| 1 | from OFS.Folder import Folder |
|---|
| 2 | from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate |
|---|
| 3 | from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
|---|
| 4 | from AccessControl import ClassSecurityInfo |
|---|
| 5 | from AccessControl import getSecurityManager |
|---|
| 6 | from Globals import package_home |
|---|
| 7 | |
|---|
| 8 | #from Ft.Xml import EMPTY_NAMESPACE, Parse |
|---|
| 9 | #import Ft.Xml.Domlette |
|---|
| 10 | |
|---|
| 11 | import xml.etree.ElementTree as ET |
|---|
| 12 | |
|---|
| 13 | import os.path |
|---|
| 14 | import sys |
|---|
| 15 | import urllib |
|---|
| 16 | import logging |
|---|
| 17 | import math |
|---|
| 18 | import urlparse |
|---|
| 19 | import re |
|---|
| 20 | import string |
|---|
| 21 | |
|---|
| 22 | from SrvTxtUtils import getInt, getText, getHttpData |
|---|
| 23 | |
|---|
| 24 | def logger(txt,method,txt2): |
|---|
| 25 | """logging""" |
|---|
| 26 | logging.info(txt+ txt2) |
|---|
| 27 | |
|---|
| 28 | |
|---|
| 29 | def serializeNode(node, encoding="utf-8"): |
|---|
| 30 | """returns a string containing node as XML""" |
|---|
| 31 | s = ET.tostring(node) |
|---|
| 32 | |
|---|
| 33 | # 4Suite: |
|---|
| 34 | # stream = cStringIO.StringIO() |
|---|
| 35 | # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
|---|
| 36 | # s = stream.getvalue() |
|---|
| 37 | # stream.close() |
|---|
| 38 | return s |
|---|
| 39 | |
|---|
| 40 | def browserCheck(self): |
|---|
| 41 | """check the browsers request to find out the browser type""" |
|---|
| 42 | bt = {} |
|---|
| 43 | ua = self.REQUEST.get_header("HTTP_USER_AGENT") |
|---|
| 44 | bt['ua'] = ua |
|---|
| 45 | bt['isIE'] = False |
|---|
| 46 | bt['isN4'] = False |
|---|
| 47 | bt['versFirefox']="" |
|---|
| 48 | bt['versIE']="" |
|---|
| 49 | bt['versSafariChrome']="" |
|---|
| 50 | bt['versOpera']="" |
|---|
| 51 | |
|---|
| 52 | if string.find(ua, 'MSIE') > -1: |
|---|
| 53 | bt['isIE'] = True |
|---|
| 54 | else: |
|---|
| 55 | bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) |
|---|
| 56 | # Safari oder Chrome identification |
|---|
| 57 | try: |
|---|
| 58 | nav = ua[string.find(ua, '('):] |
|---|
| 59 | nav1=ua[string.find(ua,')'):] |
|---|
| 60 | nav2=nav1[string.find(nav1,'('):] |
|---|
| 61 | nav3=nav2[string.find(nav2,')'):] |
|---|
| 62 | ie = string.split(nav, "; ")[1] |
|---|
| 63 | ie1 =string.split(nav1, " ")[2] |
|---|
| 64 | ie2 =string.split(nav3, " ")[1] |
|---|
| 65 | ie3 =string.split(nav3, " ")[2] |
|---|
| 66 | if string.find(ie3, "Safari") >-1: |
|---|
| 67 | bt['versSafariChrome']=string.split(ie2, "/")[1] |
|---|
| 68 | except: pass |
|---|
| 69 | # IE identification |
|---|
| 70 | try: |
|---|
| 71 | nav = ua[string.find(ua, '('):] |
|---|
| 72 | ie = string.split(nav, "; ")[1] |
|---|
| 73 | if string.find(ie, "MSIE") > -1: |
|---|
| 74 | bt['versIE'] = string.split(ie, " ")[1] |
|---|
| 75 | except:pass |
|---|
| 76 | # Firefox identification |
|---|
| 77 | try: |
|---|
| 78 | nav = ua[string.find(ua, '('):] |
|---|
| 79 | nav1=ua[string.find(ua,')'):] |
|---|
| 80 | if string.find(ie1, "Firefox") >-1: |
|---|
| 81 | nav5= string.split(ie1, "/")[1] |
|---|
| 82 | logging.debug("FIREFOX: %s"%(nav5)) |
|---|
| 83 | bt['versFirefox']=nav5[0:3] |
|---|
| 84 | except:pass |
|---|
| 85 | #Opera identification |
|---|
| 86 | try: |
|---|
| 87 | if string.find(ua,"Opera") >-1: |
|---|
| 88 | nav = ua[string.find(ua, '('):] |
|---|
| 89 | nav1=nav[string.find(nav,')'):] |
|---|
| 90 | bt['versOpera']=string.split(nav1,"/")[2] |
|---|
| 91 | except:pass |
|---|
| 92 | |
|---|
| 93 | bt['isMac'] = string.find(ua, 'Macintosh') > -1 |
|---|
| 94 | bt['isWin'] = string.find(ua, 'Windows') > -1 |
|---|
| 95 | bt['isIEWin'] = bt['isIE'] and bt['isWin'] |
|---|
| 96 | bt['isIEMac'] = bt['isIE'] and bt['isMac'] |
|---|
| 97 | bt['staticHTML'] = False |
|---|
| 98 | |
|---|
| 99 | return bt |
|---|
| 100 | |
|---|
| 101 | def getParentPath(path, cnt=1): |
|---|
| 102 | """returns pathname shortened by cnt""" |
|---|
| 103 | # make sure path doesn't end with / |
|---|
| 104 | path = path.rstrip('/') |
|---|
| 105 | # split by /, shorten, and reassemble |
|---|
| 106 | return '/'.join(path.split('/')[0:-cnt]) |
|---|
| 107 | |
|---|
| 108 | |
|---|
| 109 | ## |
|---|
| 110 | ## documentViewer class |
|---|
| 111 | ## |
|---|
| 112 | class documentViewer(Folder): |
