Annotation of documentViewer/documentViewer.py, revision 1.99
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:
1.70 casties 9: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.73 casties 10: import Ft.Xml.Domlette
1.1 dwinter 11: import os.path
1.7 casties 12: import sys
1.1 dwinter 13: import urllib
1.70 casties 14: import urllib2
1.20 dwinter 15: import logging
1.28 casties 16: import math
1.18 dwinter 17: import urlparse
1.70 casties 18: import cStringIO
1.99 ! dwinter 19: import re
1.43 casties 20:
1.22 dwinter 21: def logger(txt,method,txt2):
22: """logging"""
23: logging.info(txt+ txt2)
24:
25:
1.4 casties 26: def getInt(number, default=0):
27: """returns always an int (0 in case of problems)"""
28: try:
29: return int(number)
30: except:
1.29 casties 31: return int(default)
1.4 casties 32:
1.1 dwinter 33: def getTextFromNode(nodename):
1.18 dwinter 34: """get the cdata content of a node"""
1.8 casties 35: if nodename is None:
36: return ""
1.1 dwinter 37: nodelist=nodename.childNodes
38: rc = ""
39: for node in nodelist:
40: if node.nodeType == node.TEXT_NODE:
41: rc = rc + node.data
42: return rc
43:
1.43 casties 44: def serializeNode(node, encoding='utf-8'):
45: """returns a string containing node as XML"""
46: buf = cStringIO.StringIO()
1.75 casties 47: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
1.43 casties 48: s = buf.getvalue()
49: buf.close()
50: return s
51:
1.9 casties 52:
53: def getParentDir(path):
54: """returns pathname shortened by one"""
55: return '/'.join(path.split('/')[0:-1])
56:
57:
1.70 casties 58: def getHttpData(url, data=None, num_tries=3, timeout=10):
59: """returns result from url+data HTTP request"""
60: # we do GET (by appending data to url)
61: if isinstance(data, str) or isinstance(data, unicode):
62: # if data is string then append
63: url = "%s?%s"%(url,data)
64: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
65: # urlencode
66: url = "%s?%s"%(url,urllib.urlencode(data))
67:
68: response = None
69: errmsg = None
70: for cnt in range(num_tries):
71: try:
1.95 abukhman 72: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
1.70 casties 73: if sys.version_info < (2, 6):
74: # set timeout on socket -- ugly :-(
75: import socket
76: socket.setdefaulttimeout(float(timeout))
77: response = urllib2.urlopen(url)
78: else:
79: response = urllib2.urlopen(url,timeout=float(timeout))
80: # check result?
81: break
82: except urllib2.HTTPError, e:
1.95 abukhman 83: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
1.70 casties 84: errmsg = str(e)
85: # stop trying
86: break
87: except urllib2.URLError, e:
1.95 abukhman 88: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
1.70 casties 89: errmsg = str(e)
90: # stop trying
91: #break
92:
93: if response is not None:
94: data = response.read()
95: response.close()
96: return data
97:
98: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
99: #return None
1.1 dwinter 100:
101:
102:
1.3 casties 103: ##
104: ## documentViewer class
105: ##
106: class documentViewer(Folder):
1.1 dwinter 107: """document viewer"""
108: meta_type="Document viewer"
109:
110: security=ClassSecurityInfo()
1.3 casties 111: manage_options=Folder.manage_options+(
1.1 dwinter 112: {'label':'main config','action':'changeDocumentViewerForm'},
113: )
114:
1.3 casties 115: # templates and forms
116: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 117: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
118: toc_text = PageTemplateFile('zpt/toc_text', globals())
119: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 120: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
121: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 122: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 123: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 124: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 125: head_main = PageTemplateFile('zpt/head_main', globals())
126: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 127: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 128:
129:
1.32 dwinter 130: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 131: security.declareProtected('View management screens','changeDocumentViewerForm')
132: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
133:
1.1 dwinter 134:
