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 | if digilibBaseUrl is not None: |
---|
180 | self.digilibBaseUrl = digilibBaseUrl |
---|
181 | |
---|
182 | |
---|
183 | # proxy text server methods to fulltextclient |
---|
184 | def getTextPage(self, **args): |
---|
185 | """get page""" |
---|
186 | return self.template.fulltextclient.getTextPage(**args) |
---|
187 | |
---|
188 | def getOrigPages(self, **args): |
---|
189 | """get page""" |
---|
190 | return self.template.fulltextclient.getOrigPages(**args) |
---|
191 | |
---|
192 | def getOrigPagesNorm(self, **args): |
---|
193 | """get page""" |
---|
194 | return self.template.fulltextclient.getOrigPagesNorm(**args) |
---|
195 | |
---|
196 | def getQuery(self, **args): |
---|
197 | """get query in search""" |
---|
198 | return self.template.fulltextclient.getQuery(**args) |
---|
199 | |
---|
200 | def getSearch(self, **args): |
---|
201 | """get search""" |
---|
202 | return self.template.fulltextclient.getSearch(**args) |
---|
203 | |
---|
204 | def getGisPlaces(self, **args): |
---|
205 | """get gis places""" |
---|
206 | return self.template.fulltextclient.getGisPlaces(**args) |
---|
207 | |
---|
208 | def getAllGisPlaces(self, **args): |
---|
209 | """get all gis places """ |
---|
210 | return self.template.fulltextclient.getAllGisPlaces(**args) |
---|
211 | |
---|
212 | def getWordInfo(self, **args): |
---|
213 | """get translate""" |
---|
214 | return self.template.fulltextclient.getWordInfo(**args) |
---|
215 | |
---|
216 | def getLemma(self, **args): |
---|
217 | """get lemma""" |
---|
218 | return self.template.fulltextclient.getLemma(**args) |
---|
219 | |
---|
220 | def getLemmaQuery(self, **args): |
---|
221 | """get query""" |
---|
222 | return self.template.fulltextclient.getLemmaQuery(**args) |
---|
223 | |
---|
224 | def getLex(self, **args): |
---|
225 | """get lex""" |
---|
226 | return self.template.fulltextclient.getLex(**args) |
---|
227 | |
---|
228 | def getToc(self, **args): |
---|
229 | """get toc""" |
---|
230 | return self.template.fulltextclient.getToc(**args) |
---|
231 | |
---|
232 | def getTocPage(self, **args): |
---|
233 | """get tocpage""" |
---|
234 | return self.template.fulltextclient.getTocPage(**args) |
---|
235 | |
---|
236 | |
---|
237 | security.declareProtected('View','thumbs_rss') |
---|
238 | def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): |
---|
239 | ''' |
---|
240 | view it |
---|
241 | @param mode: defines how to access the document behind url |
---|
242 | @param url: url which contains display information |
---|
243 | @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
---|
244 | |
---|
245 | ''' |
---|
246 | logging.debug("HHHHHHHHHHHHHH:load the rss") |
---|
247 | logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
---|
248 | |
---|
249 | if not hasattr(self, 'template'): |
---|
250 | # create template folder if it doesn't exist |
---|
251 | self.manage_addFolder('template') |
---|
252 | |
---|
253 | if not self.digilibBaseUrl: |
---|
254 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
---|
255 | |
---|
256 | docinfo = self.getDocinfo(mode=mode,url=url) |
---|
257 | #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
---|
258 | pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) |
---|
259 | ''' ZDES ''' |
---|
260 | pt = getattr(self.template, 'thumbs_main_rss') |
---|
261 | |
---|
262 | if viewMode=="auto": # automodus gewaehlt |
---|
263 | if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
---|
264 | viewMode="text" |
---|
265 | else: |
---|
266 | viewMode="images" |
---|
267 | |
---|
268 | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
---|
269 | |
---|
270 | |
---|
271 | security.declareProtected('View','index_html') |
---|
272 | def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1): |
---|
273 | """ |
---|
274 | view page |
---|
275 | @param url: url which contains display information |
---|
276 | @param mode: defines how to access the document behind url |
---|