|---|
| 113 | """document viewer""" |
|---|
| 114 | meta_type="Document viewer" |
|---|
| 115 | |
|---|
| 116 | security=ClassSecurityInfo() |
|---|
| 117 | manage_options=Folder.manage_options+( |
|---|
| 118 | {'label':'main config','action':'changeDocumentViewerForm'}, |
|---|
| 119 | ) |
|---|
| 120 | |
|---|
| 121 | metadataService = None |
|---|
| 122 | """MetaDataFolder instance""" |
|---|
| 123 | |
|---|
| 124 | # templates and forms |
|---|
| 125 | viewer_main = PageTemplateFile('zpt/viewer_main', globals()) |
|---|
| 126 | toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) |
|---|
| 127 | toc_text = PageTemplateFile('zpt/toc_text', globals()) |
|---|
| 128 | toc_figures = PageTemplateFile('zpt/toc_figures', globals()) |
|---|
| 129 | page_main_images = PageTemplateFile('zpt/page_main_images', globals()) |
|---|
| 130 | page_main_double = PageTemplateFile('zpt/page_main_double', globals()) |
|---|
| 131 | page_main_text = PageTemplateFile('zpt/page_main_text', globals()) |
|---|
| 132 | page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
|---|
| 133 | page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) |
|---|
| 134 | page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) |
|---|
| 135 | page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals()) |
|---|
| 136 | head_main = PageTemplateFile('zpt/head_main', globals()) |
|---|
| 137 | docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) |
|---|
| 138 | info_xml = PageTemplateFile('zpt/info_xml', globals()) |
|---|
| 139 | |
|---|
| 140 | |
|---|
| 141 | thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
|---|
| 142 | |
|---|
| 143 | |
|---|
| 144 | def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
|---|
| 145 | """init document viewer""" |
|---|
| 146 | self.id=id |
|---|
| 147 | self.title=title |
|---|
| 148 | self.thumbcols = thumbcols |
|---|
| 149 | self.thumbrows = thumbrows |
|---|
| 150 | # authgroups is list of authorized groups (delimited by ,) |
|---|
| 151 | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
|---|
| 152 | # create template folder so we can always use template.something |
|---|
| 153 | |
|---|
| 154 | templateFolder = Folder('template') |
|---|
| 155 | #self['template'] = templateFolder # Zope-2.12 style |
|---|
| 156 | self._setObject('template',templateFolder) # old style |
|---|
| 157 | try: |
|---|
| 158 | import MpdlXmlTextServer |
|---|
| 159 | textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
|---|
| 160 | #templateFolder['fulltextclient'] = xmlRpcClient |
|---|
| 161 | templateFolder._setObject('fulltextclient',textServer) |
|---|
| 162 | except Exception, e: |
|---|
| 163 | logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
|---|
| 164 | |
|---|
| 165 | try: |
|---|
| 166 | from Products.zogiLib.zogiLib import zogiLib |
|---|
| 167 | zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
|---|
| 168 | #templateFolder['zogilib'] = zogilib |
|---|
| 169 | templateFolder._setObject('zogilib',zogilib) |
|---|
| 170 | except Exception, e: |
|---|
| 171 | logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
|---|
| 172 | |
|---|
| 173 | try: |
|---|
| 174 | # assume MetaDataFolder instance is called metadata |
|---|
| 175 | self.metadataService = getattr(self, 'metadata') |
|---|
| 176 | except Exception, e: |
|---|
| 177 | logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) |
|---|
| 178 | |
|---|
| 179 | |
|---|
| 180 | # proxy text server methods to fulltextclient |
|---|
| 181 | def getTextPage(self, **args): |
|---|
| 182 | """get page""" |
|---|
| 183 | return self.template.fulltextclient.getTextPage(**args) |
|---|
| 184 | |
|---|
| 185 | def getOrigPages(self, **args): |
|---|
| 186 | """get page""" |
|---|
| 187 | return self.template.fulltextclient.getOrigPages(**args) |
|---|
| 188 | |
|---|
| 189 | def getOrigPagesNorm(self, **args): |
|---|
| 190 | """get page""" |
|---|
| 191 | return self.template.fulltextclient.getOrigPagesNorm(**args) |
|---|
| 192 | |
|---|
| 193 | def getQuery(self, **args): |
|---|
| 194 | """get query in search""" |
|---|
| 195 | return self.template.fulltextclient.getQuery(**args) |
|---|
| 196 | |
|---|
| 197 | def getSearch(self, **args): |
|---|
| 198 | """get search""" |
|---|
| 199 | return self.template.fulltextclient.getSearch(**args) |
|---|
| 200 | |
|---|
| 201 | def getGisPlaces(self, **args): |