1.45 abukhman 135: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 136: """init document viewer"""
137: self.id=id
138: self.title=title
1.4 casties 139: self.thumbcols = thumbcols
140: self.thumbrows = thumbrows
1.8 casties 141: # authgroups is list of authorized groups (delimited by ,)
142: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 143: # create template folder so we can always use template.something
144:
145: templateFolder = Folder('template')
146: #self['template'] = templateFolder # Zope-2.12 style
147: self._setObject('template',templateFolder) # old style
148: try:
1.70 casties 149: import MpdlXmlTextServer
1.71 casties 150: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 151: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 152: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 153: except Exception, e:
1.70 casties 154: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 155: try:
156: from Products.zogiLib.zogiLib import zogiLib
157: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
158: #templateFolder['zogilib'] = zogilib
159: templateFolder._setObject('zogilib',zogilib)
160: except Exception, e:
161: logging.error("Unable to create zogiLib for zogilib: "+str(e))
162:
1.70 casties 163:
164: # proxy text server methods to fulltextclient
165: def getTextPage(self, **args):
166: """get page"""
167: return self.template.fulltextclient.getTextPage(**args)
168:
169: def getQuery(self, **args):
170: """get query"""
171: return self.template.fulltextclient.getQuery(**args)
172:
173: def getSearch(self, **args):
174: """get search"""
175: return self.template.fulltextclient.getSearch(**args)
176:
1.72 casties 177: def getNumPages(self, docinfo):
1.70 casties 178: """get numpages"""
1.72 casties 179: return self.template.fulltextclient.getNumPages(docinfo)
1.70 casties 180:
181: def getTranslate(self, **args):
182: """get translate"""
183: return self.template.fulltextclient.getTranslate(**args)
184:
185: def getLemma(self, **args):
186: """get lemma"""
187: return self.template.fulltextclient.getLemma(**args)
188:
189: def getToc(self, **args):
190: """get toc"""
191: return self.template.fulltextclient.getToc(**args)
192:
193: def getTocPage(self, **args):
194: """get tocpage"""
195: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 196:
1.70 casties 197:
1.32 dwinter 198: security.declareProtected('View','thumbs_rss')
199: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
200: '''
201: view it
202: @param mode: defines how to access the document behind url
203: @param url: url which contains display information
204: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
205:
206: '''
1.95 abukhman 207: logging.debug("HHHHHHHHHHHHHH:load the rss")
208: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 209:
210: if not hasattr(self, 'template'):
211: # create template folder if it doesn't exist
212: self.manage_addFolder('template')
213:
214: if not self.digilibBaseUrl:
215: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
216:
217: docinfo = self.getDocinfo(mode=mode,url=url)
218: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
219: pt = getattr(self.template, 'thumbs_main_rss')
220:
221: if viewMode=="auto": # automodus gewaehlt
1.70 casties 222: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 223: viewMode="text"
224: else:
225: viewMode="images"
226:
227: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
228:
1.3 casties 229: security.declareProtected('View','index_html')
1.97 abukhman 230: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
1.3 casties 231: '''
232: view it
1.26 casties 233: @param mode: defines how to access the document behind url
1.3 casties 234: @param url: url which contains display information
1.44 casties 235: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 236: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 237: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 238: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 239: '''
240:
1.95 abukhman 241: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 242:
1.3 casties 243: if not hasattr(self, 'template'):
1.43 casties 244: # this won't work
245: logging.error("template folder missing!")
246: return "ERROR: template folder missing!"
