| 1 | |
|---|
| 2 | from OFS.Folder import Folder |
|---|
| 3 | from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate |
|---|
| 4 | from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
|---|
| 5 | from AccessControl import ClassSecurityInfo |
|---|
| 6 | from AccessControl import getSecurityManager |
|---|
| 7 | from Globals import package_home |
|---|
| 8 | |
|---|
| 9 | from Ft.Xml import EMPTY_NAMESPACE, Parse |
|---|
| 10 | import Ft.Xml.Domlette |
|---|
| 11 | import os.path |
|---|
| 12 | import sys |
|---|
| 13 | import urllib |
|---|
| 14 | import urllib2 |
|---|
| 15 | import logging |
|---|
| 16 | import math |
|---|
| 17 | import urlparse |
|---|
| 18 | import cStringIO |
|---|
| 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) |
|---|
| 31 | |
|---|
| 32 | def getTextFromNode(nodename): |
|---|
| 33 | """get the cdata content of a node""" |
|---|
| 34 | if nodename is None: |
|---|
| 35 | return "" |
|---|
| 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 | |
|---|
| 43 | def serializeNode(node, encoding='utf-8'): |
|---|
| 44 | """returns a string containing node as XML""" |
|---|
| 45 | buf = cStringIO.StringIO() |
|---|
| 46 | Ft.Xml.Domlette.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 | |
|---|
| 57 | def getHttpData(url, data=None, num_tries=3, timeout=10): |
|---|
| 58 | """returns result from url+data HTTP request""" |
|---|
| 59 | # we do GET (by appending data to url) |
|---|
| 60 | if isinstance(data, str) or isinstance(data, unicode): |
|---|
| 61 | # if data is string then append |
|---|
| 62 | url = "%s?%s"%(url,data) |
|---|
| 63 | elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): |
|---|
| 64 | # urlencode |
|---|
| 65 | url = "%s?%s"%(url,urllib.urlencode(data)) |
|---|
| 66 | |
|---|
| 67 | response = None |
|---|
| 68 | errmsg = None |
|---|
| 69 | for cnt in range(num_tries): |
|---|
| 70 | try: |
|---|
| 71 | logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) |
|---|
| 72 | if sys.version_info < (2, 6): |
|---|
| 73 | # set timeout on socket -- ugly :-( |
|---|
| 74 | import socket |
|---|
| 75 | socket.setdefaulttimeout(float(timeout)) |
|---|
| 76 | response = urllib2.urlopen(url) |
|---|
| 77 | else: |
|---|
| 78 | response = urllib2.urlopen(url,timeout=float(timeout)) |
|---|
| 79 | # check result? |
|---|
| 80 | break |
|---|
| 81 | except urllib2.HTTPError, e: |
|---|
| 82 | logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) |
|---|
| 83 | errmsg = str(e) |
|---|
| 84 | # stop trying |
|---|
| 85 | break |
|---|
| 86 | except urllib2.URLError, e: |
|---|
| 87 | logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) |
|---|
| 88 | errmsg = str(e) |
|---|
| 89 | # stop trying |
|---|
| 90 | #break |
|---|
| 91 | |
|---|
| 92 | if response is not None: |
|---|
| 93 | data = response.read() |
|---|
| 94 | response.close() |
|---|
| 95 | return data |
|---|
| 96 | |
|---|
| 97 | raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) |
|---|
| 98 | #return None |
|---|
| 99 | |
|---|
| 100 | |
|---|
| 101 | |
|---|
| 102 | ## |
|---|
| 103 | ## documentViewer class |
|---|
| 104 | ## |
|---|
| 105 | class documentViewer(Folder): |
|---|
| 106 | """document viewer""" |
|---|
| 107 | meta_type="Document viewer" |
|---|
| 108 | |
|---|
| 109 | security=ClassSecurityInfo() |
|---|
| 110 | manage_options=Folder.manage_options+( |
|---|
| 111 | {'label':'main config','action':'changeDocumentViewerForm'}, |
|---|
| 112 | ) |
|---|
| 113 | |
|---|
| 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()) |
|---|
| 126 | |
|---|
| 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"): |
|---|
