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 | from Products.zogiLib import browserCheck |
---|
9 | |
---|
10 | from Ft.Xml import EMPTY_NAMESPACE, Parse |
---|
11 | import Ft.Xml.Domlette |
---|
12 | import os.path |
---|
13 | import sys |
---|
14 | import urllib |
---|
15 | import urllib2 |
---|
16 | import logging |
---|
17 | import math |
---|
18 | import urlparse |
---|
19 | import cStringIO |
---|
20 | import re |
---|
21 | |
---|
22 | |
---|
23 | def logger(txt,method,txt2): |
---|
24 | """logging""" |
---|
25 | logging.info(txt+ txt2) |
---|
26 | |
---|
27 | |
---|
28 | def getInt(number, default=0): |
---|
29 | """returns always an int (0 in case of problems)""" |
---|
30 | try: |
---|
31 | return int(number) |
---|
32 | except: |
---|
33 | return int(default) |
---|
34 | |
---|
35 | def getTextFromNode(nodename): |
---|
36 | """get the cdata content of a node""" |
---|
37 | if nodename is None: |
---|
38 | return "" |
---|
39 | nodelist=nodename.childNodes |
---|
40 | rc = "" |
---|
41 | for node in nodelist: |
---|
42 | if node.nodeType == node.TEXT_NODE: |
---|
43 | rc = rc + node.data |
---|
44 | return rc |
---|
45 | |
---|
46 | def serializeNode(node, encoding='utf-8'): |
---|
47 | """returns a string containing node as XML""" |
---|
48 | buf = cStringIO.StringIO() |
---|
49 | Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding) |
---|
50 | s = buf.getvalue() |
---|
51 | buf.close() |
---|
52 | return s |
---|
53 | |
---|
54 | |
---|
55 | def getParentDir(path): |
---|
56 | """returns pathname shortened by one""" |
---|
57 | return '/'.join(path.split('/')[0:-1]) |
---|
58 | |
---|
59 | |
---|
60 | def getHttpData(url, data=None, num_tries=3, timeout=10): |
---|
61 | """returns result from url+data HTTP request""" |
---|
62 | # we do GET (by appending data to url) |
---|
63 | if isinstance(data, str) or isinstance(data, unicode): |
---|
64 | # if data is string then append |
---|
65 | url = "%s?%s"%(url,data) |
---|
66 | elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): |
---|
67 | # urlencode |
---|
68 | url = "%s?%s"%(url,urllib.urlencode(data)) |
---|
69 | |
---|
70 | response = None |
---|
71 | errmsg = None |
---|
72 | for cnt in range(num_tries): |
---|
73 | try: |
---|
74 | logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) |
---|
75 | if sys.version_info < (2, 6): |
---|
76 | # set timeout on socket -- ugly :-( |
---|
77 | import socket |
---|
78 | socket.setdefaulttimeout(float(timeout)) |
---|
79 | response = urllib2.urlopen(url) |
---|
80 | else: |
---|
81 | response = urllib2.urlopen(url,timeout=float(timeout)) |
---|
82 | # check result? |
---|
83 | break |
---|
84 | except urllib2.HTTPError, e: |
---|
85 | logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) |
---|
86 | errmsg = str(e) |
---|
87 | # stop trying |
---|
88 | break |
---|
89 | except urllib2.URLError, e: |
---|
90 | logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) |
---|
91 | errmsg = str(e) |
---|
92 | # stop trying |
---|
93 | #break |
---|
94 | |
---|
95 | if response is not None: |
---|
96 | data = response.read() |
---|
97 | response.close() |
---|
98 | return data |
---|
99 | |
---|
100 | raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) |
---|
101 | #return None |
---|
102 | |
---|
103 | |
---|
104 | |
---|
105 | ## |
---|
106 | ## documentViewer class |
---|
107 | ## |
---|
108 | class documentViewer(Folder): |
---|
109 | """document viewer""" |
---|
110 | meta_type="Document viewer" |
---|
111 | |
---|
112 | security=ClassSecurityInfo() |
---|
113 | manage_options=Folder.manage_options+( |
---|
114 | {'label':'main config','action':'changeDocumentViewerForm'}, |
---|
115 | ) |
---|
116 | |
---|
117 | # templates and forms |
---|
118 | viewer_main = PageTemplateFile('zpt/viewer_main', globals()) |
---|
119 | toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) |
---|
120 | toc_text = PageTemplateFile('zpt/toc_text', globals()) |
---|
121 | toc_figures = PageTemplateFile('zpt/toc_figures', globals()) |
---|
122 | page_main_images = PageTemplateFile('zpt/page_main_images', globals()) |
---|
123 | page_main_text = PageTemplateFile('zpt/page_main_text', globals()) |
---|
124 | page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
---|
