | if params.has_key(param): |
|---|
| 194 | del params[param] |
|---|
| 195 | else: |
|---|
| 196 | params[param] = str(val) |
|---|
| 197 | |
|---|
| 198 | # quote values and assemble into query string |
|---|
| 199 | logging.info("XYXXXXX: %s"%repr(params.items())) |
|---|
| 200 | ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
|---|
| 201 | url=self.REQUEST['URL1']+"?"+ps |
|---|
| 202 | return url |
|---|
| 203 | def getInfo_xml(self,url,mode): |
|---|
| 204 | """returns info about the document as XML""" |
|---|
| 205 | |
|---|
| 206 | if not self.digilibBaseUrl: |
|---|
| 207 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
|---|
| 208 | |
|---|
| 209 | docinfo = self.getDocinfo(mode=mode,url=url) |
|---|
| 210 | pt = getattr(self.template, 'info_xml') |
|---|
| 211 | return pt(docinfo=docinfo) |
|---|
| 212 | |
|---|
| 213 | |
|---|
| 214 | def getStyle(self, idx, selected, style=""): |
|---|
| 215 | """returns a string with the given style and append 'sel' if path == selected.""" |
|---|
| 216 | #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
|---|
| 217 | if idx == selected: |
|---|
| 218 | return style + 'sel' |
|---|
| 219 | else: |
|---|
| 220 | return style |
|---|
| 221 | |
|---|
| 222 | |
|---|
| 223 | def isAccessible(self, docinfo): |
|---|
| 224 | """returns if access to the resource is granted""" |
|---|
| 225 | access = docinfo.get('accessType', None) |
|---|
| 226 | logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
|---|
| 227 | if access is not None and access == 'free': |
|---|
| 228 | logger("documentViewer (accessOK)", logging.INFO, "access is free") |
|---|
| 229 | return True |
|---|
| 230 | elif access is None or access in self.authgroups: |
|---|
| 231 | # only local access -- only logged in users |
|---|
| 232 | user = getSecurityManager().getUser() |
|---|
| 233 | if user is not None: |
|---|
| 234 | #print "user: ", user |
|---|
| 235 | return (user.getUserName() != "Anonymous User") |
|---|
| 236 | else: |
|---|
| 237 | return False |
|---|
| 238 | |
|---|
| 239 | logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
|---|
| 240 | return False |
|---|
| 241 | |
|---|
| 242 | |
|---|
| 243 | def getDirinfoFromDigilib(self,path,docinfo=None): |
|---|
| 244 | """gibt param von dlInfo aus""" |
|---|
| 245 | num_retries = 3 |
|---|
| 246 | if docinfo is None: |
|---|
| 247 | docinfo = {} |
|---|
| 248 | |
|---|
| 249 | infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
|---|
| 250 | |
|---|
| 251 | logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
|---|
| 252 | |
|---|
| 253 | for cnt in range(num_retries): |
|---|
| 254 | try: |
|---|
| 255 | # dom = NonvalidatingReader.parseUri(imageUrl) |
|---|
| 256 | txt=urllib.urlopen(infoUrl).read() |
|---|
| 257 | dom = Parse(txt) |
|---|
| 258 | break |
|---|
| 259 | except: |
|---|
| 260 | logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
|---|
| 261 | else: |
|---|
| 262 | raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
|---|
| 263 | |
|---|
| 264 | sizes=dom.xpath("//dir/size") |
|---|
| 265 | logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
|---|
| 266 | |
|---|
| 267 | if sizes: |
|---|
| 268 | docinfo['numPages'] = int(getTextFromNode(sizes[0])) |
|---|
| 269 | else: |
|---|
| 270 | docinfo['numPages'] = 0 |
|---|
| 271 | |
|---|
| 272 | return docinfo |
|---|
| 273 | |
|---|
| 274 | |
|---|
| 275 | def getIndexMeta(self, url): |
|---|
| 276 | """returns dom of index.meta document at url""" |
|---|
| 277 | num_retries = 3 |
|---|
| 278 | dom = None |
|---|
| 279 | metaUrl = None |
|---|
| 280 | if url.startswith("http://"): |
|---|
| 281 | # real URL |
|---|