277 | @param viewMode: 'images': display images, 'text': display text, default is 'auto' |
---|
278 | @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text' |
---|
279 | @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
---|
280 | """ |
---|
281 | |
---|
282 | logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewType=%s start=%s pn=%s"%(mode,url,viewMode,viewType,start,pn)) |
---|
283 | |
---|
284 | if not hasattr(self, 'template'): |
---|
285 | # this won't work |
---|
286 | logging.error("template folder missing!") |
---|
287 | return "ERROR: template folder missing!" |
---|
288 | |
---|
289 | if not getattr(self, 'digilibBaseUrl', None): |
---|
290 | self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
---|
291 | |
---|
292 | docinfo = self.getDocinfo(mode=mode,url=url) |
---|
293 | |
---|
294 | if tocMode != "thumbs": |
---|
295 | # get table of contents |
---|
296 | docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
---|
297 | |
---|
298 | # auto viewMode: text if there is a text else images |
---|
299 | if viewMode=="auto": |
---|
300 | if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): |
---|
301 | viewMode = "text" |
---|
302 | viewType = "dict" |
---|
303 | else: |
---|
304 | viewMode = "images" |
---|
305 | |
---|
306 | elif viewMode == "text_dict": |
---|
307 | # legacy fix |
---|
308 | viewMode = "text" |
---|
309 | viewType = "dict" |
---|
310 | |
---|
311 | # stringify viewType |
---|
312 | if isinstance(viewType, list): |
---|
313 | logging.debug("index_html: viewType is list:%s"%viewType) |
---|
314 | viewType = ','.join([t for t in viewType if t]) |
---|
315 | |
---|
316 | pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode) |
---|
317 | |
---|
318 | # get template /template/viewer_$viewMode |
---|
319 | pt = getattr(self.template, 'viewer_%s'%viewMode, None) |
---|
320 | if pt is None: |
---|
321 | logging.error("No template for viewMode=%s!"%viewMode) |
---|
322 | # TODO: error page? |
---|
323 | return "No template for viewMode=%s!"%viewMode |
---|
324 | |
---|
325 | # and execute with parameters |
---|
326 | return pt(docinfo=docinfo, pageinfo=pageinfo) |
---|
327 | |
---|
328 | def generateMarks(self,mk): |
---|
329 | ret="" |
---|
330 | if mk is None: |
---|
331 | return "" |
---|
332 | if not isinstance(mk, list): |
---|
333 | mk=[mk] |
---|
334 | for m in mk: |
---|
335 | ret+="mk=%s"%m |
---|
336 | return ret |
---|
337 | |
---|
338 | |
---|
339 | def getBrowser(self): |
---|
340 | """getBrowser the version of browser """ |
---|
341 | bt = browserCheck(self) |
---|
342 | logging.debug("BROWSER VERSION: %s"%(bt)) |
---|
343 | return bt |
---|
344 | |
---|
345 | def findDigilibUrl(self): |
---|
346 | """try to get the digilib URL from zogilib""" |
---|
347 | url = self.template.zogilib.getDLBaseUrl() |
---|
348 | return url |
---|
349 | |
---|
350 | def getDocumentViewerURL(self): |
---|
351 | """returns the URL of this instance""" |
---|
352 | return self.absolute_url() |
---|
353 | |
---|
354 | def getStyle(self, idx, selected, style=""): |
---|
355 | """returns a string with the given style and append 'sel' if path == selected.""" |
---|
356 | #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
---|
357 | if idx == selected: |
---|
358 | return style + 'sel' |
---|
359 | else: |
---|
360 | return style |
---|
361 | |
---|
362 | def getParams(self, param=None, val=None, params=None, duplicates=None): |
---|
363 | """returns dict with URL parameters. |
---|
364 | |
---|
365 | Takes URL parameters and additionally param=val or dict params. |
---|
366 | Deletes key if value is None.""" |
---|
367 | # copy existing request params |
---|
368 | newParams=self.REQUEST.form.copy() |
---|
369 | # change single param |
---|
370 | if param is not None: |
---|
371 | if val is None: |
---|
372 | if newParams.has_key(param): |
---|
373 | del newParams[param] |
---|
374 | else: |
---|
375 | newParams[param] = str(val) |
---|
376 | |
---|
377 | # change more params |
---|
378 | if params is not None: |
---|
379 | for (k, v) in params.items(): |