| 134 | """init document viewer""" |
|---|
| 135 | self.id=id |
|---|
| 136 | self.title=title |
|---|
| 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 |
|---|
| 142 | |
|---|
| 143 | templateFolder = Folder('template') |
|---|
| 144 | #self['template'] = templateFolder # Zope-2.12 style |
|---|
| 145 | self._setObject('template',templateFolder) # old style |
|---|
| 146 | try: |
|---|
| 147 | import MpdlXmlTextServer |
|---|
| 148 | textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
|---|
| 149 | #templateFolder['fulltextclient'] = xmlRpcClient |
|---|
| 150 | templateFolder._setObject('fulltextclient',textServer) |
|---|
| 151 | except Exception, e: |
|---|
| 152 | logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
|---|
| 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 | |
|---|
| 161 | |
|---|
| 162 | # proxy text server methods to fulltextclient |
|---|
| 163 | def getTextPage(self, **args): |
|---|
| 164 | """get page""" |
|---|
| 165 | return self.template.fulltextclient.getTextPage(**args) |
|---|
| 166 | |
|---|
| 167 | def getQuery(self, **args): |
|---|
| 168 | """get query""" |
|---|
| 169 | return self.template.fulltextclient.getQuery(**args) |
|---|
| 170 | |
|---|
| 171 | def getSearch(self, **args): |
|---|
| 172 | """get search""" |
|---|
| 173 | return self.template.fulltextclient.getSearch(**args) |
|---|
| 174 | |
|---|
| 175 | def getNumPages(self, docinfo): |
|---|
| 176 | """get numpages""" |
|---|
| 177 | return self.template.fulltextclient.getNumPages(docinfo) |
|---|
| 178 | |
|---|
| 179 | def getTranslate(self, **args): |
|---|
| 180 | """get translate""" |
|---|
| 181 | return self.template.fulltextclient.getTranslate(**args) |
|---|
| 182 | |
|---|
| 183 | def getLemma(self, **args): |
|---|
| 184 | """get lemma""" |
|---|
| 185 | return self.template.fulltextclient.getLemma(**args) |
|---|
| 186 | |
|---|
| 187 | def getToc(self, **args): |
|---|
| 188 | """get toc""" |
|---|
| 189 | return self.template.fulltextclient.getToc(**args) |
|---|
| 190 | |
|---|
| 191 | def getTocPage(self, **args): |
|---|
| 192 | """get tocpage""" |
|---|
| 193 | return self.template.fulltextclient.getTocPage(**args) |
|---|
| 194 | |
|---|
| 195 | |
|---|
| 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)) |
|---|
| 207 | |
|---|
| 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.has_key("textURL") or docinfo.has_key('textURLPath'): #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://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
|---|
| 247 | |
|---|
| 248 | docinfo = self.getDocinfo(mode=mode,url=url) |
|---|
| 249 | |
|---|
| 250 | if tocMode != "thumbs": |
|---|
| 251 | # get table of contents |
|---|
| 252 | docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
|---|
| 253 | |
|---|
| 254 | if viewMode=="auto": # automodus gewaehlt |
|---|
| 255 | if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert |
|---|
| 256 | viewMode="text_dict" |
|---|
| 257 | else: |
|---|
| 258 | viewMode="images" |
|---|
| 259 | |
|---|
| 260 | pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) |
|---|
| 261 | |
|---|
| 262 | pt = getattr(self.template, 'viewer_main') |
|---|
| 263 | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
|---|
| 264 | |
|---|
| 265 | def generateMarks(self,mk): |
|---|
| 266 | ret="" |
|---|
| 267 | if mk is None: |
|---|
| 268 | return "" |
|---|
| 269 | if not isinstance(mk, list): |
|---|
| 270 | mk=[mk] |
|---|
| 271 | for m in mk: |
|---|
| 272 | ret+="mk=%s"%m |
|---|
| 273 | return ret |
|---|
| 274 | |
|---|
| 275 | |
|---|
| 276 | def findDigilibUrl(self): |
|---|
| 277 | """try to get the digilib URL from zogilib""" |