125 | page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) |
---|
126 | page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) |
---|
127 | head_main = PageTemplateFile('zpt/head_main', globals()) |
---|
128 | docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) |
---|
129 | info_xml = PageTemplateFile('zpt/info_xml', globals()) |
---|
130 | |
---|
131 | |
---|
132 | thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
---|
133 | security.declareProtected('View management screens','changeDocumentViewerForm') |
---|
134 | changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
---|
135 | |
---|
136 | |
---|
137 | def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
---|
138 | """init document viewer""" |
---|
139 | self.id=id |
---|
140 | self.title=title |
---|
141 | self.thumbcols = thumbcols |
---|
142 | self.thumbrows = thumbrows |
---|
143 | # authgroups is list of authorized groups (delimited by ,) |
---|
144 | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
---|
145 | # create template folder so we can always use template.something |
---|
146 | |
---|
147 | templateFolder = Folder('template') |
---|
148 | #self['template'] = templateFolder # Zope-2.12 style |
---|
149 | self._setObject('template',templateFolder) # old style |
---|
150 | try: |
---|
151 | import MpdlXmlTextServer |
---|
152 | textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
---|
153 | #templateFolder['fulltextclient'] = xmlRpcClient |
---|
154 | templateFolder._setObject('fulltextclient',textServer) |
---|
155 | except Exception, e: |
---|
156 | logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
---|
157 | try: |
---|
158 | from Products.zogiLib.zogiLib import zogiLib |
---|
159 | zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
---|
160 | #templateFolder['zogilib'] = zogilib |
---|
161 | templateFolder._setObject('zogilib',zogilib) |
---|
162 | except Exception, e: |
---|
163 | logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
---|
164 | |
---|
165 | |
---|
166 | # proxy text server methods to fulltextclient |
---|
167 | def getTextPage(self, **args): |
---|
168 | """get page""" |
---|
169 | return self.template.fulltextclient.getTextPage(**args) |
---|
170 | |
---|
171 | def getQuery(self, **args): |
---|
172 | """get query""" |
---|
173 | return self.template.fulltextclient.getQuery(**args) |
---|
174 | |
---|
175 | def getSearch(self, **args): |
---|
176 | """get search""" |
---|
177 | return self.template.fulltextclient.getSearch(**args) |
---|
178 | |
---|
179 | def getNumPages(self, docinfo): |
---|
180 | """get numpages""" |
---|
181 | return self.template.fulltextclient.getNumPages(docinfo) |
---|
182 | |
---|
183 | def getNumTextPages(self, docinfo): |
---|
184 | """get numpages text""" |
---|
185 | return self.template.fulltextclient.getNumTextPages(docinfo) |
---|
186 | |
---|
187 | def getTranslate(self, **args): |
---|
188 | """get translate""" |
---|
189 | return self.template.fulltextclient.getTranslate(**args) |
---|
190 | |
---|
191 | def getLemma(self, **args): |
---|
192 | """get lemma""" |
---|
193 | return self.template.fulltextclient.getLemma(**args) |
---|
194 | |
---|
195 | def getToc(self, **args): |
---|
196 | """get toc""" |
---|
197 | return self.template.fulltextclient.getToc(**args) |
---|
198 | |
---|
199 | def getTocPage(self, **args): |
---|
200 | """get tocpage""" |
---|
201 | return self.template.fulltextclient.getTocPage(**args) |
---|
202 | |
---|
203 | |
---|
204 | security.declareProtected('View','thumbs_rss') |
---|
205 | def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): |
---|
206 | ''' |
---|
207 | view it |
---|
208 | @param mode: defines how to access the document behind url |
---|
209 | @param url: url which contains display information |
---|
210 | @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
---|
211 | |
---|
212 | ''' |
---|
213 | logging.debug("HHHHHHHHHHHHHH:load the rss") |
---|
214 | logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
---|
215 | |
---|
216 | if not hasattr(self, 'template'): |
---|
217 | # create template folder if it doesn't exist |
---|
218 | self.manage_addFolder('template') |
---|
219 | |
---|
220 | if not self.digilibBaseUrl: |
---|
221 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