---|
380 | if v is None: |
---|
381 | # val=None removes param |
---|
382 | if newParams.has_key(k): |
---|
383 | del newParams[k] |
---|
384 | |
---|
385 | else: |
---|
386 | newParams[k] = v |
---|
387 | |
---|
388 | if duplicates: |
---|
389 | # eliminate lists (coming from duplicate keys) |
---|
390 | for (k,v) in newParams.items(): |
---|
391 | if isinstance(v, list): |
---|
392 | if duplicates == 'comma': |
---|
393 | # make comma-separated list of non-empty entries |
---|
394 | newParams[k] = ','.join([t for t in v if t]) |
---|
395 | elif duplicates == 'first': |
---|
396 | # take first non-empty entry |
---|
397 | newParams[k] = [t for t in v if t][0] |
---|
398 | |
---|
399 | return newParams |
---|
400 | |
---|
401 | def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'): |
---|
402 | """returns URL to documentviewer with parameter param set to val or from dict params""" |
---|
403 | urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates) |
---|
404 | # quote values and assemble into query string (not escaping '/') |
---|
405 | ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()]) |
---|
406 | if baseUrl is None: |
---|
407 | baseUrl = self.getDocumentViewerURL() |
---|
408 | |
---|
409 | url = "%s?%s"%(baseUrl, ps) |
---|
410 | return url |
---|
411 | |
---|
412 | def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'): |
---|
413 | """link to documentviewer with parameter param set to val""" |
---|
414 | return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&', duplicates=duplicates) |
---|
415 | |
---|
416 | |
---|
417 | def getInfo_xml(self,url,mode): |
---|
418 | """returns info about the document as XML""" |
---|
419 | if not self.digilibBaseUrl: |
---|
420 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
---|
421 | |
---|
422 | docinfo = self.getDocinfo(mode=mode,url=url) |
---|
423 | pt = getattr(self.template, 'info_xml') |
---|
424 | return pt(docinfo=docinfo) |
---|
425 | |
---|
426 | def isAccessible(self, docinfo): |
---|
427 | """returns if access to the resource is granted""" |
---|
428 | access = docinfo.get('accessType', None) |
---|
429 | logging.debug("documentViewer (accessOK) access type %s"%access) |
---|
430 | if access == 'free': |
---|
431 | logging.debug("documentViewer (accessOK) access is free") |
---|
432 | return True |
---|
433 | |
---|
434 | elif access is None or access in self.authgroups: |
---|
435 | # only local access -- only logged in users |
---|
436 | user = getSecurityManager().getUser() |
---|
437 | logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
---|
438 | if user is not None: |
---|
439 | #print "user: ", user |
---|
440 | return (user.getUserName() != "Anonymous User") |
---|
441 | else: |
---|
442 | return False |
---|
443 | |
---|
444 | logging.error("documentViewer (accessOK) unknown access type %s"%access) |
---|
445 | return False |
---|
446 | |
---|
447 | |
---|
448 | |
---|
449 | def getDocinfo(self, mode, url): |
---|
450 | """returns docinfo depending on mode""" |
---|
451 | logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) |
---|
452 | # look for cached docinfo in session |
---|
453 | if self.REQUEST.SESSION.has_key('docinfo'): |
---|
454 | docinfo = self.REQUEST.SESSION['docinfo'] |
---|
455 | # check if its still current |
---|
456 | if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: |
---|
457 | logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) |
---|
458 | return docinfo |
---|
459 | |
---|
460 | # new docinfo |
---|
461 | docinfo = {'mode': mode, 'url': url} |
---|
462 | # add self url |
---|
463 | docinfo['viewerUrl'] = self.getDocumentViewerURL() |
---|
464 | docinfo['digilibBaseUrl'] = self.digilibBaseUrl |
---|
465 | # get index.meta DOM |
---|
466 | docUrl = None |
---|
467 | metaDom = None |
---|
468 | if mode=="texttool": |
---|
469 | # url points to document dir or index.meta |
---|
470 | metaDom = self.metadataService.getDomFromPathOrUrl(url) |
---|
471 | docUrl = url.replace('/index.meta', '') |
---|