|---|
| 278 | url = self.template.zogilib.getDLBaseUrl() |
|---|
| 279 | return url |
|---|
| 280 | |
|---|
| 281 | def getDocumentViewerURL(self): |
|---|
| 282 | """returns the URL of this instance""" |
|---|
| 283 | return self.absolute_url() |
|---|
| 284 | |
|---|
| 285 | def getStyle(self, idx, selected, style=""): |
|---|
| 286 | """returns a string with the given style and append 'sel' if path == selected.""" |
|---|
| 287 | #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
|---|
| 288 | if idx == selected: |
|---|
| 289 | return style + 'sel' |
|---|
| 290 | else: |
|---|
| 291 | return style |
|---|
| 292 | |
|---|
| 293 | def getLink(self,param=None,val=None): |
|---|
| 294 | """link to documentviewer with parameter param set to val""" |
|---|
| 295 | params=self.REQUEST.form.copy() |
|---|
| 296 | if param is not None: |
|---|
| 297 | if val is None: |
|---|
| 298 | if params.has_key(param): |
|---|
| 299 | del params[param] |
|---|
| 300 | else: |
|---|
| 301 | params[param] = str(val) |
|---|
| 302 | |
|---|
| 303 | if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
|---|
| 304 | params["mode"] = "imagepath" |
|---|
| 305 | params["url"] = getParentDir(params["url"]) |
|---|
| 306 | |
|---|
| 307 | # quote values and assemble into query string |
|---|
| 308 | #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
|---|
| 309 | ps = urllib.urlencode(params) |
|---|
| 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 |
|---|
| 324 | logging.debug("XYXXXXX: %s"%repr(params.items())) |
|---|
| 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" |
|---|
| 334 | |
|---|
| 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) |
|---|
| 343 | logging.debug("documentViewer (accessOK) access type %s"%access) |
|---|
| 344 | if access is not None and access == 'free': |
|---|
| 345 | logging.debug("documentViewer (accessOK) access is free") |
|---|
| 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 |
|---|
| 355 | |
|---|
| 356 | logging.debug("documentViewer (accessOK) unknown access type %s"%access) |
|---|
| 357 | return False |
|---|
| 358 | |
|---|
| 359 | |
|---|
| 360 | def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
|---|
| 361 | """gibt param von dlInfo aus""" |
|---|
| 362 | if docinfo is None: |
|---|
| 363 | docinfo = {} |
|---|
| 364 | |
|---|
| 365 | for x in range(cut): |
|---|
| 366 | |
|---|
| 367 | path=getParentDir(path) |
|---|
| 368 | |
|---|
| 369 | infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
|---|
| 370 | |
|---|
| 371 | logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) |
|---|
| 372 | |
|---|
| 373 | txt = getHttpData(infoUrl) |
|---|
| 374 | if txt is None: |
|---|
| 375 | raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
|---|
| 376 | |
|---|
| 377 | dom = Parse(txt) |
|---|
| 378 | sizes=dom.xpath("//dir/size") |
|---|
| 379 | logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) |
|---|
| 380 | |
|---|
| 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 | |
|---|
| 405 | logging.debug("(getIndexMeta): METAURL: %s"%metaUrl) |
|---|
| 406 | txt=getHttpData(metaUrl) |
|---|
| 407 | if txt is None: |
|---|
| 408 | raise IOError("Unable to read index meta from %s"%(url)) |
|---|
| 409 | |
|---|
| 410 | dom = Parse(txt) |
|---|
| 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","") |
|---|
| 424 | |
|---|
| 425 | txt=getHttpData(metaUrl) |
|---|
| 426 | if txt is None: |
|---|
| 427 | raise IOError("Unable to read infoXMLfrom %s"%(url)) |
|---|
| 428 | |
|---|
| 429 | dom = Parse(txt) |
|---|
| 430 | return dom |
|---|
| 431 | |
|---|
| 432 | |
|---|
| 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""" |