---|
222 | |
---|
223 | docinfo = self.getDocinfo(mode=mode,url=url) |
---|
224 | pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
---|
225 | pt = getattr(self.template, 'thumbs_main_rss') |
---|
226 | |
---|
227 | if viewMode=="auto": # automodus gewaehlt |
---|
228 | if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert |
---|
229 | viewMode="text" |
---|
230 | else: |
---|
231 | viewMode="images" |
---|
232 | |
---|
233 | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
---|
234 | |
---|
235 | security.declareProtected('View','index_html') |
---|
236 | def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""): |
---|
237 | ''' |
---|
238 | view it |
---|
239 | @param mode: defines how to access the document behind url |
---|
240 | @param url: url which contains display information |
---|
241 | @param viewMode: if images display images, if text display text, default is auto (text,images or auto) |
---|
242 | @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
---|
243 | @param characterNormalization type of text display (reg, norm, none) |
---|
244 | @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) |
---|
245 | ''' |
---|
246 | |
---|
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 | # this won't work |
---|
251 | logging.error("template folder missing!") |
---|
252 | return "ERROR: template folder missing!" |
---|
253 | |
---|
254 | if not getattr(self, 'digilibBaseUrl', None): |
---|
255 | self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
---|
256 | |
---|
257 | docinfo = self.getDocinfo(mode=mode,url=url) |
---|
258 | |
---|
259 | if tocMode != "thumbs": |
---|
260 | # get table of contents |
---|
261 | docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
---|
262 | |
---|
263 | if viewMode=="auto": # automodus gewaehlt |
---|
264 | if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert |
---|
265 | viewMode="text_dict" |
---|
266 | else: |
---|
267 | viewMode="images" |
---|
268 | |
---|
269 | pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) |
---|
270 | |
---|
271 | pt = getattr(self.template, 'viewer_main') |
---|
272 | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
---|
273 | |
---|
274 | def generateMarks(self,mk): |
---|
275 | ret="" |
---|
276 | if mk is None: |
---|
277 | return "" |
---|
278 | if not isinstance(mk, list): |
---|
279 | mk=[mk] |
---|
280 | for m in mk: |
---|
281 | ret+="mk=%s"%m |
---|
282 | return ret |
---|
283 | |
---|
284 | |
---|
285 | def findDigilibUrl(self): |
---|
286 | """try to get the digilib URL from zogilib""" |
---|
287 | url = self.template.zogilib.getDLBaseUrl() |
---|
288 | return url |
---|
289 | |
---|
290 | def getDocumentViewerURL(self): |
---|
291 | """returns the URL of this instance""" |
---|
292 | return self.absolute_url() |
---|
293 | |
---|
294 | def getStyle(self, idx, selected, style=""): |
---|
295 | """returns a string with the given style and append 'sel' if path == selected.""" |
---|
296 | #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
---|
297 | if idx == selected: |
---|
298 | return style + 'sel' |
---|
299 | else: |
---|
300 | return style |
---|
301 | |
---|
302 | def getLink(self,param=None,val=None): |
---|
303 | """link to documentviewer with parameter param set to val""" |
---|
304 | params=self.REQUEST.form.copy() |
---|
305 | if param is not None: |
---|
306 | if val is None: |
---|
307 | if params.has_key(param): |
---|
308 | del params[param] |
---|
309 | else: |
---|
310 | params[param] = str(val) |
---|
311 | |
---|
312 | if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
---|
313 | params["mode"] = "imagepath" |
---|
314 | params["url"] = getParentDir(params["url"]) |
---|
315 | |
---|
316 | # quote values and assemble into query string |
---|
317 | #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
---|
318 | ps = urllib.urlencode(params) |
---|
319 | url=self.REQUEST['URL1']+"?"+ps |
---|
320 | return url |
---|
321 | |
---|
322 | def getLinkAmp(self,param=None,val=None): |
---|
323 | """link to documentviewer with parameter param set to val""" |
---|
324 | params=self.REQUEST.form.copy() |
---|
325 | if param is not None: |
---|
326 | if val is None: |
---|
327 | if params.has_key(param): |
---|
