Annotation of documentViewer/documentViewer.py, revision 1.69.2.12
1.18 dwinter 1:
1.1 dwinter 2: from OFS.Folder import Folder
3: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
1.22 dwinter 4: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
1.1 dwinter 5: from AccessControl import ClassSecurityInfo
1.8 casties 6: from AccessControl import getSecurityManager
1.1 dwinter 7: from Globals import package_home
8:
1.11 casties 9: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.69.2.10 casties 10: from Ft.Xml.Domlette import PrettyPrint, Print
1.1 dwinter 11: import os.path
1.7 casties 12: import sys
1.1 dwinter 13: import urllib
1.69.2.5 casties 14: import urllib2
1.20 dwinter 15: import logging
1.69.2.7 casties 16: import math
17: import urlparse
1.69.2.9 casties 18: import cStringIO
1.43 casties 19:
1.22 dwinter 20: def logger(txt,method,txt2):
21: """logging"""
22: logging.info(txt+ txt2)
23:
24:
1.4 casties 25: def getInt(number, default=0):
26: """returns always an int (0 in case of problems)"""
27: try:
28: return int(number)
29: except:
1.29 casties 30: return int(default)
1.4 casties 31:
1.1 dwinter 32: def getTextFromNode(nodename):
1.18 dwinter 33: """get the cdata content of a node"""
1.8 casties 34: if nodename is None:
35: return ""
1.1 dwinter 36: nodelist=nodename.childNodes
37: rc = ""
38: for node in nodelist:
39: if node.nodeType == node.TEXT_NODE:
40: rc = rc + node.data
41: return rc
42:
1.43 casties 43: def serializeNode(node, encoding='utf-8'):
44: """returns a string containing node as XML"""
45: buf = cStringIO.StringIO()
46: Print(node, stream=buf, encoding=encoding)
47: s = buf.getvalue()
48: buf.close()
49: return s
50:
1.9 casties 51:
52: def getParentDir(path):
53: """returns pathname shortened by one"""
54: return '/'.join(path.split('/')[0:-1])
55:
56:
1.69.2.3 casties 57: def getHttpData(url, data=None, num_tries=3, timeout=10):
58: """returns result from url+data HTTP request"""
59: # we do GET (by appending data to url)
60: if isinstance(data, str) or isinstance(data, unicode):
61: # if data is string then append
62: url = "%s?%s"%(url,data)
63: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
64: # urlencode
65: url = "%s?%s"%(url,urllib.urlencode(data))
66:
67: response = None
68: errmsg = None
69: for cnt in range(num_tries):
70: try:
71: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
72: if sys.version_info < (2, 6):
73: # set timeout on socket -- ugly :-(
74: import socket
1.69.2.8 casties 75: socket.setdefaulttimeout(float(timeout))
1.69.2.3 casties 76: response = urllib2.urlopen(url)
77: else:
78: response = urllib2.urlopen(url,timeout=float(timeout))
79: # check result?
80: break
81: except urllib2.HTTPError, e:
82: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
83: errmsg = str(e)
84: # stop trying
85: break
86: except urllib2.URLError, e:
87: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
88: errmsg = str(e)
89: # stop trying
90: #break
91:
92: if response is not None:
93: data = response.read()
94: response.close()
95: return data
96:
97: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
98: #return None
1.1 dwinter 99:
100:
101:
1.3 casties 102: ##
103: ## documentViewer class
104: ##
1.69.2.3 casties 105: class documentViewer(Folder):
1.1 dwinter 106: """document viewer"""
107: meta_type="Document viewer"
108:
109: security=ClassSecurityInfo()
1.3 casties 110: manage_options=Folder.manage_options+(
1.1 dwinter 111: {'label':'main config','action':'changeDocumentViewerForm'},
112: )
113:
1.3 casties 114: # templates and forms
115: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 116: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
117: toc_text = PageTemplateFile('zpt/toc_text', globals())
118: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 119: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
120: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 121: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.48 abukhman 122: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 123: head_main = PageTemplateFile('zpt/head_main', globals())
124: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 125: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.69.2.1 abukhman 126:
127:
1.32 dwinter 128: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 129: security.declareProtected('View management screens','changeDocumentViewerForm')
130: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
131:
1.1 dwinter 132:
1.45 abukhman 133: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 134: """init document viewer"""
135: self.id=id
136: self.title=title
1.4 casties 137: self.thumbcols = thumbcols
138: self.thumbrows = thumbrows
1.8 casties 139: # authgroups is list of authorized groups (delimited by ,)
140: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 141: # create template folder so we can always use template.something
142:
143: templateFolder = Folder('template')
144: #self['template'] = templateFolder # Zope-2.12 style
145: self._setObject('template',templateFolder) # old style
146: try:
1.69.2.3 casties 147: import MpdlXmlTextServer