|---|
| 435 | logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) |
|---|
| 436 | |
|---|
| 437 | access = None |
|---|
| 438 | |
|---|
| 439 | if docinfo is None: |
|---|
| 440 | docinfo = {} |
|---|
| 441 | |
|---|
| 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 |
|---|
| 455 | |
|---|
| 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 |
|---|
| 477 | |
|---|
| 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 |
|---|
| 507 | |
|---|
| 508 | |
|---|
| 509 | def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): |
|---|
| 510 | """parse texttool tag in index meta""" |
|---|
| 511 | logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) |
|---|
| 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: |
|---|
| 526 | logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) |
|---|
| 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 |
|---|
| 538 | logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url)) |
|---|
| 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)) |
|---|
| 545 | |
|---|
| 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 | # old style text URL |
|---|
| 573 | textUrls = dom.xpath("//texttool/text") |
|---|
| 574 | if textUrls and (len(textUrls) > 0): |
|---|
| 575 | textUrl = getTextFromNode(textUrls[0]) |
|---|
| 576 | if urlparse.urlparse(textUrl)[0] == "": #keine url |
|---|
| 577 | textUrl = os.path.join(archivePath, textUrl) |
|---|
| 578 | # fix URLs starting with /mpiwg/online |
|---|
| 579 | if textUrl.startswith("/mpiwg/online"): |
|---|
| 580 | textUrl = textUrl.replace("/mpiwg/online", '', 1) |
|---|
| 581 | |
|---|
| 582 | docinfo['textURL'] = textUrl |
|---|
| 583 | |
|---|
| 584 | # new style text-url-path |
|---|
| 585 | textUrls = dom.xpath("//texttool/text-url-path") |
|---|
| 586 | if textUrls and (len(textUrls) > 0): |
|---|
| 587 | textUrl = getTextFromNode(textUrls[0]) |
|---|
| 588 | docinfo['textURLPath'] = textUrl |
|---|
| 589 | if not docinfo['imagePath']: |
|---|
| 590 | # text-only, no page images |
|---|
| 591 | docinfo = self.getNumPages(docinfo) |
|---|
| 592 | |
|---|
| 593 | presentationUrls = dom.xpath("//texttool/presentation") |
|---|
| 594 | docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag |
|---|
| 595 | |
|---|
| 596 | if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen |
|---|
| 597 | # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten |
|---|
| 598 | # durch den relativen Pfad auf die presentation infos |
|---|
| 599 | presentationPath = getTextFromNode(presentationUrls[0]) |
|---|
| 600 | if url.endswith("index.meta"): |
|---|
| 601 | presentationUrl = url.replace('index.meta', presentationPath) |
|---|
| 602 | else: |
|---|
| 603 | presentationUrl = url + "/" + presentationPath |
|---|
| 604 | |
|---|
| 605 | docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) |
|---|
| 606 | |
|---|
| 607 | docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info |
|---|
| 608 | |
|---|
| 609 | return docinfo |
|---|
| 610 | |
|---|
| 611 | |
|---|
| 612 | def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
|---|
| 613 | """gets the bibliographical information from the preseantion entry in texttools |
|---|
| 614 | """ |
|---|
| 615 | dom=self.getPresentationInfoXML(url) |
|---|
| 616 | try: |
|---|
| 617 | docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) |
|---|
| 618 | except: |
|---|
| 619 | pass |
|---|
| 620 | try: |
|---|
| 621 | docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) |
|---|
| 622 | except: |
|---|
| 623 | pass |
|---|
| 624 | try: |
|---|
| 625 | docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) |
|---|