| 282 | metaUrl = url |
|---|
| 283 | else: |
|---|
| 284 | # online path |
|---|
| 285 | server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
|---|
| 286 | metaUrl=server+url.replace("/mpiwg/online","") |
|---|
| 287 | if not metaUrl.endswith("index.meta"): |
|---|
| 288 | metaUrl += "/index.meta" |
|---|
| 289 | print metaUrl |
|---|
| 290 | for cnt in range(num_retries): |
|---|
| 291 | try: |
|---|
| 292 | # patch dirk encoding fehler treten dann nicht mehr auf |
|---|
| 293 | # dom = NonvalidatingReader.parseUri(metaUrl) |
|---|
| 294 | txt=urllib.urlopen(metaUrl).read() |
|---|
| 295 | dom = Parse(txt) |
|---|
| 296 | break |
|---|
| 297 | except: |
|---|
| 298 | logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
|---|
| 299 | |
|---|
| 300 | if dom is None: |
|---|
| 301 | raise IOError("Unable to read index meta from %s"%(url)) |
|---|
| 302 | |
|---|
| 303 | return dom |
|---|
| 304 | |
|---|
| 305 | def getPresentationInfoXML(self, url): |
|---|
| 306 | """returns dom of info.xml document at url""" |
|---|
| 307 | num_retries = 3 |
|---|
| 308 | dom = None |
|---|
| 309 | metaUrl = None |
|---|
| 310 | if url.startswith("http://"): |
|---|
| 311 | # real URL |
|---|
| 312 | metaUrl = url |
|---|
| 313 | else: |
|---|
| 314 | # online path |
|---|
| 315 | server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
|---|
| 316 | metaUrl=server+url.replace("/mpiwg/online","") |
|---|
| 317 | |
|---|
| 318 | |
|---|
| 319 | for cnt in range(num_retries): |
|---|
| 320 | try: |
|---|
| 321 | # patch dirk encoding fehler treten dann nicht mehr auf |
|---|
| 322 | # dom = NonvalidatingReader.parseUri(metaUrl) |
|---|
| 323 | txt=urllib.urlopen(metaUrl).read() |
|---|
| 324 | dom = Parse(txt) |
|---|
| 325 | break |
|---|
| 326 | except: |
|---|
| 327 | logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
|---|
| 328 | |
|---|
| 329 | if dom is None: |
|---|
| 330 | raise IOError("Unable to read infoXMLfrom %s"%(url)) |
|---|
| 331 | |
|---|
| 332 | return dom |
|---|
| 333 | |
|---|
| 334 | |
|---|
| 335 | def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None): |
|---|
| 336 | """gets authorization info from the index.meta file at path or given by dom""" |
|---|
| 337 | logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
|---|
| 338 | |
|---|
| 339 | access = None |
|---|
| 340 | |
|---|
| 341 | if docinfo is None: |
|---|
| 342 | docinfo = {} |
|---|
| 343 | |
|---|
| 344 | if dom is None: |
|---|
| 345 | dom = self.getIndexMeta(getParentDir(path)) |
|---|
| 346 | |
|---|
| 347 | acctype = dom.xpath("//access-conditions/access/@type") |
|---|
| 348 | if acctype and (len(acctype)>0): |
|---|
| 349 | access=acctype[0].value |
|---|
| 350 | if access in ['group', 'institution']: |
|---|
| 351 | access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
|---|
| 352 | |
|---|
| 353 | docinfo['accessType'] = access |
|---|
| 354 | return docinfo |
|---|
| 355 | |
|---|
| 356 | |
|---|
| 357 | def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None): |
|---|
| 358 | """gets bibliographical info from the index.meta file at path or given by dom""" |
|---|
| 359 | logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
|---|
| 360 | |
|---|
| 361 | if docinfo is None: |
|---|
| 362 | docinfo = {} |
|---|
| 363 | |
|---|
| 364 | if dom is None: |
|---|
| 365 | dom = self.getIndexMeta(getParentDir(path)) |
|---|
| 366 | |
|---|
| 367 | # put in all raw bib fields as dict "bib" |
|---|
| 368 | bib = dom.xpath("//bib/*") |
|---|
| 369 | if bib and len(bib)>0: |
|---|
| 370 | bibinfo = {} |
|---|
| 371 | for e in bib: |
|---|
| 372 | bibinfo[e.localName] = getTextFromNode(e) |