|---|
| 202 | """get gis places""" |
|---|
| 203 | return self.template.fulltextclient.getGisPlaces(**args) |
|---|
| 204 | |
|---|
| 205 | def getAllGisPlaces(self, **args): |
|---|
| 206 | """get all gis places """ |
|---|
| 207 | return self.template.fulltextclient.getAllGisPlaces(**args) |
|---|
| 208 | |
|---|
| 209 | def getTranslate(self, **args): |
|---|
| 210 | """get translate""" |
|---|
| 211 | return self.template.fulltextclient.getTranslate(**args) |
|---|
| 212 | |
|---|
| 213 | def getLemma(self, **args): |
|---|
| 214 | """get lemma""" |
|---|
| 215 | return self.template.fulltextclient.getLemma(**args) |
|---|
| 216 | |
|---|
| 217 | def getLemmaQuery(self, **args): |
|---|
| 218 | """get query""" |
|---|
| 219 | return self.template.fulltextclient.getLemmaQuery(**args) |
|---|
| 220 | |
|---|
| 221 | def getLex(self, **args): |
|---|
| 222 | """get lex""" |
|---|
| 223 | return self.template.fulltextclient.getLex(**args) |
|---|
| 224 | |
|---|
| 225 | def getToc(self, **args): |
|---|
| 226 | """get toc""" |
|---|
| 227 | return self.template.fulltextclient.getToc(**args) |
|---|
| 228 | |
|---|
| 229 | def getTocPage(self, **args): |
|---|
| 230 | """get tocpage""" |
|---|
| 231 | return self.template.fulltextclient.getTocPage(**args) |
|---|
| 232 | |
|---|
| 233 | |
|---|
| 234 | security.declareProtected('View','thumbs_rss') |
|---|
| 235 | def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): |
|---|
| 236 | ''' |
|---|
| 237 | view it |
|---|
| 238 | @param mode: defines how to access the document behind url |
|---|
| 239 | @param url: url which contains display information |
|---|
| 240 | @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
|---|
| 241 | |
|---|
| 242 | ''' |
|---|
| 243 | logging.debug("HHHHHHHHHHHHHH:load the rss") |
|---|
| 244 | logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
|---|
| 245 | |
|---|
| 246 | if not hasattr(self, 'template'): |
|---|
| 247 | # create template folder if it doesn't exist |
|---|
| 248 | self.manage_addFolder('template') |
|---|
| 249 | |
|---|
| 250 | if not self.digilibBaseUrl: |
|---|
| 251 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
|---|
| 252 | |
|---|
| 253 | docinfo = self.getDocinfo(mode=mode,url=url) |
|---|
| 254 | #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
|---|
| 255 | pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) |
|---|
| 256 | ''' ZDES ''' |
|---|
| 257 | pt = getattr(self.template, 'thumbs_main_rss') |
|---|
| 258 | |
|---|
| 259 | if viewMode=="auto": # automodus gewaehlt |
|---|
| 260 | if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
|---|
| 261 | viewMode="text" |
|---|
| 262 | else: |
|---|
| 263 | viewMode="images" |
|---|
| 264 | |
|---|
| 265 | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
|---|
| 266 | |
|---|
| 267 | |
|---|
| 268 | security.declareProtected('View','index_html') |
|---|
| 269 | def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1): |
|---|
| 270 | """ |
|---|
| 271 | view page |
|---|
| 272 | @param url: url which contains display information |
|---|
| 273 | @param mode: defines how to access the document behind url |
|---|
| 274 | @param viewMode: 'images': display images, 'text': display text, default is 'auto' |
|---|
| 275 | @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text' |
|---|
| 276 | @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
|---|
| 277 | """ |
|---|
| 278 | |
|---|
| 279 | logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
|---|
| 280 | |
|---|
| 281 | if not hasattr(self, 'template'): |
|---|
| 282 | # this won't work |
|---|
| 283 | logging.error("template folder missing!") |
|---|
| 284 | return "ERROR: template folder missing!" |
|---|
| 285 | |
|---|
| 286 | if not getattr(self, 'digilibBaseUrl', None): |
|---|
| 287 | self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
|---|
| 288 | |
|---|
| 289 | docinfo = self.getDocinfo(mode=mode,url=url) |
|---|
| 290 | |
|---|
| 291 | if tocMode != "thumbs": |
|---|
| 292 | # get table of contents |
|---|
| 293 | docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
|---|
| 294 | |
|---|
| 295 | # auto viewMode: text if there is a text else images |
|---|
| 296 | if viewMode=="auto": |
|---|
| 297 | if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): |
|---|
| 298 | viewMode = "text" |
|---|
| 299 | viewType = "dict" |