328 | del params[param] |
---|
329 | else: |
---|
330 | params[param] = str(val) |
---|
331 | |
---|
332 | # quote values and assemble into query string |
---|
333 | logging.debug("XYXXXXX: %s"%repr(params.items())) |
---|
334 | ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
---|
335 | url=self.REQUEST['URL1']+"?"+ps |
---|
336 | return url |
---|
337 | |
---|
338 | def getInfo_xml(self,url,mode): |
---|
339 | """returns info about the document as XML""" |
---|
340 | |
---|
341 | if not self.digilibBaseUrl: |
---|
342 | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
---|
343 | |
---|
344 | docinfo = self.getDocinfo(mode=mode,url=url) |
---|
345 | pt = getattr(self.template, 'info_xml') |
---|
346 | return pt(docinfo=docinfo) |
---|
347 | |
---|
348 | |
---|
349 | def isAccessible(self, docinfo): |
---|
350 | """returns if access to the resource is granted""" |
---|
351 | access = docinfo.get('accessType', None) |
---|
352 | logging.debug("documentViewer (accessOK) access type %s"%access) |
---|
353 | if access is not None and access == 'free': |
---|
354 | logging.debug("documentViewer (accessOK) access is free") |
---|
355 | return True |
---|
356 | elif access is None or access in self.authgroups: |
---|
357 | # only local access -- only logged in users |
---|
358 | user = getSecurityManager().getUser() |
---|
359 | logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
---|
360 | if user is not None: |
---|
361 | #print "user: ", user |
---|
362 | return (user.getUserName() != "Anonymous User") |
---|
363 | else: |
---|
364 | return False |
---|
365 | |
---|
366 | logging.error("documentViewer (accessOK) unknown access type %s"%access) |
---|
367 | return False |
---|
368 | |
---|
369 | |
---|
370 | def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
---|
371 | """gibt param von dlInfo aus""" |
---|
372 | if docinfo is None: |
---|
373 | docinfo = {} |
---|
374 | |
---|
375 | for x in range(cut): |
---|
376 | |
---|
377 | path=getParentDir(path) |
---|
378 | |
---|
379 | infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
---|
380 | |
---|
381 | logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) |
---|
382 | |
---|
383 | txt = getHttpData(infoUrl) |
---|
384 | if txt is None: |
---|
385 | raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
---|
386 | |
---|
387 | dom = Parse(txt) |
---|
388 | sizes=dom.xpath("//dir/size") |
---|
389 | logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) |
---|
390 | |
---|
391 | if sizes: |
---|
392 | docinfo['numPages'] = int(getTextFromNode(sizes[0])) |
---|
393 | else: |
---|
394 | docinfo['numPages'] = 0 |
---|
395 | |
---|
396 | # TODO: produce and keep list of image names and numbers |
---|
397 | |
---|
398 | return docinfo |
---|
399 | |
---|
400 | def getIndexMetaPath(self,url): |
---|
401 | """gib nur den Pfad zurueck""" |
---|
402 | regexp = re.compile(r".*(experimental|permanent)/(.*)") |
---|
403 | regpath = regexp.match(url) |
---|
404 | if (regpath==None): |
---|
405 | return "" |
---|
406 | logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2)) |
---|
407 | return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2)) |
---|
408 | |
---|
409 | |
---|
410 | |
---|
411 | def getIndexMetaUrl(self,url): |
---|
412 | """returns utr of index.meta document at url""" |
---|
413 | |
---|
414 | metaUrl = None |
---|
415 | if url.startswith("http://"): |
---|
416 | # real URL |
---|
417 | metaUrl = url |
---|
418 | else: |
---|
419 | # online path |
---|
420 | server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
---|
421 | metaUrl=server+url.replace("/mpiwg/online","") |
---|
422 | if not metaUrl.endswith("index.meta"): |
---|
423 | metaUrl += "/index.meta" |
---|
424 | |
---|
425 | return metaUrl |
---|
426 | |
---|
427 | def getDomFromIndexMeta(self, url): |
---|
428 | """get dom from index meta""" |
---|
429 | dom = None |
---|
430 | metaUrl = self.getIndexMetaUrl(url) |
---|
431 | |
---|
432 | logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl) |
---|
433 | txt=getHttpData(metaUrl) |
---|
434 | if txt is None: |
---|
435 | raise IOError("Unable to read index meta from %s"%(url)) |
---|
436 | |
---|
437 | dom = Parse(txt) |
---|
438 | return dom |
---|
439 | |
---|
440 | def getPresentationInfoXML(self, url): |