|---|
| 373 | docinfo['bib'] = bibinfo |
|---|
| 374 | |
|---|
| 375 | # extract some fields (author, title, year) according to their mapping |
|---|
| 376 | metaData=self.metadata.main.meta.bib |
|---|
| 377 | bibtype=dom.xpath("//bib/@type") |
|---|
| 378 | if bibtype and (len(bibtype)>0): |
|---|
| 379 | bibtype=bibtype[0].value |
|---|
| 380 | else: |
|---|
| 381 | bibtype="generic" |
|---|
| 382 | |
|---|
| 383 | bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
|---|
| 384 | docinfo['bib_type'] = bibtype |
|---|
| 385 | bibmap=metaData.generateMappingForType(bibtype) |
|---|
| 386 | # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
|---|
| 387 | if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
|---|
| 388 | try: |
|---|
| 389 | docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) |
|---|
| 390 | except: pass |
|---|
| 391 | try: |
|---|
| 392 | docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) |
|---|
| 393 | except: pass |
|---|
| 394 | try: |
|---|
| 395 | docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) |
|---|
| 396 | except: pass |
|---|
| 397 | logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
|---|
| 398 | try: |
|---|
| 399 | docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) |
|---|
| 400 | except: |
|---|
| 401 | docinfo['lang']='' |
|---|
| 402 | |
|---|
| 403 | return docinfo |
|---|
| 404 | |
|---|
| 405 | |
|---|
| 406 | def getDocinfoFromTextTool(self,url,dom=None,docinfo=None): |
|---|
| 407 | """parse texttool tag in index meta""" |
|---|
| 408 | logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url)) |
|---|
| 409 | if docinfo is None: |
|---|
| 410 | docinfo = {} |
|---|
| 411 | |
|---|
| 412 | if docinfo.get('lang',None) is None: |
|---|
| 413 | docinfo['lang']='' # default keine Sprache gesetzt |
|---|
| 414 | if dom is None: |
|---|
| 415 | dom = self.getIndexMeta(url) |
|---|
| 416 | |
|---|
| 417 | archivePath = None |
|---|
| 418 | archiveName = None |
|---|
| 419 | |
|---|
| 420 | archiveNames=dom.xpath("//resource/name") |
|---|
| 421 | if archiveNames and (len(archiveNames)>0): |
|---|
| 422 | archiveName=getTextFromNode(archiveNames[0]) |
|---|
| 423 | else: |
|---|
| 424 | logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url)) |
|---|
| 425 | |
|---|
| 426 | archivePaths=dom.xpath("//resource/archive-path") |
|---|
| 427 | if archivePaths and (len(archivePaths)>0): |
|---|
| 428 | archivePath=getTextFromNode(archivePaths[0]) |
|---|
| 429 | # clean up archive path |
|---|
| 430 | if archivePath[0] != '/': |
|---|
| 431 | archivePath = '/' + archivePath |
|---|
| 432 | if archiveName and (not archivePath.endswith(archiveName)): |
|---|
| 433 | archivePath += "/" + archiveName |
|---|
| 434 | else: |
|---|
| 435 | # try to get archive-path from url |
|---|
| 436 | logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url)) |
|---|
| 437 | if (not url.startswith('http')): |
|---|
| 438 | archivePath = url.replace('index.meta', '') |
|---|
| 439 | |
|---|
| 440 | if archivePath is None: |
|---|
| 441 | # we balk without archive-path |
|---|
| 442 | raise IOError("Missing archive-path (for text-tool) in %s"%(url)) |
|---|
| 443 | |
|---|
| 444 | imageDirs=dom.xpath("//texttool/image") |
|---|
| 445 | if imageDirs and (len(imageDirs)>0): |
|---|
| 446 | imageDir=getTextFromNode(imageDirs[0]) |
|---|
| 447 | else: |
|---|
| 448 | # we balk with no image tag / not necessary anymore because textmode is now standard |
|---|
| 449 | #raise IOError("No text-tool info in %s"%(url)) |
|---|
| 450 | imageDir="" |
|---|
| 451 | docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht |
|---|
| 452 | |