|---|
| 300 | else: |
|---|
| 301 | viewMode = "images" |
|---|
| 302 | |
|---|
| 303 | pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode) |
|---|
| 304 | |
|---|
| 305 | # get template /template/viewer_main |
|---|
| 306 | pt = getattr(self.template, 'viewer_main') |
|---|
| 307 | # and execute with parameters |
|---|
| 308 | return pt(docinfo=docinfo, pageinfo=pageinfo) |
|---|
| 309 | |
|---|
| 310 | def generateMarks(self,mk): |
|---|
| 311 | ret="" |
|---|
| 312 | if mk is None: |
|---|
| 313 | return "" |
|---|
| 314 | if not isinstance(mk, list): |
|---|
| 315 | mk=[mk] |
|---|
| 316 | for m in mk: |
|---|
| 317 | ret+="mk=%s"%m |
|---|
| 318 | return ret |
|---|
| 319 | |
|---|
| 320 | |
|---|
| 321 | def getBrowser(self): |
|---|
| 322 | """getBrowser the version of browser """ |
|---|
| 323 | bt = browserCheck(self) |
|---|
| 324 | logging.debug("BROWSER VERSION: %s"%(bt)) |
|---|
| 325 | return bt |
|---|
| 326 | |
|---|
| 327 | def findDigilibUrl(self): |
|---|
| 328 | """try to get the digilib URL from zogilib""" |
|---|
| 329 | url = self.template.zogilib.getDLBaseUrl() |
|---|
| 330 | return url |
|---|
| 331 | |
|---|
| 332 | def getDocumentViewerURL(self): |
|---|
| 333 | """returns the URL of this instance""" |
|---|
| 334 | return self.absolute_url() |
|---|
| 335 | |
|---|
| 336 | def getStyle(self, idx, selected, style=""): |
|---|
| 337 | """returns a string with the given style and append 'sel' if path == selected.""" |
|---|
| 338 | #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
|---|
| 339 | if idx == selected: |
|---|
| 340 | return style + 'sel' |
|---|
| 341 | else: |
|---|
| 342 | return style |
|---|
| 343 | |
|---|
| 344 | def getParams(self, param=None, val=None, params=None): |
|---|
| 345 | """returns dict with URL parameters. |
|---|
| 346 | |
|---|
| 347 | Takes URL parameters and additionally param=val or dict params. |
|---|
| 348 | Deletes key if value is None.""" |
|---|
| 349 | # copy existing request params |
|---|
| 350 | newParams=self.REQUEST.form.copy() |
|---|
| 351 | # change single param |
|---|
| 352 | if param is not None: |
|---|
| 353 | if val is None: |
|---|
| 354 | if newParams.has_key(param): |
|---|
| 355 | del newParams[param] |
|---|
| 356 | else: |
|---|
| 357 | newParams[param] = str(val) |
|---|
| 358 | |
|---|
| 359 | # change more params |
|---|
| 360 | if params is not None: |
|---|
| 361 | for k in params.keys(): |
|---|
| 362 | v = params[k] |
|---|
| 363 | if v is None: |
|---|
| 364 | # val=None removes param |
|---|
| 365 | if newParams.has_key(k): |
|---|
| 366 | del newParams[k] |
|---|
| 367 | |
|---|
| 368 | else: |
|---|
| 369 | newParams[k] = v |
|---|
| 370 | |
|---|
| 371 | return newParams |
|---|
| 372 | |
|---|
| 373 | def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'): |
|---|
| 374 | """returns URL to documentviewer with parameter param set to val or from dict params""" |
|---|
| 375 | urlParams = self.getParams(param=param, val=val, params=params) |
|---|
| 376 | # quote values and assemble into query string (not escaping '/') |
|---|
| 377 | ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()]) |
|---|
| 378 | if baseUrl is None: |
|---|
| 379 | baseUrl = self.getDocumentViewerURL() |
|---|
| 380 | |
|---|
| 381 | url = "%s?%s"%(baseUrl, ps) |
|---|
| 382 | return url |
|---|
| 383 | |
|---|
| 384 | def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None): |
|---|
| 385 | """link to documentviewer with parameter param set to val""" |
|---|
| 386 | return self.getLink(param, val, params, baseUrl, '&') |
|---|
| 387 | |
|---|
| 388 | |
|---|
| 389 | def getInfo_xml(self,url,mode): |
|---|
| 390 | """returns info about the document as XML""" |
|---|
| 391 | if not self.digilibBaseUrl: |
|---|
| 392 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
|---|
| 393 | |
|---|
| 394 | docinfo = self.getDocinfo(mode=mode,url=url) |
|---|
| 395 | pt = getattr(self.template, 'info_xml') |
|---|
| 396 | return pt(docinfo=docinfo) |
|---|
| 397 | |
|---|
| 398 | def isAccessible(self, docinfo): |
|---|
| 399 | """returns if access to the resource is granted""" |
|---|
| 400 | access = docinfo.get('accessType', None) |
|---|
| 401 | logging.debug("documentViewer (accessOK) access type %s"%access) |
|---|
| 402 | if access == 'free': |
|---|
| 403 | logging.debug("documentViewer (accessOK) access is free") |