148: textServer = MpdlXmlTextServer(id='fulltextclient')
1.43 casties 149: #templateFolder['fulltextclient'] = xmlRpcClient
1.69.2.3 casties 150: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 151: except Exception, e:
1.69.2.3 casties 152: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 153: try:
154: from Products.zogiLib.zogiLib import zogiLib
155: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
156: #templateFolder['zogilib'] = zogilib
157: templateFolder._setObject('zogilib',zogilib)
158: except Exception, e:
159: logging.error("Unable to create zogiLib for zogilib: "+str(e))
160:
1.69.2.3 casties 161:
162: # proxy text server methods to fulltextclient
163: def getTextPage(self, **args):
164: """get page"""
165: return self.template.fulltextclient.getTextPage(**args)
166:
167: def getQuery(self, **args):
168: """get query"""
169: return self.template.fulltextclient.getQuery(**args)
170:
171: def getSearch(self, **args):
172: """get search"""
173: return self.template.fulltextclient.getSearch(**args)
174:
175: def getNumPages(self, **args):
176: """get numpages"""
177: return self.template.fulltextclient.getNumPages(**args)
178:
179: def getTranslate(self, **args):
180: """get translate"""
181: return self.template.fulltextclient.getTranslate(**args)
182:
183: def getLemma(self, **args):
184: """get lemma"""
185: return self.template.fulltextclient.getLemma(**args)
186:
187: def getToc(self, **args):
188: """get toc"""
189: return self.template.fulltextclient.getToc(**args)
190:
191: def getTocPage(self, **args):
192: """get tocpage"""
193: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 194:
1.69.2.3 casties 195:
1.32 dwinter 196: security.declareProtected('View','thumbs_rss')
197: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
198: '''
199: view it
200: @param mode: defines how to access the document behind url
201: @param url: url which contains display information
202: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
203:
204: '''
1.43 casties 205: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 206: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
207:
208: if not hasattr(self, 'template'):
209: # create template folder if it doesn't exist
210: self.manage_addFolder('template')
211:
212: if not self.digilibBaseUrl:
213: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
214:
215: docinfo = self.getDocinfo(mode=mode,url=url)
216: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
217: pt = getattr(self.template, 'thumbs_main_rss')
218:
219: if viewMode=="auto": # automodus gewaehlt
1.69.2.11 casties 220: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 221: viewMode="text"
222: else:
223: viewMode="images"
224:
225: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
226:
1.3 casties 227: security.declareProtected('View','index_html')
1.45 abukhman 228: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3 casties 229: '''
230: view it
1.26 casties 231: @param mode: defines how to access the document behind url
1.3 casties 232: @param url: url which contains display information
1.44 casties 233: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 234: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.49 abukhman 235: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 236: '''
237:
1.43 casties 238: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 239:
1.3 casties 240: if not hasattr(self, 'template'):
1.43 casties 241: # this won't work
242: logging.error("template folder missing!")
243: return "ERROR: template folder missing!"
1.3 casties 244:
1.43 casties 245: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 246: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
247:
1.4 casties 248: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 249:
250:
1.44 casties 251: if tocMode != "thumbs":
252: # get table of contents
253: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 254:
1.21 dwinter 255: if viewMode=="auto": # automodus gewaehlt
1.69.2.11 casties 256: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 257: viewMode="text_dict"
1.21 dwinter 258: else:
259: viewMode="images"
1.44 casties 260:
1.68 casties 261: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
262:
1.44 casties 263: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 264: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 265:
1.36 dwinter 266: def generateMarks(self,mk):
267: ret=""
1.44 casties 268: if mk is None:
269: return ""
270: if type(mk) is not ListType:
271: mk=[mk]
1.36 dwinter 272: for m in mk:
1.37 dwinter 273: ret+="mk=%s"%m
1.36 dwinter 274: return ret
1.43 casties 275:
1.44 casties 276:
1.43 casties 277: def findDigilibUrl(self):
278: """try to get the digilib URL from zogilib"""
279: url = self.template.zogilib.getDLBaseUrl()
280: return url
1.67 casties 281:
282: def getDocumentViewerURL(self):
283: """returns the URL of this instance"""
284: return self.absolute_url()
1.43 casties 285:
286: def getStyle(self, idx, selected, style=""):
287: """returns a string with the given style and append 'sel' if path == selected."""