472 | if metaDom is None: |
---|
473 | raise IOError("Unable to find index.meta for mode=texttool!") |
---|
474 | |
---|
475 | elif mode=="imagepath": |
---|
476 | # url points to folder with images, index.meta optional |
---|
477 | # asssume index.meta in parent dir |
---|
478 | docUrl = getParentPath(url) |
---|
479 | metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
---|
480 | |
---|
481 | elif mode=="filepath": |
---|
482 | # url points to image file, index.meta optional |
---|
483 | # asssume index.meta is two path segments up |
---|
484 | docUrl = getParentPath(url, 2) |
---|
485 | metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
---|
486 | |
---|
487 | else: |
---|
488 | logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
---|
489 | raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
---|
490 | |
---|
491 | docinfo['documentUrl'] = docUrl |
---|
492 | # process index.meta contents |
---|
493 | if metaDom is not None and metaDom.tag == 'resource': |
---|
494 | # document directory name and path |
---|
495 | resource = self.metadataService.getResourceData(dom=metaDom) |
---|
496 | if resource: |
---|
497 | docinfo = self.getDocinfoFromResource(docinfo, resource) |
---|
498 | |
---|
499 | # texttool info |
---|
500 | texttool = self.metadataService.getTexttoolData(dom=metaDom) |
---|
501 | if texttool: |
---|
502 | docinfo = self.getDocinfoFromTexttool(docinfo, texttool) |
---|
503 | |
---|
504 | # bib info |
---|
505 | bib = self.metadataService.getBibData(dom=metaDom) |
---|
506 | if bib: |
---|
507 | docinfo = self.getDocinfoFromBib(docinfo, bib) |
---|
508 | else: |
---|
509 | # no bib - try info.xml |
---|
510 | docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) |
---|
511 | |
---|
512 | # auth info |
---|
513 | access = self.metadataService.getAccessData(dom=metaDom) |
---|
514 | if access: |
---|
515 | docinfo = self.getDocinfoFromAccess(docinfo, access) |
---|
516 | |
---|
517 | # attribution info |
---|
518 | attribution = self.metadataService.getAttributionData(dom=metaDom) |
---|
519 | if attribution: |
---|
520 | logging.debug("getDocinfo: attribution=%s"%repr(attribution)) |
---|
521 | docinfo['attribution'] = attribution |
---|
522 | #docinfo = self.getDocinfoFromAccess(docinfo, access) |
---|
523 | |
---|
524 | # copyright info |
---|
525 | copyright = self.metadataService.getCopyrightData(dom=metaDom) |
---|
526 | if copyright: |
---|
527 | logging.debug("getDocinfo: copyright=%s"%repr(copyright)) |
---|
528 | docinfo['copyright'] = copyright |
---|
529 | #docinfo = self.getDocinfoFromAccess(docinfo, access) |
---|
530 | |
---|
531 | # image path |
---|
532 | if mode != 'texttool': |
---|
533 | # override image path from texttool with url |
---|
534 | docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1) |
---|
535 | |
---|
536 | |
---|
537 | |
---|
538 | # number of images from digilib |
---|
539 | if docinfo.get('imagePath', None): |
---|
540 | docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath'] |
---|
541 | docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath']) |
---|
542 | |
---|
543 | logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
---|
544 | #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
---|
545 | # store in session |
---|
546 | self.REQUEST.SESSION['docinfo'] = docinfo |
---|
547 | return docinfo |
---|
548 | |
---|
549 | def getDocinfoFromResource(self, docinfo, resource): |
---|
550 | """reads contents of resource element into docinfo""" |
---|
551 | docName = resource.get('name', None) |
---|
552 | docinfo['documentName'] = docName |
---|
553 | docPath = resource.get('archive-path', None) |
---|
554 | if docPath: |
---|
555 | # clean up document path |
---|
556 | if docPath[0] != '/': |
---|
557 | docPath = '/' + docPath |
---|
558 | |
---|
559 | if docName and (not docPath.endswith(docName)): |
---|
560 | docPath += "/" + docName |
---|
561 | |
---|
562 | else: |
---|
563 | # use docUrl as docPath |
---|
564 | docUrl = docinfo['documentURL'] |
---|