---|
441 | """returns dom of info.xml document at url""" |
---|
442 | dom = None |
---|
443 | metaUrl = None |
---|
444 | if url.startswith("http://"): |
---|
445 | # real URL |
---|
446 | metaUrl = url |
---|
447 | else: |
---|
448 | # online path |
---|
449 | server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
---|
450 | metaUrl=server+url.replace("/mpiwg/online","") |
---|
451 | |
---|
452 | txt=getHttpData(metaUrl) |
---|
453 | if txt is None: |
---|
454 | raise IOError("Unable to read infoXMLfrom %s"%(url)) |
---|
455 | |
---|
456 | dom = Parse(txt) |
---|
457 | return dom |
---|
458 | |
---|
459 | |
---|
460 | def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
---|
461 | """gets authorization info from the index.meta file at path or given by dom""" |
---|
462 | logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) |
---|
463 | |
---|
464 | access = None |
---|
465 | |
---|
466 | if docinfo is None: |
---|
467 | docinfo = {} |
---|
468 | |
---|
469 | if dom is None: |
---|
470 | for x in range(cut): |
---|
471 | path=getParentDir(path) |
---|
472 | dom = self.getDomFromIndexMeta(path) |
---|
473 | |
---|
474 | acctype = dom.xpath("//access-conditions/access/@type") |
---|
475 | if acctype and (len(acctype)>0): |
---|
476 | access=acctype[0].value |
---|
477 | if access in ['group', 'institution']: |
---|
478 | access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
---|
479 | |
---|
480 | docinfo['accessType'] = access |
---|
481 | return docinfo |
---|
482 | |
---|
483 | |
---|
484 | def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
---|
485 | """gets bibliographical info from the index.meta file at path or given by dom""" |
---|
486 | logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
---|
487 | |
---|
488 | if docinfo is None: |
---|
489 | docinfo = {} |
---|
490 | |
---|
491 | if dom is None: |
---|
492 | for x in range(cut): |
---|
493 | path=getParentDir(path) |
---|
494 | dom = self.getDomFromIndexMeta(path) |
---|
495 | |
---|
496 | docinfo['indexMetaPath']=self.getIndexMetaPath(path); |
---|
497 | |
---|
498 | logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
---|
499 | # put in all raw bib fields as dict "bib" |
---|
500 | bib = dom.xpath("//bib/*") |
---|
501 | if bib and len(bib)>0: |
---|
502 | bibinfo = {} |
---|
503 | for e in bib: |
---|
504 | bibinfo[e.localName] = getTextFromNode(e) |
---|
505 | docinfo['bib'] = bibinfo |
---|
506 | |
---|
507 | # extract some fields (author, title, year) according to their mapping |
---|
508 | metaData=self.metadata.main.meta.bib |
---|
509 | bibtype=dom.xpath("//bib/@type") |
---|
510 | if bibtype and (len(bibtype)>0): |
---|
511 | bibtype=bibtype[0].value |
---|
512 | else: |
---|
513 | bibtype="generic" |
---|
514 | |
---|
515 | bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
---|
516 | docinfo['bib_type'] = bibtype |
---|
517 | bibmap=metaData.generateMappingForType(bibtype) |
---|
518 | logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) |
---|
519 | logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) |
---|
520 | # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
---|
521 | if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
---|
522 | try: |
---|
523 | docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) |
---|
524 | except: pass |
---|
525 | try: |
---|
526 | docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) |
---|
527 | except: pass |
---|
528 | try: |
---|
529 | docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) |
---|
530 | except: pass |
---|
531 | logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
---|
532 | try: |
---|
533 | docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) |
---|
534 | except: |
---|
535 | docinfo['lang']='' |
---|
536 | |
---|
537 | return docinfo |
---|
538 | |
---|
539 | |
---|
540 | def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
---|
541 | """gets name info from the index.meta file at path or given by dom""" |
---|
542 | if docinfo is None: |
---|
543 | docinfo = {} |
---|
544 | |
---|
545 | if dom is None: |
---|
546 | for x in range(cut): |
---|
547 | path=getParentDir(path) |
---|
548 | dom = self.getDomFromIndexMeta(path) |
---|
549 | |
---|