288: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
289: if idx == selected:
290: return style + 'sel'
291: else:
292: return style
1.36 dwinter 293:
1.4 casties 294: def getLink(self,param=None,val=None):
295: """link to documentviewer with parameter param set to val"""
1.9 casties 296: params=self.REQUEST.form.copy()
1.4 casties 297: if param is not None:
1.7 casties 298: if val is None:
299: if params.has_key(param):
300: del params[param]
1.4 casties 301: else:
1.9 casties 302: params[param] = str(val)
1.43 casties 303:
304: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 305: params["mode"] = "imagepath"
306: params["url"] = getParentDir(params["url"])
1.7 casties 307:
1.9 casties 308: # quote values and assemble into query string
309: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
310: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 311: return url
312:
1.32 dwinter 313: def getLinkAmp(self,param=None,val=None):
314: """link to documentviewer with parameter param set to val"""
315: params=self.REQUEST.form.copy()
316: if param is not None:
317: if val is None:
318: if params.has_key(param):
319: del params[param]
320: else:
321: params[param] = str(val)
322:
323: # quote values and assemble into query string
1.69.2.2 casties 324: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 325: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
326: url=self.REQUEST['URL1']+"?"+ps
327: return url
1.40 casties 328:
1.26 casties 329: def getInfo_xml(self,url,mode):
330: """returns info about the document as XML"""
331:
332: if not self.digilibBaseUrl:
333: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
334:
335: docinfo = self.getDocinfo(mode=mode,url=url)
336: pt = getattr(self.template, 'info_xml')
337: return pt(docinfo=docinfo)
338:
1.4 casties 339:
1.9 casties 340: def isAccessible(self, docinfo):
1.8 casties 341: """returns if access to the resource is granted"""
342: access = docinfo.get('accessType', None)
1.69.2.2 casties 343: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 344: if access is not None and access == 'free':
1.69.2.2 casties 345: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 346: return True
1.17 casties 347: elif access is None or access in self.authgroups:
1.9 casties 348: # only local access -- only logged in users
349: user = getSecurityManager().getUser()
350: if user is not None:
351: #print "user: ", user
352: return (user.getUserName() != "Anonymous User")
353: else:
354: return False
1.8 casties 355:
1.69.2.2 casties 356: logging.debug("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 357: return False
1.9 casties 358:
1.8 casties 359:
1.35 dwinter 360: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 361: """gibt param von dlInfo aus"""
1.7 casties 362: if docinfo is None:
363: docinfo = {}
1.35 dwinter 364:
365: for x in range(cut):
1.38 dwinter 366:
1.35 dwinter 367: path=getParentDir(path)
1.38 dwinter 368:
1.13 casties 369: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 370:
1.69.2.2 casties 371: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 372:
1.69.2.3 casties 373: txt = getHttpData(infoUrl)
374: if txt is None:
1.13 casties 375: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.69.2.3 casties 376:
377: dom = Parse(txt)
1.10 casties 378: sizes=dom.xpath("//dir/size")
1.69.2.2 casties 379: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 380:
1.10 casties 381: if sizes:
382: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 383: else:
384: docinfo['numPages'] = 0
1.43 casties 385:
386: # TODO: produce and keep list of image names and numbers
1.7 casties 387:
388: return docinfo
1.8 casties 389:
1.6 casties 390:
1.9 casties 391: def getIndexMeta(self, url):
392: """returns dom of index.meta document at url"""
393: dom = None
1.12 casties 394: metaUrl = None
1.9 casties 395: if url.startswith("http://"):
396: # real URL
1.12 casties 397: metaUrl = url
1.9 casties 398: else:
399: # online path
400: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 401: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 402: if not metaUrl.endswith("index.meta"):
403: metaUrl += "/index.meta"
1.12 casties 404:
1.69.2.3 casties 405: logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
406: txt=getHttpData(metaUrl)
407: if txt is None:
1.12 casties 408: raise IOError("Unable to read index meta from %s"%(url))
1.69.2.3 casties 409:
410: dom = Parse(txt)
1.9 casties 411: return dom
1.20 dwinter 412:
413: def getPresentationInfoXML(self, url):
414: """returns dom of info.xml document at url"""
415: dom = None
416: metaUrl = None
417: if url.startswith("http://"):
418: # real URL
419: metaUrl = url
420: else:
421: # online path
422: server=self.digilibBaseUrl+"/servlet/Texter?fn="
423: metaUrl=server+url.replace("/mpiwg/online","")
424:
1.69.2.3 casties 425: txt=getHttpData(metaUrl)
426: if txt is None:
1.20 dwinter 427: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.69.2.3 casties 428:
429: dom = Parse(txt)
1.20 dwinter 430: return dom
1.9 casties 431:
432:
1.33 dwinter 433: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 434: """gets authorization info from the index.meta file at path or given by dom"""
1.69.2.2 casties 435: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 436:
437: access = None
438:
439: if docinfo is None:
440: docinfo = {}
441:
442: if dom is None:
1.38 dwinter 443: for x in range(cut):
1.33 dwinter 444: path=getParentDir(path)
445: dom = self.getIndexMeta(path)
1.18 dwinter 446:
1.8 casties 447: acctype = dom.xpath("//access-conditions/access/@type")
448: if acctype and (len(acctype)>0):
449: access=acctype[0].value
1.9 casties 450: if access in ['group', 'institution']:
1.8 casties 451: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
452:
453: docinfo['accessType'] = access
454: return docinfo
1.6 casties 455:
1.8 casties 456:
1.33 dwinter 457: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 458: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 459: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 460:
1.3 casties 461: if docinfo is None:
462: docinfo = {}
1.38 dwinter 463:
1.3 casties 464: if dom is None:
1.38 dwinter 465: for x in range(cut):
1.33 dwinter 466: path=getParentDir(path)
467: dom = self.getIndexMeta(path)
1.39 dwinter 468:
469: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 470: # put in all raw bib fields as dict "bib"
471: bib = dom.xpath("//bib/*")
472: if bib and len(bib)>0:
473: bibinfo = {}
474: for e in bib:
475: bibinfo[e.localName] = getTextFromNode(e)
476: docinfo['bib'] = bibinfo
477:
478: # extract some fields (author, title, year) according to their mapping
1.4 casties 479: metaData=self.metadata.main.meta.bib
480: bibtype=dom.xpath("//bib/@type")
481: if bibtype and (len(bibtype)>0):
482: bibtype=bibtype[0].value
1.2 dwinter 483: else:
1.4 casties 484: bibtype="generic"
1.27 casties 485:
1.4 casties 486: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 487: docinfo['bib_type'] = bibtype
1.4 casties 488: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 489: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 490: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 491: try:
492: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
493: except: pass
494: try:
495: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
496: except: pass
497: try:
498: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
499: except: pass
1.27 casties 500: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 501: try:
502: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
503: except:
504: docinfo['lang']=''
1.27 casties 505:
1.3 casties 506: return docinfo
1.42 abukhman 507:
508:
1.43 casties 509: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
510: """parse texttool tag in index meta"""
1.69.2.2 casties 511: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 512: if docinfo is None:
513: docinfo = {}
514: if docinfo.get('lang', None) is None:
515: docinfo['lang'] = '' # default keine Sprache gesetzt
516: if dom is None:
517: dom = self.getIndexMeta(url)
518:
519: archivePath = None
520: archiveName = None
521:
522: archiveNames = dom.xpath("//resource/name")
523: if archiveNames and (len(archiveNames) > 0):
524: archiveName = getTextFromNode(archiveNames[0])
525: else:
1.69.2.2 casties 526: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 527:
528: archivePaths = dom.xpath("//resource/archive-path")
529: if archivePaths and (len(archivePaths) > 0):
530: archivePath = getTextFromNode(archivePaths[0])
531: # clean up archive path
532: if archivePath[0] != '/':
533: archivePath = '/' + archivePath
534: if archiveName and (not archivePath.endswith(archiveName)):