|---|
| 404 | return True |
|---|
| 405 | |
|---|
| 406 | elif access is None or access in self.authgroups: |
|---|
| 407 | # only local access -- only logged in users |
|---|
| 408 | user = getSecurityManager().getUser() |
|---|
| 409 | logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
|---|
| 410 | if user is not None: |
|---|
| 411 | #print "user: ", user |
|---|
| 412 | return (user.getUserName() != "Anonymous User") |
|---|
| 413 | else: |
|---|
| 414 | return False |
|---|
| 415 | |
|---|
| 416 | logging.error("documentViewer (accessOK) unknown access type %s"%access) |
|---|
| 417 | return False |
|---|
| 418 | |
|---|
| 419 | |
|---|
| 420 | |
|---|
| 421 | def getDocinfo(self, mode, url): |
|---|
| 422 | """returns docinfo depending on mode""" |
|---|
| 423 | logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) |
|---|
| 424 | # look for cached docinfo in session |
|---|
| 425 | if self.REQUEST.SESSION.has_key('docinfo'): |
|---|
| 426 | docinfo = self.REQUEST.SESSION['docinfo'] |
|---|
| 427 | # check if its still current |
|---|
| 428 | if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: |
|---|
| 429 | logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) |
|---|
| 430 | return docinfo |
|---|
| 431 | |
|---|
| 432 | # new docinfo |
|---|
| 433 | docinfo = {'mode': mode, 'url': url} |
|---|
| 434 | # add self url |
|---|
| 435 | docinfo['viewerUrl'] = self.getDocumentViewerURL() |
|---|
| 436 | # get index.meta DOM |
|---|
| 437 | docUrl = None |
|---|
| 438 | metaDom = None |
|---|
| 439 | if mode=="texttool": |
|---|
| 440 | # url points to document dir or index.meta |
|---|
| 441 | metaDom = self.metadataService.getDomFromPathOrUrl(url) |
|---|
| 442 | docUrl = url.replace('/index.meta', '') |
|---|
| 443 | if metaDom is None: |
|---|
| 444 | raise IOError("Unable to find index.meta for mode=texttool!") |
|---|
| 445 | |
|---|
| 446 | elif mode=="imagepath": |
|---|
| 447 | # url points to folder with images, index.meta optional |
|---|
| 448 | # asssume index.meta in parent dir |
|---|
| 449 | docUrl = getParentPath(url) |
|---|
| 450 | metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
|---|
| 451 | |
|---|
| 452 | elif mode=="filepath": |
|---|
| 453 | # url points to image file, index.meta optional |
|---|
| 454 | # asssume index.meta is two path segments up |
|---|
| 455 | docUrl = getParentPath(url, 2) |
|---|
| 456 | metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
|---|
| 457 | |
|---|
| 458 | else: |
|---|
| 459 | logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
|---|
| 460 | raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
|---|
| 461 | |
|---|
| 462 | docinfo['documentUrl'] = docUrl |
|---|
| 463 | # process index.meta contents |
|---|
| 464 | if metaDom is not None and metaDom.tag == 'resource': |
|---|
| 465 | # document directory name and path |
|---|
| 466 | resource = self.metadataService.getResourceData(dom=metaDom) |
|---|
| 467 | if resource: |
|---|
| 468 | docinfo = self.getDocinfoFromResource(docinfo, resource) |
|---|
| 469 | |
|---|
| 470 | # texttool info |
|---|
| 471 | texttool = self.metadataService.getTexttoolData(dom=metaDom) |
|---|
| 472 | if texttool: |
|---|
| 473 | docinfo = self.getDocinfoFromTexttool(docinfo, texttool) |
|---|
| 474 | |
|---|
| 475 | # bib info |
|---|
| 476 | bib = self.metadataService.getBibData(dom=metaDom) |
|---|
| 477 | if bib: |
|---|
| 478 | docinfo = self.getDocinfoFromBib(docinfo, bib) |
|---|
| 479 | else: |
|---|
| 480 | # no bib - try info.xml |
|---|
| 481 | docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) |
|---|
| 482 | |
|---|
| 483 | # auth info |
|---|
| 484 | access = self.metadataService.getAccessData(dom=metaDom) |
|---|
| 485 | if access: |
|---|
| 486 | docinfo = self.getDocinfoFromAccess(docinfo, access) |
|---|
| 487 | |
|---|
| 488 | # attribution info |
|---|
| 489 | attribution = self.metadataService.getAttributionData(dom=metaDom) |
|---|
| 490 | if attribution: |
|---|
| 491 | logging.debug("getDocinfo: attribution=%s"%repr(attribution)) |
|---|
| 492 | docinfo['attribution'] = attribution |
|---|
| 493 | #docinfo = self.getDocinfoFromAccess(docinfo, access) |
|---|
| 494 | |
|---|
| 495 | # copyright info |
|---|
| 496 | copyright = self.metadataService.getCopyrightData(dom=metaDom) |
|---|
| 497 | if copyright: |
|---|