|---|
| 453 | docinfo['imagePath'] = "" # keine Bilder |
|---|
| 454 | docinfo['imageURL'] = "" |
|---|
| 455 | |
|---|
| 456 | if imageDir and archivePath: |
|---|
| 457 | #print "image: ", imageDir, " archivepath: ", archivePath |
|---|
| 458 | imageDir=os.path.join(archivePath,imageDir) |
|---|
| 459 | imageDir=imageDir.replace("/mpiwg/online",'') |
|---|
| 460 | docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo) |
|---|
| 461 | docinfo['imagePath'] = imageDir |
|---|
| 462 | docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir |
|---|
| 463 | |
|---|
| 464 | viewerUrls=dom.xpath("//texttool/digiliburlprefix") |
|---|
| 465 | if viewerUrls and (len(viewerUrls)>0): |
|---|
| 466 | viewerUrl=getTextFromNode(viewerUrls[0]) |
|---|
| 467 | docinfo['viewerURL'] = viewerUrl |
|---|
| 468 | |
|---|
| 469 | textUrls=dom.xpath("//texttool/text") |
|---|
| 470 | if textUrls and (len(textUrls)>0): |
|---|
| 471 | textUrl=getTextFromNode(textUrls[0]) |
|---|
| 472 | if urlparse.urlparse(textUrl)[0]=="": #keine url |
|---|
| 473 | textUrl=os.path.join(archivePath,textUrl) |
|---|
| 474 | # fix URLs starting with /mpiwg/online |
|---|
| 475 | if textUrl.startswith("/mpiwg/online"): |
|---|
| 476 | textUrl = textUrl.replace("/mpiwg/online",'',1) |
|---|
| 477 | |
|---|
| 478 | docinfo['textURL'] = textUrl |
|---|
| 479 | |
|---|
| 480 | presentationUrls=dom.xpath("//texttool/presentation") |
|---|
| 481 | docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag |
|---|
| 482 | |
|---|
| 483 | if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen |
|---|
| 484 | # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten |
|---|
| 485 | # durch den relativen Pfad auf die presentation infos |
|---|
| 486 | presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0])) |
|---|
| 487 | docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom) |
|---|
| 488 | |
|---|
| 489 | docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info |
|---|
| 490 | return docinfo |
|---|
| 491 | |
|---|
| 492 | |
|---|
| 493 | def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
|---|
| 494 | """gets the bibliographical information from the preseantion entry in texttools |
|---|
| 495 | """ |
|---|
| 496 | dom=self.getPresentationInfoXML(url) |
|---|
| 497 | try: |
|---|
| 498 | docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) |
|---|
| 499 | except: |
|---|
| 500 | pass |
|---|
| 501 | try: |
|---|
| 502 | docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) |
|---|
| 503 | except: |
|---|
| 504 | pass |
|---|
| 505 | try: |
|---|
| 506 | docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) |
|---|
| 507 | except: |
|---|
| 508 | pass |
|---|
| 509 | return docinfo |
|---|
| 510 | |
|---|
| 511 | def getDocinfoFromImagePath(self,path,docinfo=None): |
|---|
| 512 | """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
|---|
| 513 | logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
|---|
| 514 | if docinfo is None: |
|---|
| 515 | docinfo = {} |
|---|
| 516 | path=path.replace("/mpiwg/online","") |
|---|
| 517 | docinfo['imagePath'] = path |
|---|
| 518 | docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo) |
|---|
| 519 | imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
|---|
| 520 | docinfo['imageURL'] = imageUrl |
|---|
| 521 | |
|---|
| 522 | docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo) |
|---|
| 523 | docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo) |
|---|
| 524 | return docinfo |
|---|
| 525 | |
|---|
| 526 | |
|---|
| 527 | def getDocinfo(self, mode, url): |
|---|
| 528 | """returns docinfo depending on mode""" |
|---|