535: archivePath += "/" + archiveName
536: else:
537: # try to get archive-path from url
1.69.2.2 casties 538: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 539: if (not url.startswith('http')):
540: archivePath = url.replace('index.meta', '')
541:
542: if archivePath is None:
543: # we balk without archive-path
544: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
545:
546: imageDirs = dom.xpath("//texttool/image")
547: if imageDirs and (len(imageDirs) > 0):
548: imageDir = getTextFromNode(imageDirs[0])
549:
550: else:
551: # we balk with no image tag / not necessary anymore because textmode is now standard
552: #raise IOError("No text-tool info in %s"%(url))
553: imageDir = ""
554: #xquery="//pb"
555: docinfo['imagePath'] = "" # keine Bilder
556: docinfo['imageURL'] = ""
557:
558: if imageDir and archivePath:
559: #print "image: ", imageDir, " archivepath: ", archivePath
560: imageDir = os.path.join(archivePath, imageDir)
561: imageDir = imageDir.replace("/mpiwg/online", '')
562: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
563: docinfo['imagePath'] = imageDir
564:
565: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
566:
567: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
568: if viewerUrls and (len(viewerUrls) > 0):
569: viewerUrl = getTextFromNode(viewerUrls[0])
570: docinfo['viewerURL'] = viewerUrl
1.69.2.11 casties 571:
572: # old style text URL
1.43 casties 573: textUrls = dom.xpath("//texttool/text")
574: if textUrls and (len(textUrls) > 0):
575: textUrl = getTextFromNode(textUrls[0])
576: if urlparse.urlparse(textUrl)[0] == "": #keine url
577: textUrl = os.path.join(archivePath, textUrl)
578: # fix URLs starting with /mpiwg/online
579: if textUrl.startswith("/mpiwg/online"):
580: textUrl = textUrl.replace("/mpiwg/online", '', 1)
581:
582: docinfo['textURL'] = textUrl
583:
1.69.2.11 casties 584: # new style text-url-path
1.43 casties 585: textUrls = dom.xpath("//texttool/text-url-path")
586: if textUrls and (len(textUrls) > 0):
587: textUrl = getTextFromNode(textUrls[0])
1.51 casties 588: docinfo['textURLPath'] = textUrl
589: if not docinfo['imagePath']:
590: # text-only, no page images
591: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
1.43 casties 592:
593: presentationUrls = dom.xpath("//texttool/presentation")
594: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
595:
596: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
597: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
598: # durch den relativen Pfad auf die presentation infos
599: presentationPath = getTextFromNode(presentationUrls[0])
600: if url.endswith("index.meta"):
601: presentationUrl = url.replace('index.meta', presentationPath)
602: else:
603: presentationUrl = url + "/" + presentationPath
1.51 casties 604:
1.43 casties 605: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
606:
607: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 608:
1.43 casties 609: return docinfo
1.3 casties 610:
1.20 dwinter 611:
612: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
613: """gets the bibliographical information from the preseantion entry in texttools
614: """
615: dom=self.getPresentationInfoXML(url)
1.29 casties 616: try:
617: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
618: except:
619: pass
620: try:
621: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
622: except:
623: pass
624: try:
625: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
626: except:
627: pass
1.20 dwinter 628: return docinfo
629:
1.33 dwinter 630: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 631: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.69.2.2 casties 632: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 633: if docinfo is None:
634: docinfo = {}
1.6 casties 635: path=path.replace("/mpiwg/online","")
1.3 casties 636: docinfo['imagePath'] = path
1.35 dwinter 637: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 638:
1.39 dwinter 639: pathorig=path
1.38 dwinter 640: for x in range(cut):
641: path=getParentDir(path)
1.69.2.2 casties 642: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 643: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 644: docinfo['imageURL'] = imageUrl
645:
1.39 dwinter 646: #path ist the path to the images it assumes that the index.meta file is one level higher.