550 | #docinfo['indexMetaPath']=self.getIndexMetaPath(path); |
---|
551 | |
---|
552 | #result= dom.xpath("//result/resultPage") |
---|
553 | #docinfo['numPages']=int(getTextFromNode(result[0])) |
---|
554 | |
---|
555 | #result =dom.xpath("//name") |
---|
556 | docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0]) |
---|
557 | logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) |
---|
558 | |
---|
559 | #logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
---|
560 | return docinfo |
---|
561 | |
---|
562 | def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): |
---|
563 | """parse texttool tag in index meta""" |
---|
564 | logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) |
---|
565 | if docinfo is None: |
---|
566 | docinfo = {} |
---|
567 | if docinfo.get('lang', None) is None: |
---|
568 | docinfo['lang'] = '' # default keine Sprache gesetzt |
---|
569 | if dom is None: |
---|
570 | dom = self.getDomFromIndexMeta(url) |
---|
571 | |
---|
572 | archivePath = None |
---|
573 | archiveName = None |
---|
574 | |
---|
575 | archiveNames = dom.xpath("//resource/name") |
---|
576 | if archiveNames and (len(archiveNames) > 0): |
---|
577 | archiveName = getTextFromNode(archiveNames[0]) |
---|
578 | else: |
---|
579 | logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) |
---|
580 | |
---|
581 | archivePaths = dom.xpath("//resource/archive-path") |
---|
582 | if archivePaths and (len(archivePaths) > 0): |
---|
583 | archivePath = getTextFromNode(archivePaths[0]) |
---|
584 | # clean up archive path |
---|
585 | if archivePath[0] != '/': |
---|
586 | archivePath = '/' + archivePath |
---|
587 | if archiveName and (not archivePath.endswith(archiveName)): |
---|
588 | archivePath += "/" + archiveName |
---|
589 | else: |
---|
590 | # try to get archive-path from url |
---|
591 | logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url)) |
---|
592 | if (not url.startswith('http')): |
---|
593 | archivePath = url.replace('index.meta', '') |
---|
594 | |
---|
595 | if archivePath is None: |
---|
596 | # we balk without archive-path |
---|
597 | raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
---|
598 | |
---|
599 | imageDirs = dom.xpath("//texttool/image") |
---|
600 | if imageDirs and (len(imageDirs) > 0): |
---|
601 | imageDir = getTextFromNode(imageDirs[0]) |
---|
602 | |
---|
603 | else: |
---|
604 | # we balk with no image tag / not necessary anymore because textmode is now standard |
---|
605 | #raise IOError("No text-tool info in %s"%(url)) |
---|
606 | imageDir = "" |
---|
607 | #xquery="//pb" |
---|
608 | docinfo['imagePath'] = "" # keine Bilder |
---|
609 | docinfo['imageURL'] = "" |
---|
610 | |
---|
611 | if imageDir and archivePath: |
---|
612 | #print "image: ", imageDir, " archivepath: ", archivePath |
---|
613 | imageDir = os.path.join(archivePath, imageDir) |
---|
614 | imageDir = imageDir.replace("/mpiwg/online", '') |
---|
615 | docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
---|
616 | docinfo['imagePath'] = imageDir |
---|
617 | |
---|
618 | docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir |
---|
619 | |
---|
620 | viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
---|
621 | if viewerUrls and (len(viewerUrls) > 0): |
---|
622 | viewerUrl = getTextFromNode(viewerUrls[0]) |
---|
623 | docinfo['viewerURL'] = viewerUrl |
---|
624 | |
---|
625 | # old style text URL |
---|
626 | textUrls = dom.xpath("//texttool/text") |
---|
627 | if textUrls and (len(textUrls) > 0): |
---|
628 | textUrl = getTextFromNode(textUrls[0]) |
---|
629 | if urlparse.urlparse(textUrl)[0] == "": #keine url |
---|
630 | textUrl = os.path.join(archivePath, textUrl) |
---|
631 | # fix URLs starting with /mpiwg/online |
---|
632 | if textUrl.startswith("/mpiwg/online"): |
---|
633 | textUrl = textUrl.replace("/mpiwg/online", '', 1) |
---|
634 | |
---|
635 | docinfo['textURL'] = textUrl |
---|
636 | |
---|
637 | # new style text-url-path |
---|
638 | textUrls = dom.xpath("//texttool/text-url-path") |
---|
639 | if textUrls and (len(textUrls) > 0): |
---|
640 | textUrl = getTextFromNode(textUrls[0]) |
---|
641 | docinfo['textURLPath'] = textUrl |
---|
642 | if not docinfo['imagePath']: |
---|
643 | # text-only, no page images |
---|
644 | docinfo = self.getNumTextPages(docinfo) |