| 529 | logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
|---|
| 530 | # look for cached docinfo in session |
|---|
| 531 | if self.REQUEST.SESSION.has_key('docinfo'): |
|---|
| 532 | docinfo = self.REQUEST.SESSION['docinfo'] |
|---|
| 533 | # check if its still current |
|---|
| 534 | if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: |
|---|
| 535 | logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
|---|
| 536 | return docinfo |
|---|
| 537 | # new docinfo |
|---|
| 538 | docinfo = {'mode': mode, 'url': url} |
|---|
| 539 | if mode=="texttool": #index.meta with texttool information |
|---|
| 540 | docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) |
|---|
| 541 | elif mode=="imagepath": |
|---|
| 542 | docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) |
|---|
| 543 | else: |
|---|
| 544 | logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
|---|
| 545 | raise ValueError("Unknown mode %s"%(mode)) |
|---|
| 546 | |
|---|
| 547 | logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
|---|
| 548 | self.REQUEST.SESSION['docinfo'] = docinfo |
|---|
| 549 | return docinfo |
|---|
| 550 | |
|---|
| 551 | |
|---|
| 552 | def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None): |
|---|
| 553 | """returns pageinfo with the given parameters""" |
|---|
| 554 | pageinfo = {} |
|---|
| 555 | current = getInt(current) |
|---|
| 556 | pageinfo['current'] = current |
|---|
| 557 | rows = int(rows or self.thumbrows) |
|---|
| 558 | pageinfo['rows'] = rows |
|---|
| 559 | cols = int(cols or self.thumbcols) |
|---|
| 560 | pageinfo['cols'] = cols |
|---|
| 561 | grpsize = cols * rows |
|---|
| 562 | pageinfo['groupsize'] = grpsize |
|---|
| 563 | start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
|---|
| 564 | # int(current / grpsize) * grpsize +1)) |
|---|
| 565 | pageinfo['start'] = start |
|---|
| 566 | pageinfo['end'] = start + grpsize |
|---|
| 567 | if docinfo is not None: |
|---|
| 568 | np = int(docinfo['numPages']) |
|---|
| 569 | pageinfo['end'] = min(pageinfo['end'], np) |
|---|
| 570 | pageinfo['numgroups'] = int(np / grpsize) |
|---|
| 571 | if np % grpsize > 0: |
|---|
| 572 | pageinfo['numgroups'] += 1 |
|---|
| 573 | |
|---|
| 574 | return pageinfo |
|---|
| 575 | |
|---|
| 576 | def text(self,mode,url,pn): |
|---|
| 577 | """give text""" |
|---|
| 578 | if mode=="texttool": #index.meta with texttool information |
|---|
| 579 | (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) |
|---|
| 580 | |
|---|
| 581 | #print textpath |
|---|
| 582 | try: |
|---|
| 583 | dom = NonvalidatingReader.parseUri(textpath) |
|---|
| 584 | except: |
|---|
| 585 | return None |
|---|
| 586 | |
|---|
| 587 | list=[] |
|---|
| 588 | nodes=dom.xpath("//pb") |
|---|
| 589 | |
|---|
| 590 | node=nodes[int(pn)-1] |
|---|
| 591 | |
|---|
| 592 | p=node |
|---|
| 593 | |
|---|
| 594 | while p.tagName!="p": |
|---|
| 595 | p=p.parentNode |
|---|
| 596 | |
|---|
| 597 | |
|---|
| 598 | endNode=nodes[int(pn)] |
|---|
| 599 | |
|---|
| 600 | |
|---|
| 601 | e=endNode |
|---|
| 602 | |
|---|
| 603 | while e.tagName!="p": |
|---|
| 604 | e=e.parentNode |
|---|
| 605 | |
|---|
| 606 | |
|---|
| 607 | next=node.parentNode |
|---|
| 608 | |
|---|
| 609 | #sammle s |
|---|
| 610 | while next and (next!=endNode.parentNode): |
|---|
| 611 | list.append(next) |
|---|
| 612 | next=next.nextSibling |
|---|
| 613 | list.append(endNode.parentNode) |
|---|
| 614 | |
|---|
| 615 | if p==e:# beide im selben paragraphen |
|---|
| 616 | pass |
|---|
| 617 | # else: |
|---|
| 618 | # next=p |
|---|
| 619 | # while next!=e: |
|---|
| 620 | # print next,e |
|---|
| 621 | # list.append(next) |
|---|