647: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
648: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 649: return docinfo
650:
1.2 dwinter 651:
1.3 casties 652: def getDocinfo(self, mode, url):
653: """returns docinfo depending on mode"""
1.69.2.2 casties 654: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 655: # look for cached docinfo in session
1.21 dwinter 656: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 657: docinfo = self.REQUEST.SESSION['docinfo']
658: # check if its still current
659: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.69.2.2 casties 660: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 661: return docinfo
662: # new docinfo
663: docinfo = {'mode': mode, 'url': url}
664: if mode=="texttool": #index.meta with texttool information
665: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
666: elif mode=="imagepath":
667: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 668: elif mode=="filepath":
1.37 dwinter 669: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 670: else:
1.69.2.2 casties 671: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 672: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 673:
1.69.2.2 casties 674: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 675: self.REQUEST.SESSION['docinfo'] = docinfo
676: return docinfo
1.69 abukhman 677:
1.44 casties 678: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 679: """returns pageinfo with the given parameters"""
680: pageinfo = {}
1.4 casties 681: current = getInt(current)
682: pageinfo['current'] = current
683: rows = int(rows or self.thumbrows)
684: pageinfo['rows'] = rows
685: cols = int(cols or self.thumbcols)
686: pageinfo['cols'] = cols
687: grpsize = cols * rows
688: pageinfo['groupsize'] = grpsize
1.28 casties 689: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
690: # int(current / grpsize) * grpsize +1))
1.3 casties 691: pageinfo['start'] = start
1.4 casties 692: pageinfo['end'] = start + grpsize
1.44 casties 693: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 694: np = int(docinfo['numPages'])
695: pageinfo['end'] = min(pageinfo['end'], np)
696: pageinfo['numgroups'] = int(np / grpsize)
697: if np % grpsize > 0:
1.69 abukhman 698: pageinfo['numgroups'] += 1
1.44 casties 699: pageinfo['viewMode'] = viewMode
700: pageinfo['tocMode'] = tocMode
1.45 abukhman 701: pageinfo['query'] = self.REQUEST.get('query',' ')
702: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
703: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 704: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 705: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 706: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 707: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 708: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 709: toc = int (pageinfo['tocPN'])
710: pageinfo['textPages'] =int (toc)
711:
712: if 'tocSize_%s'%tocMode in docinfo:
713: tocSize = int(docinfo['tocSize_%s'%tocMode])
714: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 715: # cached toc
1.48 abukhman 716: if tocSize%tocPageSize>0:
717: tocPages=tocSize/tocPageSize+1
718: else:
719: tocPages=tocSize/tocPageSize
1.69 abukhman 720: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 721: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 722: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 723: return pageinfo
1.69.2.12! abukhman 724:
! 725: def getOverview(self, mode="text" , docinfo=None, pageinfo=None, url=None, viewMode="auto", start=None,pn=1,textURLPath="auto", **args):
! 726: """overview mode all thumbnails in one window"""
! 727:
! 728: docinfo = self.getDocinfo(mode=mode,url=url)
! 729: pageinfo = self.getPageinfo(current=pn,docinfo=docinfo)
! 730:
! 731: return (docinfo, pageinfo, viewMode)
1.3 casties 732:
1.69 abukhman 733: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 734: """init document viewer"""
735: self.title=title
736: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 737: self.thumbrows = thumbrows
738: self.thumbcols = thumbcols
1.8 casties 739: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 740: if RESPONSE is not None:
741: RESPONSE.redirect('manage_main')
1.1 dwinter 742:
743: def manage_AddDocumentViewerForm(self):
744: """add the viewer form"""
1.3 casties 745: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 746: return pt()
747:
1.43 casties 748: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 749: """add the viewer"""
1.43 casties 750: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 751: self._setObject(id,newObj)
752:
753: if RESPONSE is not None:
754: RESPONSE.redirect('manage_main')
1.3 casties 755:
756: ## DocumentViewerTemplate class
757: class DocumentViewerTemplate(ZopePageTemplate):
758: """Template for document viewer"""
759: meta_type="DocumentViewer Template"
760:
761:
762: def manage_addDocumentViewerTemplateForm(self):
763: """Form for adding"""
764: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
765: return pt()
766:
767: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
768: REQUEST=None, submit=None):
769: "Add a Page Template with optional file content."
770:
771: self._setObject(id, DocumentViewerTemplate(id))
772: ob = getattr(self, id)
1.23 dwinter 773: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
774: logging.info("txt %s:"%txt)
775: ob.pt_edit(txt,"text/html")
1.3 casties 776: if title:
777: ob.pt_setTitle(title)
778: try:
779: u = self.DestinationURL()
780: except AttributeError:
781: u = REQUEST['URL1']
782:
783: u = "%s/%s" % (u, urllib.quote(id))
784: REQUEST.RESPONSE.redirect(u+'/manage_main')
785: return ''
786:
787:
1.14 casties 788:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>