565 | if not docUrl.startswith('http:'): |
---|
566 | docPath = docUrl |
---|
567 | if docPath: |
---|
568 | # fix URLs starting with /mpiwg/online |
---|
569 | docPath = docPath.replace('/mpiwg/online', '', 1) |
---|
570 | |
---|
571 | docinfo['documentPath'] = docPath |
---|
572 | return docinfo |
---|
573 | |
---|
574 | def getDocinfoFromTexttool(self, docinfo, texttool): |
---|
575 | """reads contents of texttool element into docinfo""" |
---|
576 | # image dir |
---|
577 | imageDir = texttool.get('image', None) |
---|
578 | docPath = docinfo.get('documentPath', None) |
---|
579 | if imageDir and docPath: |
---|
580 | #print "image: ", imageDir, " archivepath: ", archivePath |
---|
581 | imageDir = os.path.join(docPath, imageDir) |
---|
582 | imageDir = imageDir.replace('/mpiwg/online', '', 1) |
---|
583 | docinfo['imagePath'] = imageDir |
---|
584 | |
---|
585 | # old style text URL |
---|
586 | textUrl = texttool.get('text', None) |
---|
587 | if textUrl and docPath: |
---|
588 | if urlparse.urlparse(textUrl)[0] == "": #keine url |
---|
589 | textUrl = os.path.join(docPath, textUrl) |
---|
590 | |
---|
591 | docinfo['textURL'] = textUrl |
---|
592 | |
---|
593 | # new style text-url-path |
---|
594 | textUrl = texttool.get('text-url-path', None) |
---|
595 | if textUrl: |
---|
596 | docinfo['textURLPath'] = textUrl |
---|
597 | |
---|
598 | # page flow |
---|
599 | docinfo['pageFlow'] = texttool.get('page-flow', 'ltr') |
---|
600 | |
---|
601 | # odd pages are left |
---|
602 | docinfo['oddPage'] = texttool.get('odd-scan-position', 'left') |
---|
603 | |
---|
604 | # number of title page (0: not defined) |
---|
605 | docinfo['titlePage'] = texttool.get('title-scan-no', 0) |
---|
606 | |
---|
607 | # old presentation stuff |
---|
608 | presentation = texttool.get('presentation', None) |
---|
609 | if presentation and docPath: |
---|
610 | if presentation.startswith('http:'): |
---|
611 | docinfo['presentationUrl'] = presentation |
---|
612 | else: |
---|
613 | docinfo['presentationUrl'] = os.path.join(docPath, presentation) |
---|
614 | |
---|
615 | |
---|
616 | return docinfo |
---|
617 | |
---|
618 | def getDocinfoFromBib(self, docinfo, bib): |
---|
619 | """reads contents of bib element into docinfo""" |
---|
620 | logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
---|
621 | # put all raw bib fields in dict "bib" |
---|
622 | docinfo['bib'] = bib |
---|
623 | bibtype = bib.get('@type', None) |
---|
624 | docinfo['bibType'] = bibtype |
---|
625 | # also store DC metadata for convenience |
---|
626 | dc = self.metadataService.getDCMappedData(bib) |
---|
627 | docinfo['creator'] = dc.get('creator',None) |
---|
628 | docinfo['title'] = dc.get('title',None) |
---|
629 | docinfo['date'] = dc.get('date',None) |
---|
630 | return docinfo |
---|
631 | |
---|
632 | def getDocinfoFromAccess(self, docinfo, acc): |
---|
633 | """reads contents of access element into docinfo""" |
---|
634 | #TODO: also read resource type |
---|
635 | logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
---|
636 | try: |
---|
637 | acctype = acc['@attr']['type'] |
---|
638 | if acctype: |
---|
639 | access=acctype |
---|
640 | if access in ['group', 'institution']: |
---|
641 | access = acc['name'].lower() |
---|
642 | |
---|
643 | docinfo['accessType'] = access |
---|
644 | |
---|
645 | except: |
---|
646 | pass |
---|
647 | |
---|
648 | return docinfo |
---|
649 | |
---|
650 | def getDocinfoFromDigilib(self, docinfo, path): |
---|
651 | infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
---|
652 | # fetch data |
---|
653 | txt = getHttpData(infoUrl) |
---|
654 | if not txt: |
---|
655 | logging.error("Unable to get dir-info from %s"%(infoUrl)) |
---|
656 | return docinfo |
---|
657 | |
---|
658 | dom = ET.fromstring(txt) |
---|
659 | size = getText(dom.find("size")) |
---|
660 | logging.debug("getDocinfoFromDigilib: size=%s"%size) |
---|
661 | if size: |
---|
662 | docinfo['numPages'] = int(size) |
---|
663 | else: |
---|
664 | docinfo['numPages'] = 0 |
---|
665 | |
---|