---|
645 | |
---|
646 | presentationUrls = dom.xpath("//texttool/presentation") |
---|
647 | docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag |
---|
648 | docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) |
---|
649 | |
---|
650 | if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen |
---|
651 | # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten |
---|
652 | # durch den relativen Pfad auf die presentation infos |
---|
653 | presentationPath = getTextFromNode(presentationUrls[0]) |
---|
654 | if url.endswith("index.meta"): |
---|
655 | presentationUrl = url.replace('index.meta', presentationPath) |
---|
656 | else: |
---|
657 | presentationUrl = url + "/" + presentationPath |
---|
658 | |
---|
659 | docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) |
---|
660 | |
---|
661 | docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info |
---|
662 | |
---|
663 | return docinfo |
---|
664 | |
---|
665 | |
---|
666 | def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
---|
667 | """gets the bibliographical information from the preseantion entry in texttools |
---|
668 | """ |
---|
669 | dom=self.getPresentationInfoXML(url) |
---|
670 | try: |
---|
671 | docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) |
---|
672 | except: |
---|
673 | pass |
---|
674 | try: |
---|
675 | docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) |
---|
676 | except: |
---|
677 | pass |
---|
678 | try: |
---|
679 | docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) |
---|
680 | except: |
---|
681 | pass |
---|
682 | return docinfo |
---|
683 | |
---|
684 | def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
---|
685 | """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
---|
686 | logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) |
---|
687 | if docinfo is None: |
---|
688 | docinfo = {} |
---|
689 | path=path.replace("/mpiwg/online","") |
---|
690 | docinfo['imagePath'] = path |
---|
691 | docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
---|
692 | |
---|
693 | pathorig=path |
---|
694 | for x in range(cut): |
---|
695 | path=getParentDir(path) |
---|
696 | logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) |
---|
697 | imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
---|
698 | docinfo['imageURL'] = imageUrl |
---|
699 | |
---|
700 | #path ist the path to the images it assumes that the index.meta file is one level higher. |
---|
701 | docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
---|
702 | docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
---|
703 | return docinfo |
---|
704 | |
---|
705 | |
---|
706 | def getDocinfo(self, mode, url): |
---|
707 | """returns docinfo depending on mode""" |
---|
708 | logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) |
---|
709 | # look for cached docinfo in session |
---|
710 | if self.REQUEST.SESSION.has_key('docinfo'): |
---|
711 | docinfo = self.REQUEST.SESSION['docinfo'] |
---|
712 | # check if its still current |
---|
713 | if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: |
---|
714 | logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) |
---|
715 | return docinfo |
---|
716 | # new docinfo |
---|
717 | docinfo = {'mode': mode, 'url': url} |
---|
718 | if mode=="texttool": #index.meta with texttool information |
---|
719 | docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) |
---|
720 | elif mode=="imagepath": |
---|
721 | docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) |
---|
722 | elif mode=="filepath": |
---|
723 | docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
---|
724 | else: |
---|
725 | logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
---|
726 | raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
---|
727 | |
---|
728 | logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
---|
729 | self.REQUEST.SESSION['docinfo'] = docinfo |
---|
730 | return docinfo |
---|
731 | |
---|
732 | def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""): |
---|
733 | """returns pageinfo with the given parameters""" |
---|
734 | pageinfo = {} |
---|
735 | current = getInt(current) |
---|
736 | pageinfo['current'] = current |
---|
737 | rows = int(rows or self.thumbrows) |
---|
738 | pageinfo['rows'] = rows |