| 498 | logging.debug("getDocinfo: copyright=%s"%repr(copyright)) |
|---|
| 499 | docinfo['copyright'] = copyright |
|---|
| 500 | #docinfo = self.getDocinfoFromAccess(docinfo, access) |
|---|
| 501 | |
|---|
| 502 | # image path |
|---|
| 503 | if mode != 'texttool': |
|---|
| 504 | # override image path from texttool |
|---|
| 505 | docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1) |
|---|
| 506 | |
|---|
| 507 | # number of images from digilib |
|---|
| 508 | if docinfo.get('imagePath', None): |
|---|
| 509 | docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath'] |
|---|
| 510 | docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath']) |
|---|
| 511 | |
|---|
| 512 | logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
|---|
| 513 | #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
|---|
| 514 | # store in session |
|---|
| 515 | self.REQUEST.SESSION['docinfo'] = docinfo |
|---|
| 516 | return docinfo |
|---|
| 517 | |
|---|
| 518 | def getDocinfoFromResource(self, docinfo, resource): |
|---|
| 519 | """reads contents of resource element into docinfo""" |
|---|
| 520 | docName = resource.get('name', None) |
|---|
| 521 | docinfo['documentName'] = docName |
|---|
| 522 | docPath = resource.get('archive-path', None) |
|---|
| 523 | if docPath: |
|---|
| 524 | # clean up document path |
|---|
| 525 | if docPath[0] != '/': |
|---|
| 526 | docPath = '/' + docPath |
|---|
| 527 | |
|---|
| 528 | if docName and (not docPath.endswith(docName)): |
|---|
| 529 | docPath += "/" + docName |
|---|
| 530 | |
|---|
| 531 | else: |
|---|
| 532 | # use docUrl as docPath |
|---|
| 533 | docUrl = docinfo['documentURL'] |
|---|
| 534 | if not docUrl.startswith('http:'): |
|---|
| 535 | docPath = docUrl |
|---|
| 536 | if docPath: |
|---|
| 537 | # fix URLs starting with /mpiwg/online |
|---|
| 538 | docPath = docPath.replace('/mpiwg/online', '', 1) |
|---|
| 539 | |
|---|
| 540 | docinfo['documentPath'] = docPath |
|---|
| 541 | return docinfo |
|---|
| 542 | |
|---|
| 543 | def getDocinfoFromTexttool(self, docinfo, texttool): |
|---|
| 544 | """reads contents of texttool element into docinfo""" |
|---|
| 545 | # image dir |
|---|
| 546 | imageDir = texttool.get('image', None) |
|---|
| 547 | docPath = docinfo.get('documentPath', None) |
|---|
| 548 | if imageDir and docPath: |
|---|
| 549 | #print "image: ", imageDir, " archivepath: ", archivePath |
|---|
| 550 | imageDir = os.path.join(docPath, imageDir) |
|---|
| 551 | imageDir = imageDir.replace('/mpiwg/online', '', 1) |
|---|
| 552 | docinfo['imagePath'] = imageDir |
|---|
| 553 | |
|---|
| 554 | # old style text URL |
|---|
| 555 | textUrl = texttool.get('text', None) |
|---|
| 556 | if textUrl and docPath: |
|---|
| 557 | if urlparse.urlparse(textUrl)[0] == "": #keine url |
|---|
| 558 | textUrl = os.path.join(docPath, textUrl) |
|---|
| 559 | |
|---|
| 560 | docinfo['textURL'] = textUrl |
|---|
| 561 | |
|---|
| 562 | # new style text-url-path |
|---|
| 563 | textUrl = texttool.get('text-url-path', None) |
|---|
| 564 | if textUrl: |
|---|
| 565 | docinfo['textURLPath'] = textUrl |
|---|
| 566 | |
|---|
| 567 | # page flow |
|---|
| 568 | docinfo['pageFlow'] = texttool.get('page-flow', 'ltr') |
|---|
| 569 | |
|---|
| 570 | # odd pages are left |
|---|
| 571 | docinfo['oddPage'] = texttool.get('odd-scan-orientation', 'left') |
|---|
| 572 | |
|---|
| 573 | # number of title page (0: not defined) |
|---|
| 574 | docinfo['titlePage'] = texttool.get('title-scan-no', 0) |
|---|
| 575 | |
|---|
| 576 | # old presentation stuff |
|---|
| 577 | presentation = texttool.get('presentation', None) |
|---|
| 578 | if presentation and docPath: |
|---|
| 579 | if presentation.startswith('http:'): |
|---|
| 580 | docinfo['presentationUrl'] = presentation |
|---|
| 581 | else: |
|---|
| 582 | docinfo['presentationUrl'] = os.path.join(docPath, presentation) |
|---|
| 583 | |
|---|
| 584 | |
|---|
| 585 | return docinfo |
|---|
| 586 | |
|---|
| 587 | def getDocinfoFromBib(self, docinfo, bib): |
|---|
| 588 | """reads contents of bib element into docinfo""" |
|---|
| 589 | logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
|---|
| 590 | # put all raw bib fields in dict "bib" |
|---|
| 591 | docinfo['bib'] = bib |
|---|
| 592 | bibtype = bib.get('@type', None) |
|---|
| 593 | docinfo['bibType'] = bibtype |
|---|
| 594 | # also store DC metadata for convenience |