666 | # TODO: produce and keep list of image names and numbers |
---|
667 | return docinfo |
---|
668 | |
---|
669 | |
---|
670 | def getDocinfoFromPresentationInfoXml(self,docinfo): |
---|
671 | """gets DC-like bibliographical information from the presentation entry in texttools""" |
---|
672 | url = docinfo.get('presentationUrl', None) |
---|
673 | if not url: |
---|
674 | logging.error("getDocinfoFromPresentation: no URL!") |
---|
675 | return docinfo |
---|
676 | |
---|
677 | dom = None |
---|
678 | metaUrl = None |
---|
679 | if url.startswith("http://"): |
---|
680 | # real URL |
---|
681 | metaUrl = url |
---|
682 | else: |
---|
683 | # online path |
---|
684 | |
---|
685 | server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
---|
686 | metaUrl=server+url |
---|
687 | |
---|
688 | txt=getHttpData(metaUrl) |
---|
689 | if txt is None: |
---|
690 | logging.error("Unable to read info.xml from %s"%(url)) |
---|
691 | return docinfo |
---|
692 | |
---|
693 | dom = ET.fromstring(txt) |
---|
694 | docinfo['creator']=getText(dom.find(".//author")) |
---|
695 | docinfo['title']=getText(dom.find(".//title")) |
---|
696 | docinfo['date']=getText(dom.find(".//date")) |
---|
697 | return docinfo |
---|
698 | |
---|
699 | |
---|
700 | def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None): |
---|
701 | """returns pageinfo with the given parameters""" |
---|
702 | logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewType=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewType,tocMode)) |
---|
703 | pageinfo = {} |
---|
704 | pageinfo['viewMode'] = viewMode |
---|
705 | pageinfo['viewType'] = viewType |
---|
706 | pageinfo['tocMode'] = tocMode |
---|
707 | |
---|
708 | current = getInt(current) |
---|
709 | pageinfo['current'] = current |
---|
710 | rows = int(rows or self.thumbrows) |
---|
711 | pageinfo['rows'] = rows |
---|
712 | cols = int(cols or self.thumbcols) |
---|
713 | pageinfo['cols'] = cols |
---|
714 | grpsize = cols * rows |
---|
715 | pageinfo['groupsize'] = grpsize |
---|
716 | # is start is empty use one around current |
---|
717 | start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
---|
718 | # int(current / grpsize) * grpsize +1)) |
---|
719 | pageinfo['start'] = start |
---|
720 | pn = self.REQUEST.get('pn','1') |
---|
721 | pageinfo['pn'] = pn |
---|
722 | np = int(docinfo.get('numPages', 0)) |
---|
723 | if np == 0: |
---|
724 | # numPages unknown - maybe we can get it from text page |
---|
725 | if docinfo.get('textURLPath', None): |
---|
726 | # cache text page as well |
---|
727 | pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=pn, docinfo=docinfo, pageinfo=pageinfo) |
---|
728 | np = int(docinfo.get('numPages', 0)) |
---|
729 | |
---|
730 | pageinfo['numgroups'] = int(np / grpsize) |
---|
731 | if np % grpsize > 0: |
---|
732 | pageinfo['numgroups'] += 1 |
---|
733 | |
---|
734 | pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl' |
---|
735 | oddScanLeft = docinfo.get('oddPage', 'left') != 'right' |
---|
736 | # add zeroth page for two columns |
---|
737 | pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft)) |
---|
738 | pageinfo['pageZero'] = pageZero |
---|
739 | pageinfo['pageList'] = self.getPageList(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np) |
---|
740 | |
---|
741 | pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
---|
742 | pageinfo['query'] = self.REQUEST.get('query','') |
---|
743 | pageinfo['queryType'] = self.REQUEST.get('queryType','') |
---|
744 | pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
---|
745 | pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
---|
746 | pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30)) |
---|
747 | pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10)) |
---|
748 | pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1')) |
---|
749 | pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1')) |
---|
750 | |
---|
751 | # limit tocPN |
---|
752 | if 'tocSize_%s'%tocMode in docinfo: |
---|