---|
739 | cols = int(cols or self.thumbcols) |
---|
740 | pageinfo['cols'] = cols |
---|
741 | grpsize = cols * rows |
---|
742 | pageinfo['groupsize'] = grpsize |
---|
743 | start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
---|
744 | # int(current / grpsize) * grpsize +1)) |
---|
745 | pageinfo['start'] = start |
---|
746 | pageinfo['end'] = start + grpsize |
---|
747 | if (docinfo is not None) and ('numPages' in docinfo): |
---|
748 | np = int(docinfo['numPages']) |
---|
749 | pageinfo['end'] = min(pageinfo['end'], np) |
---|
750 | pageinfo['numgroups'] = int(np / grpsize) |
---|
751 | if np % grpsize > 0: |
---|
752 | pageinfo['numgroups'] += 1 |
---|
753 | pageinfo['viewMode'] = viewMode |
---|
754 | pageinfo['tocMode'] = tocMode |
---|
755 | #pageinfo['characterNormalization'] =characterNormalization |
---|
756 | pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ') |
---|
757 | pageinfo['query'] = self.REQUEST.get('query',' ') |
---|
758 | pageinfo['queryType'] = self.REQUEST.get('queryType',' ') |
---|
759 | pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
---|
760 | pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
---|
761 | pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
---|
762 | pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
---|
763 | pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') |
---|
764 | pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
---|
765 | toc = int (pageinfo['tocPN']) |
---|
766 | pageinfo['textPages'] =int (toc) |
---|
767 | |
---|
768 | if 'tocSize_%s'%tocMode in docinfo: |
---|
769 | tocSize = int(docinfo['tocSize_%s'%tocMode]) |
---|
770 | tocPageSize = int(pageinfo['tocPageSize']) |
---|
771 | # cached toc |
---|
772 | if tocSize%tocPageSize>0: |
---|
773 | tocPages=tocSize/tocPageSize+1 |
---|
774 | else: |
---|
775 | tocPages=tocSize/tocPageSize |
---|
776 | pageinfo['tocPN'] = min (tocPages,toc) |
---|
777 | pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
---|
778 | pageinfo['sn'] =self.REQUEST.get('sn','') |
---|
779 | return pageinfo |
---|
780 | |
---|
781 | def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
---|
782 | """init document viewer""" |
---|
783 | self.title=title |
---|
784 | self.digilibBaseUrl = digilibBaseUrl |
---|
785 | self.thumbrows = thumbrows |
---|
786 | self.thumbcols = thumbcols |
---|
787 | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
---|
788 | if RESPONSE is not None: |
---|
789 | RESPONSE.redirect('manage_main') |
---|
790 | |
---|
791 | def manage_AddDocumentViewerForm(self): |
---|
792 | """add the viewer form""" |
---|
793 | pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
---|
794 | return pt() |
---|
795 | |
---|
796 | def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
---|
797 | """add the viewer""" |
---|
798 | newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
---|
799 | self._setObject(id,newObj) |
---|
800 | |
---|
801 | if RESPONSE is not None: |
---|
802 | RESPONSE.redirect('manage_main') |
---|
803 | |
---|
804 | ## DocumentViewerTemplate class |
---|
805 | class DocumentViewerTemplate(ZopePageTemplate): |
---|
806 | """Template for document viewer""" |
---|
807 | meta_type="DocumentViewer Template" |
---|
808 | |
---|
809 | |
---|
810 | def manage_addDocumentViewerTemplateForm(self): |
---|
811 | """Form for adding""" |
---|
812 | pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) |
---|
813 | return pt() |
---|
814 | |
---|
815 | def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, |
---|
816 | REQUEST=None, submit=None): |
---|
817 | "Add a Page Template with optional file content." |
---|
818 | |
---|
819 | self._setObject(id, DocumentViewerTemplate(id)) |
---|
820 | ob = getattr(self, id) |
---|
821 | txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
---|
822 | logging.info("txt %s:"%txt) |
---|
823 | ob.pt_edit(txt,"text/html") |
---|
824 | if title: |
---|
825 | ob.pt_setTitle(title) |
---|
826 | try: |
---|
827 | u = self.DestinationURL() |
---|
828 | except AttributeError: |
---|
829 | u = REQUEST['URL1'] |
---|
830 | |
---|
831 | u = "%s/%s" % (u, urllib.quote(id)) |
---|
832 | REQUEST.RESPONSE.redirect(u+'/manage_main') |
---|
833 | return '' |
---|
834 | |
---|
835 | |
---|
836 | |
---|