|---|
| 595 | dc = self.metadataService.getDCMappedData(bib) |
|---|
| 596 | docinfo['creator'] = dc.get('creator',None) |
|---|
| 597 | docinfo['title'] = dc.get('title',None) |
|---|
| 598 | docinfo['date'] = dc.get('date',None) |
|---|
| 599 | return docinfo |
|---|
| 600 | |
|---|
| 601 | def getDocinfoFromAccess(self, docinfo, acc): |
|---|
| 602 | """reads contents of access element into docinfo""" |
|---|
| 603 | #TODO: also read resource type |
|---|
| 604 | logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
|---|
| 605 | try: |
|---|
| 606 | acctype = acc['@attr']['type'] |
|---|
| 607 | if acctype: |
|---|
| 608 | access=acctype |
|---|
| 609 | if access in ['group', 'institution']: |
|---|
| 610 | access = acc['name'].lower() |
|---|
| 611 | |
|---|
| 612 | docinfo['accessType'] = access |
|---|
| 613 | |
|---|
| 614 | except: |
|---|
| 615 | pass |
|---|
| 616 | |
|---|
| 617 | return docinfo |
|---|
| 618 | |
|---|
| 619 | def getDocinfoFromDigilib(self, docinfo, path): |
|---|
| 620 | infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
|---|
| 621 | # fetch data |
|---|
| 622 | txt = getHttpData(infoUrl) |
|---|
| 623 | if not txt: |
|---|
| 624 | logging.error("Unable to get dir-info from %s"%(infoUrl)) |
|---|
| 625 | return docinfo |
|---|
| 626 | |
|---|
| 627 | dom = ET.fromstring(txt) |
|---|
| 628 | size = getText(dom.find("size")) |
|---|
| 629 | logging.debug("getDocinfoFromDigilib: size=%s"%size) |
|---|
| 630 | if size: |
|---|
| 631 | docinfo['numPages'] = int(size) |
|---|
| 632 | else: |
|---|
| 633 | docinfo['numPages'] = 0 |
|---|
| 634 | |
|---|
| 635 | # TODO: produce and keep list of image names and numbers |
|---|
| 636 | return docinfo |
|---|
| 637 | |
|---|
| 638 | |
|---|
| 639 | def getDocinfoFromPresentationInfoXml(self,docinfo): |
|---|
| 640 | """gets DC-like bibliographical information from the presentation entry in texttools""" |
|---|
| 641 | url = docinfo.get('presentationUrl', None) |
|---|
| 642 | if not url: |
|---|
| 643 | logging.error("getDocinfoFromPresentation: no URL!") |
|---|
| 644 | return docinfo |
|---|
| 645 | |
|---|
| 646 | dom = None |
|---|
| 647 | metaUrl = None |
|---|
| 648 | if url.startswith("http://"): |
|---|
| 649 | # real URL |
|---|
| 650 | metaUrl = url |
|---|
| 651 | else: |
|---|
| 652 | # online path |
|---|
| 653 | |
|---|
| 654 | server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
|---|
| 655 | metaUrl=server+url |
|---|
| 656 | |
|---|
| 657 | txt=getHttpData(metaUrl) |
|---|
| 658 | if txt is None: |
|---|
| 659 | logging.error("Unable to read info.xml from %s"%(url)) |
|---|
| 660 | return docinfo |
|---|
| 661 | |
|---|
| 662 | dom = ET.fromstring(txt) |
|---|
| 663 | docinfo['creator']=getText(dom.find(".//author")) |
|---|
| 664 | docinfo['title']=getText(dom.find(".//title")) |
|---|
| 665 | docinfo['date']=getText(dom.find(".//date")) |
|---|
| 666 | return docinfo |
|---|
| 667 | |
|---|
| 668 | |
|---|
| 669 | def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None): |
|---|
| 670 | """returns pageinfo with the given parameters""" |
|---|
| 671 | pageinfo = {} |
|---|
| 672 | pageinfo['viewMode'] = viewMode |
|---|
| 673 | pageinfo['viewType'] = viewType |
|---|
| 674 | pageinfo['tocMode'] = tocMode |
|---|
| 675 | |
|---|
| 676 | current = getInt(current) |
|---|
| 677 | pageinfo['current'] = current |
|---|
| 678 | rows = int(rows or self.thumbrows) |
|---|
| 679 | pageinfo['rows'] = rows |
|---|
| 680 | cols = int(cols or self.thumbcols) |
|---|
| 681 | pageinfo['cols'] = cols |
|---|
| 682 | grpsize = cols * rows |
|---|
| 683 | pageinfo['groupsize'] = grpsize |
|---|
| 684 | # what does this do? |
|---|
| 685 | start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
|---|
| 686 | # int(current / grpsize) * grpsize +1)) |
|---|
| 687 | pageinfo['start'] = start |
|---|
| 688 | pageinfo['end'] = start + grpsize |
|---|
| 689 | pn = self.REQUEST.get('pn','1') |
|---|
| 690 | pageinfo['pn'] = pn |
|---|
| 691 | np = int(docinfo.get('numPages', 0)) |
|---|
| 692 | if np == 0: |
|---|
| 693 | # numPages unknown - maybe we can get it from text page |
|---|
| 694 | if docinfo.get('textURLPath', None): |
|---|
| 695 | # cache text page as well |
|---|
| 696 | pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=pn, docinfo=docinfo, pageinfo=pageinfo) |
|---|