| 626 | except: |
|---|
| 627 | pass |
|---|
| 628 | return docinfo |
|---|
| 629 | |
|---|
| 630 | def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
|---|
| 631 | """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
|---|
| 632 | logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) |
|---|
| 633 | if docinfo is None: |
|---|
| 634 | docinfo = {} |
|---|
| 635 | path=path.replace("/mpiwg/online","") |
|---|
| 636 | docinfo['imagePath'] = path |
|---|
| 637 | docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
|---|
| 638 | |
|---|
| 639 | pathorig=path |
|---|
| 640 | for x in range(cut): |
|---|
| 641 | path=getParentDir(path) |
|---|
| 642 | logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) |
|---|
| 643 | imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
|---|
| 644 | docinfo['imageURL'] = imageUrl |
|---|
| 645 | |
|---|
| 646 | #path ist the path to the images it assumes that the index.meta file is one level higher. |
|---|
| 647 | docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
|---|
| 648 | docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
|---|
| 649 | return docinfo |
|---|
| 650 | |
|---|
| 651 | |
|---|
| 652 | def getDocinfo(self, mode, url): |
|---|
| 653 | """returns docinfo depending on mode""" |
|---|
| 654 | logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) |
|---|
| 655 | # look for cached docinfo in session |
|---|
| 656 | if self.REQUEST.SESSION.has_key('docinfo'): |
|---|
| 657 | docinfo = self.REQUEST.SESSION['docinfo'] |
|---|
| 658 | # check if its still current |
|---|
| 659 | if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: |
|---|
| 660 | logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) |
|---|
| 661 | return docinfo |
|---|
| 662 | # new docinfo |
|---|
| 663 | docinfo = {'mode': mode, 'url': url} |
|---|
| 664 | if mode=="texttool": #index.meta with texttool information |
|---|
| 665 | docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) |
|---|
| 666 | elif mode=="imagepath": |
|---|
| 667 | docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) |
|---|
| 668 | elif mode=="filepath": |
|---|
| 669 | docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
|---|
| 670 | else: |
|---|
| 671 | logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
|---|
| 672 | raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
|---|
| 673 | |
|---|
| 674 | logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
|---|
| 675 | self.REQUEST.SESSION['docinfo'] = docinfo |
|---|
| 676 | return docinfo |
|---|
| 677 | |
|---|
| 678 | def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): |
|---|
| 679 | """returns pageinfo with the given parameters""" |
|---|
| 680 | pageinfo = {} |
|---|
| 681 | current = getInt(current) |
|---|
| 682 | pageinfo['current'] = current |
|---|
| 683 | rows = int(rows or self.thumbrows) |
|---|
| 684 | pageinfo['rows'] = rows |
|---|
| 685 | cols = int(cols or self.thumbcols) |
|---|
| 686 | pageinfo['cols'] = cols |
|---|
| 687 | grpsize = cols * rows |
|---|
| 688 | pageinfo['groupsize'] = grpsize |
|---|
| 689 | start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
|---|
| 690 | # int(current / grpsize) * grpsize +1)) |
|---|
| 691 | pageinfo['start'] = start |
|---|
| 692 | pageinfo['end'] = start + grpsize |
|---|
| 693 | if (docinfo is not None) and ('numPages' in docinfo): |
|---|
| 694 | np = int(docinfo['numPages']) |
|---|
| 695 | pageinfo['end'] = min(pageinfo['end'], np) |
|---|
| 696 | pageinfo['numgroups'] = int(np / grpsize) |
|---|
| 697 | if np % grpsize > 0: |
|---|
| 698 | pageinfo['numgroups'] += 1 |
|---|
| 699 | pageinfo['viewMode'] = viewMode |