753 | tocSize = docinfo['tocSize_%s'%tocMode] |
---|
754 | tocPageSize = pageinfo['tocPageSize'] |
---|
755 | # cached toc |
---|
756 | if tocSize%tocPageSize>0: |
---|
757 | tocPages=tocSize/tocPageSize+1 |
---|
758 | else: |
---|
759 | tocPages=tocSize/tocPageSize |
---|
760 | |
---|
761 | pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN']) |
---|
762 | |
---|
763 | return pageinfo |
---|
764 | |
---|
765 | |
---|
766 | def getPageList(self, start=None, rows=None, cols=None, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0): |
---|
767 | """returns array of page informations for one screenfull of thumbnails""" |
---|
768 | if maxIdx == 0: |
---|
769 | maxIdx = start + rows * cols |
---|
770 | |
---|
771 | pages = [] |
---|
772 | if pageZero and start == 1: |
---|
773 | # correct beginning |
---|
774 | idx = 0 |
---|
775 | else: |
---|
776 | idx = start |
---|
777 | |
---|
778 | for r in range(rows): |
---|
779 | row = [] |
---|
780 | for c in range(cols): |
---|
781 | if idx < minIdx or idx > maxIdx: |
---|
782 | page = {'idx':None} |
---|
783 | else: |
---|
784 | page = {'idx':idx} |
---|
785 | |
---|
786 | idx += 1 |
---|
787 | if pageFlowLtr: |
---|
788 | row.append(page) |
---|
789 | else: |
---|
790 | row.insert(0, page) |
---|
791 | |
---|
792 | pages.append(row) |
---|
793 | |
---|
794 | logging.debug("getPageList returns=%s"%(pages)) |
---|
795 | return pages |
---|
796 | |
---|
797 | |
---|
798 | security.declareProtected('View management screens','changeDocumentViewerForm') |
---|
799 | changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
---|
800 | |
---|
801 | def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
---|
802 | """init document viewer""" |
---|
803 | self.title=title |
---|
804 | self.digilibBaseUrl = digilibBaseUrl |
---|
805 | self.thumbrows = thumbrows |
---|
806 | self.thumbcols = thumbcols |
---|
807 | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
---|
808 | try: |
---|
809 | # assume MetaDataFolder instance is called metadata |
---|
810 | self.metadataService = getattr(self, 'metadata') |
---|
811 | except Exception, e: |
---|
812 | logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) |
---|
813 | |
---|
814 | if RESPONSE is not None: |
---|
815 | RESPONSE.redirect('manage_main') |
---|
816 | |
---|
817 | def manage_AddDocumentViewerForm(self): |
---|
818 | """add the viewer form""" |
---|
819 | pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
---|
820 | return pt() |
---|
821 | |
---|
822 | def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
---|
823 | """add the viewer""" |
---|
824 | newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
---|
825 | self._setObject(id,newObj) |
---|
826 | |
---|
827 | if RESPONSE is not None: |
---|
828 | RESPONSE.redirect('manage_main') |
---|
829 | |
---|
830 | ## DocumentViewerTemplate class |
---|
831 | class DocumentViewerTemplate(ZopePageTemplate): |
---|
832 | """Template for document viewer""" |
---|
833 | meta_type="DocumentViewer Template" |
---|
834 | |
---|
835 | |
---|
836 | def manage_addDocumentViewerTemplateForm(self): |
---|
837 | """Form for adding""" |
---|
838 | pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) |
---|
839 | return pt() |
---|
840 | |
---|
841 | def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, |
---|
842 | REQUEST=None, submit=None): |
---|
843 | "Add a Page Template with optional file content." |
---|
844 | |
---|
845 | self._setObject(id, DocumentViewerTemplate(id)) |
---|
846 | ob = getattr(self, id) |
---|
847 | txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
---|
848 | logging.info("txt %s:"%txt) |
---|
849 | ob.pt_edit(txt,"text/html") |
---|
850 | if title: |
---|
851 | ob.pt_setTitle(title) |
---|
852 | try: |
---|
853 | u = self.DestinationURL() |
---|
854 | except AttributeError: |
---|
855 | u = REQUEST['URL1'] |
---|
856 | |
---|
857 | u = "%s/%s" % (u, urllib.quote(id)) |
---|
858 | REQUEST.RESPONSE.redirect(u+'/manage_main') |
---|
859 | return '' |
---|
860 | |
---|
861 | |
---|
862 | |
---|