| 697 | np = int(docinfo.get('numPages', 0)) |
|---|
| 698 | |
|---|
| 699 | pageinfo['end'] = min(pageinfo['end'], np) |
|---|
| 700 | pageinfo['numgroups'] = int(np / grpsize) |
|---|
| 701 | if np % grpsize > 0: |
|---|
| 702 | pageinfo['numgroups'] += 1 |
|---|
| 703 | |
|---|
| 704 | pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
|---|
| 705 | pageinfo['query'] = self.REQUEST.get('query','') |
|---|
| 706 | pageinfo['queryType'] = self.REQUEST.get('queryType','') |
|---|
| 707 | pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
|---|
| 708 | pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
|---|
| 709 | pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
|---|
| 710 | pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') |
|---|
| 711 | pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
|---|
| 712 | # WTF?: |
|---|
| 713 | toc = int(pageinfo['tocPN']) |
|---|
| 714 | pageinfo['textPages'] = int(toc) |
|---|
| 715 | |
|---|
| 716 | # What does this do? |
|---|
| 717 | if 'tocSize_%s'%tocMode in docinfo: |
|---|
| 718 | tocSize = int(docinfo['tocSize_%s'%tocMode]) |
|---|
| 719 | tocPageSize = int(pageinfo['tocPageSize']) |
|---|
| 720 | # cached toc |
|---|
| 721 | if tocSize%tocPageSize>0: |
|---|
| 722 | tocPages=tocSize/tocPageSize+1 |
|---|
| 723 | else: |
|---|
| 724 | tocPages=tocSize/tocPageSize |
|---|
| 725 | |
|---|
| 726 | pageinfo['tocPN'] = min(tocPages,toc) |
|---|
| 727 | |
|---|
| 728 | pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
|---|
| 729 | return pageinfo |
|---|
| 730 | |
|---|
| 731 | |
|---|
| 732 | security.declareProtected('View management screens','changeDocumentViewerForm') |
|---|
| 733 | changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
|---|
| 734 | |
|---|
| 735 | def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
|---|
| 736 | """init document viewer""" |
|---|
| 737 | self.title=title |
|---|
| 738 | self.digilibBaseUrl = digilibBaseUrl |
|---|
| 739 | self.thumbrows = thumbrows |
|---|
| 740 | self.thumbcols = thumbcols |
|---|
| 741 | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
|---|
| 742 | try: |
|---|
| 743 | # assume MetaDataFolder instance is called metadata |
|---|
| 744 | self.metadataService = getattr(self, 'metadata') |
|---|
| 745 | except Exception, e: |
|---|
| 746 | logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) |
|---|
| 747 | |
|---|
| 748 | if RESPONSE is not None: |
|---|
| 749 | RESPONSE.redirect('manage_main') |
|---|
| 750 | |
|---|
| 751 | def manage_AddDocumentViewerForm(self): |
|---|
| 752 | """add the viewer form""" |
|---|
| 753 | pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
|---|
| 754 | return pt() |
|---|
| 755 | |
|---|
| 756 | def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
|---|
| 757 | """add the viewer""" |
|---|
| 758 | newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
|---|
| 759 | self._setObject(id,newObj) |
|---|
| 760 | |
|---|
| 761 | if RESPONSE is not None: |
|---|
| 762 | RESPONSE.redirect('manage_main') |
|---|
| 763 | |
|---|
| 764 | ## DocumentViewerTemplate class |
|---|
| 765 | class DocumentViewerTemplate(ZopePageTemplate): |
|---|
| 766 | """Template for document viewer""" |
|---|
| 767 | meta_type="DocumentViewer Template" |
|---|
| 768 | |
|---|
| 769 | |
|---|
| 770 | def manage_addDocumentViewerTemplateForm(self): |
|---|
| 771 | """Form for adding""" |
|---|
| 772 | pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) |
|---|
| 773 | return pt() |
|---|
| 774 | |
|---|
| 775 | def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, |
|---|
| 776 | REQUEST=None, submit=None): |
|---|
| 777 | "Add a Page Template with optional file content." |
|---|
| 778 | |
|---|
| 779 | self._setObject(id, DocumentViewerTemplate(id)) |
|---|
| 780 | ob = getattr(self, id) |
|---|
| 781 | txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
|---|
| 782 | logging.info("txt %s:"%txt) |
|---|
| 783 | ob.pt_edit(txt,"text/html") |
|---|
| 784 | if title: |
|---|
| 785 | ob.pt_setTitle(title) |
|---|
| 786 | try: |
|---|
| 787 | u = self.DestinationURL() |
|---|
| 788 | except AttributeError: |
|---|
| 789 | u = REQUEST['URL1'] |
|---|
| 790 | |
|---|
| 791 | u = "%s/%s" % (u, urllib.quote(id)) |
|---|
| 792 | REQUEST.RESPONSE.redirect(u+'/manage_main') |
|---|
| 793 | return '' |
|---|
| 794 | |
|---|
| 795 | |
|---|
| 796 | |
|---|