|---|
| 700 | pageinfo['tocMode'] = tocMode |
|---|
| 701 | pageinfo['query'] = self.REQUEST.get('query',' ') |
|---|
| 702 | pageinfo['queryType'] = self.REQUEST.get('queryType',' ') |
|---|
| 703 | pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
|---|
| 704 | pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
|---|
| 705 | pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
|---|
| 706 | pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
|---|
| 707 | pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') |
|---|
| 708 | pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
|---|
| 709 | toc = int (pageinfo['tocPN']) |
|---|
| 710 | pageinfo['textPages'] =int (toc) |
|---|
| 711 | |
|---|
| 712 | if 'tocSize_%s'%tocMode in docinfo: |
|---|
| 713 | tocSize = int(docinfo['tocSize_%s'%tocMode]) |
|---|
| 714 | tocPageSize = int(pageinfo['tocPageSize']) |
|---|
| 715 | # cached toc |
|---|
| 716 | if tocSize%tocPageSize>0: |
|---|
| 717 | tocPages=tocSize/tocPageSize+1 |
|---|
| 718 | else: |
|---|
| 719 | tocPages=tocSize/tocPageSize |
|---|
| 720 | pageinfo['tocPN'] = min (tocPages,toc) |
|---|
| 721 | pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
|---|
| 722 | pageinfo['sn'] =self.REQUEST.get('sn','') |
|---|
| 723 | return pageinfo |
|---|
| 724 | |
|---|
| 725 | def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
|---|
| 726 | """init document viewer""" |
|---|
| 727 | self.title=title |
|---|
| 728 | self.digilibBaseUrl = digilibBaseUrl |
|---|
| 729 | self.thumbrows = thumbrows |
|---|
| 730 | self.thumbcols = thumbcols |
|---|
| 731 | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
|---|
| 732 | if RESPONSE is not None: |
|---|
| 733 | RESPONSE.redirect('manage_main') |
|---|
| 734 | |
|---|
| 735 | def manage_AddDocumentViewerForm(self): |
|---|
| 736 | """add the viewer form""" |
|---|
| 737 | pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
|---|
| 738 | return pt() |
|---|
| 739 | |
|---|
| 740 | def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
|---|
| 741 | """add the viewer""" |
|---|
| 742 | newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
|---|
| 743 | self._setObject(id,newObj) |
|---|
| 744 | |
|---|
| 745 | if RESPONSE is not None: |
|---|
| 746 | RESPONSE.redirect('manage_main') |
|---|
| 747 | |
|---|
| 748 | ## DocumentViewerTemplate class |
|---|
| 749 | class DocumentViewerTemplate(ZopePageTemplate): |
|---|
| 750 | """Template for document viewer""" |
|---|
| 751 | meta_type="DocumentViewer Template" |
|---|
| 752 | |
|---|
| 753 | |
|---|
| 754 | def manage_addDocumentViewerTemplateForm(self): |
|---|
| 755 | """Form for adding""" |
|---|
| 756 | pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) |
|---|
| 757 | return pt() |
|---|
| 758 | |
|---|
| 759 | def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, |
|---|
| 760 | REQUEST=None, submit=None): |
|---|
| 761 | "Add a Page Template with optional file content." |
|---|
| 762 | |
|---|
| 763 | self._setObject(id, DocumentViewerTemplate(id)) |
|---|
| 764 | ob = getattr(self, id) |
|---|
| 765 | txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
|---|
| 766 | logging.info("txt %s:"%txt) |
|---|
| 767 | ob.pt_edit(txt,"text/html") |
|---|
| 768 | if title: |
|---|
| 769 | ob.pt_setTitle(title) |
|---|
| 770 | try: |
|---|
| 771 | u = self.DestinationURL() |
|---|
| 772 | except AttributeError: |
|---|
| 773 | u = REQUEST['URL1'] |
|---|
| 774 | |
|---|
| 775 | u = "%s/%s" % (u, urllib.quote(id)) |
|---|
| 776 | REQUEST.RESPONSE.redirect(u+'/manage_main') |
|---|
| 777 | return '' |
|---|
| 778 | |
|---|
| 779 | |
|---|
| 780 | |
|---|