| 622 | # next=next.nextSibling |
|---|
| 623 | # |
|---|
| 624 | # for x in list: |
|---|
| 625 | # PrettyPrint(x) |
|---|
| 626 | # |
|---|
| 627 | # return list |
|---|
| 628 | # |
|---|
| 629 | |
|---|
| 630 | def findDigilibUrl(self): |
|---|
| 631 | """try to get the digilib URL from zogilib""" |
|---|
| 632 | url = self.imageViewerUrl[:-1] + "/getScalerUrl" |
|---|
| 633 | #print urlparse.urlparse(url)[0] |
|---|
| 634 | #print urlparse.urljoin(self.absolute_url(),url) |
|---|
| 635 | logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0]) |
|---|
| 636 | logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url)) |
|---|
| 637 | |
|---|
| 638 | try: |
|---|
| 639 | if urlparse.urlparse(url)[0]=='': #relative path |
|---|
| 640 | url=urlparse.urljoin(self.absolute_url()+"/",url) |
|---|
| 641 | |
|---|
| 642 | scaler = urlopen(url).read() |
|---|
| 643 | return scaler.replace("/servlet/Scaler?", "") |
|---|
| 644 | except: |
|---|
| 645 | return None |
|---|
| 646 | |
|---|
| 647 | def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): |
|---|
| 648 | """init document viewer""" |
|---|
| 649 | self.title=title |
|---|
| 650 | self.imageViewerUrl=imageViewerUrl |
|---|
| 651 | self.textViewerUrl=textViewerUrl |
|---|
| 652 | self.digilibBaseUrl = digilibBaseUrl |
|---|
| 653 | self.thumbrows = thumbrows |
|---|
| 654 | self.thumbcols = thumbcols |
|---|
| 655 | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
|---|
| 656 | if RESPONSE is not None: |
|---|
| 657 | RESPONSE.redirect('manage_main') |
|---|
| 658 | |
|---|
| 659 | |
|---|
| 660 | |
|---|
| 661 | |
|---|
| 662 | # security.declareProtected('View management screens','renameImageForm') |
|---|
| 663 | |
|---|
| 664 | def manage_AddDocumentViewerForm(self): |
|---|
| 665 | """add the viewer form""" |
|---|
| 666 | pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
|---|
| 667 | return pt() |
|---|
| 668 | |
|---|
| 669 | def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None): |
|---|
| 670 | """add the viewer""" |
|---|
| 671 | newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl) |
|---|
| 672 | self._setObject(id,newObj) |
|---|
| 673 | |
|---|
| 674 | if RESPONSE is not None: |
|---|
| 675 | RESPONSE.redirect('manage_main') |
|---|
| 676 | |
|---|
| 677 | |
|---|
| 678 | ## |
|---|
| 679 | ## DocumentViewerTemplate class |
|---|
| 680 | ## |
|---|
| 681 | class DocumentViewerTemplate(ZopePageTemplate): |
|---|
| 682 | """Template for document viewer""" |
|---|
| 683 | meta_type="DocumentViewer Template" |
|---|
| 684 | |
|---|
| 685 | |
|---|
| 686 | def manage_addDocumentViewerTemplateForm(self): |
|---|
| 687 | """Form for adding""" |
|---|
| 688 | pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) |
|---|
| 689 | return pt() |
|---|
| 690 | |
|---|
| 691 | def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, |
|---|
| 692 | REQUEST=None, submit=None): |
|---|
| 693 | "Add a Page Template with optional file content." |
|---|
| 694 | |
|---|
| 695 | self._setObject(id, DocumentViewerTemplate(id)) |
|---|
| 696 | ob = getattr(self, id) |
|---|
| 697 | txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
|---|
| 698 | logging.info("txt %s:"%txt) |
|---|
| 699 | ob.pt_edit(txt,"text/html") |
|---|
| 700 | if title: |
|---|
| 701 | ob.pt_setTitle(title) |
|---|
| 702 | try: |
|---|
| 703 | u = self.DestinationURL() |
|---|
| 704 | except AttributeError: |
|---|
| 705 | u = REQUEST['URL1'] |
|---|
| 706 | |
|---|
| 707 | u = "%s/%s" % (u, urllib.quote(id)) |
|---|
| 708 | REQUEST.RESPONSE.redirect(u+'/manage_main') |
|---|
| 709 | return '' |
|---|
| 710 | |
|---|
| 711 | |
|---|
| 712 | |
|---|