1.3 casties 247:
1.43 casties 248: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 249: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 250:
1.4 casties 251: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 252:
1.44 casties 253: if tocMode != "thumbs":
254: # get table of contents
255: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 256:
1.21 dwinter 257: if viewMode=="auto": # automodus gewaehlt
1.71 casties 258: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 259: viewMode="text_dict"
1.21 dwinter 260: else:
261: viewMode="images"
1.44 casties 262:
1.97 abukhman 263: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 264:
1.44 casties 265: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 266: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 267:
1.36 dwinter 268: def generateMarks(self,mk):
269: ret=""
1.44 casties 270: if mk is None:
271: return ""
1.73 casties 272: if not isinstance(mk, list):
1.71 casties 273: mk=[mk]
1.36 dwinter 274: for m in mk:
1.37 dwinter 275: ret+="mk=%s"%m
1.36 dwinter 276: return ret
1.43 casties 277:
1.44 casties 278:
1.43 casties 279: def findDigilibUrl(self):
280: """try to get the digilib URL from zogilib"""
281: url = self.template.zogilib.getDLBaseUrl()
282: return url
1.67 casties 283:
284: def getDocumentViewerURL(self):
285: """returns the URL of this instance"""
286: return self.absolute_url()
1.43 casties 287:
288: def getStyle(self, idx, selected, style=""):
289: """returns a string with the given style and append 'sel' if path == selected."""
290: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
291: if idx == selected:
292: return style + 'sel'
293: else:
294: return style
1.36 dwinter 295:
1.4 casties 296: def getLink(self,param=None,val=None):
297: """link to documentviewer with parameter param set to val"""
1.9 casties 298: params=self.REQUEST.form.copy()
1.4 casties 299: if param is not None:
1.7 casties 300: if val is None:
301: if params.has_key(param):
302: del params[param]
1.4 casties 303: else:
1.9 casties 304: params[param] = str(val)
1.43 casties 305:
306: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 307: params["mode"] = "imagepath"
308: params["url"] = getParentDir(params["url"])
1.7 casties 309:
1.9 casties 310: # quote values and assemble into query string
1.74 casties 311: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
312: ps = urllib.urlencode(params)
1.9 casties 313: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 314: return url
315:
1.32 dwinter 316: def getLinkAmp(self,param=None,val=None):
317: """link to documentviewer with parameter param set to val"""
318: params=self.REQUEST.form.copy()
319: if param is not None:
320: if val is None:
321: if params.has_key(param):
322: del params[param]
323: else:
324: params[param] = str(val)
325:
326: # quote values and assemble into query string
1.95 abukhman 327: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 328: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
329: url=self.REQUEST['URL1']+"?"+ps
330: return url
1.40 casties 331:
1.26 casties 332: def getInfo_xml(self,url,mode):
333: """returns info about the document as XML"""
334:
335: if not self.digilibBaseUrl:
336: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
337:
338: docinfo = self.getDocinfo(mode=mode,url=url)
339: pt = getattr(self.template, 'info_xml')
340: return pt(docinfo=docinfo)
341:
1.4 casties 342:
1.9 casties 343: def isAccessible(self, docinfo):
1.8 casties 344: """returns if access to the resource is granted"""
345: access = docinfo.get('accessType', None)
1.95 abukhman 346: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 347: if access is not None and access == 'free':
1.95 abukhman 348: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 349: return True
1.17 casties 350: elif access is None or access in self.authgroups:
1.9 casties 351: # only local access -- only logged in users
352: user = getSecurityManager().getUser()
1.95 abukhman 353: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 354: if user is not None:
355: #print "user: ", user
356: return (user.getUserName() != "Anonymous User")
357: else:
358: return False
1.8 casties 359:
1.95 abukhman 360: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 361: return False
1.9 casties 362:
1.8 casties 363:
1.35 dwinter 364: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 365: """gibt param von dlInfo aus"""
1.7 casties 366: if docinfo is None:
367: docinfo = {}
1.35 dwinter 368:
369: for x in range(cut):
1.38 dwinter 370:
1.35 dwinter 371: path=getParentDir(path)
1.38 dwinter 372:
1.13 casties 373: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 374:
1.95 abukhman 375: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 376:
1.70 casties 377: txt = getHttpData(infoUrl)
378: if txt is None:
1.13 casties 379: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 380:
381: dom = Parse(txt)
1.10 casties 382: sizes=dom.xpath("//dir/size")
1.95 abukhman 383: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 384:
1.10 casties 385: if sizes:
386: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 387: else:
388: docinfo['numPages'] = 0
1.43 casties 389:
390: # TODO: produce and keep list of image names and numbers
1.7 casties 391:
392: return docinfo
1.8 casties 393:
1.99 ! dwinter 394: def getIndexMetaPath(self,url):
! 395: """gib nur den Pfad zurueck"""
! 396: regexp = re.compile(r".*(experimental|permanent)/(.*)")
! 397: regpath = regexp.match(url)
! 398: if (regpath==None):
! 399: return ""
! 400:
! 401: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
! 402:
! 403: def getIndexMetaUrl(self,url):
! 404: """returns utr of index.meta document at url"""
! 405:
1.12 casties 406: metaUrl = None
1.9 casties 407: if url.startswith("http://"):
408: # real URL
1.12 casties 409: metaUrl = url
1.9 casties 410: else:
411: # online path
412: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 413: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 414: if not metaUrl.endswith("index.meta"):
415: metaUrl += "/index.meta"
1.99 ! dwinter 416:
! 417: return metaUrl
! 418:
! 419: def getDomFromIndexMeta(self, url):
! 420: """get dom from index meta"""
! 421: dom = None
! 422: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 423:
1.99 ! dwinter 424: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 425: txt=getHttpData(metaUrl)
426: if txt is None:
1.12 casties 427: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 428:
429: dom = Parse(txt)
1.9 casties 430: return dom
1.20 dwinter 431:
432: def getPresentationInfoXML(self, url):
433: """returns dom of info.xml document at url"""
434: dom = None
435: metaUrl = None
436: if url.startswith("http://"):
437: # real URL
438: metaUrl = url
439: else:
440: # online path
441: server=self.digilibBaseUrl+"/servlet/Texter?fn="
442: metaUrl=server+url.replace("/mpiwg/online","")
443:
1.70 casties 444: txt=getHttpData(metaUrl)
445: if txt is None:
1.20 dwinter 446: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 447:
448: dom = Parse(txt)
1.20 dwinter 449: return dom
1.9 casties 450:
451:
1.33 dwinter 452: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 453: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 454: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 455:
456: access = None
457:
458: if docinfo is None:
459: docinfo = {}
460:
461: if dom is None:
1.38 dwinter 462: for x in range(cut):
1.33 dwinter 463: path=getParentDir(path)
1.99 ! dwinter 464: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 465:
1.8 casties 466: acctype = dom.xpath("//access-conditions/access/@type")
467: if acctype and (len(acctype)>0):
468: access=acctype[0].value
1.9 casties 469: if access in ['group', 'institution']:
1.8 casties 470: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
471:
472: docinfo['accessType'] = access
473: return docinfo
1.6 casties 474:
1.8 casties 475:
1.33 dwinter 476: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 477: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 478: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 479:
1.3 casties 480: if docinfo is None:
481: docinfo = {}
1.38 dwinter 482:
1.3 casties 483: if dom is None:
1.38 dwinter 484: for x in range(cut):
1.33 dwinter 485: path=getParentDir(path)
1.99 ! dwinter 486: dom = self.getDomFromIndexMeta(path)
! 487:
! 488: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 489:
1.95 abukhman 490: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 491: # put in all raw bib fields as dict "bib"
492: bib = dom.xpath("//bib/*")
493: if bib and len(bib)>0:
494: bibinfo = {}
495: for e in bib:
496: bibinfo[e.localName] = getTextFromNode(e)
497: docinfo['bib'] = bibinfo
498:
499: # extract some fields (author, title, year) according to their mapping
1.4 casties 500: metaData=self.metadata.main.meta.bib
501: bibtype=dom.xpath("//bib/@type")
502: if bibtype and (len(bibtype)>0):
503: bibtype=bibtype[0].value
1.2 dwinter 504: else:
1.4 casties 505: bibtype="generic"
1.27 casties 506:
1.4 casties 507: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 508: docinfo['bib_type'] = bibtype
1.4 casties 509: bibmap=metaData.generateMappingForType(bibtype)
1.99 ! dwinter 510: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
! 511: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 512: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 513: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 514: try:
515: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
516: except: pass
517: try:
518: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
519: except: pass
520: try:
521: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
522: except: pass
1.95 abukhman 523: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 524: try:
525: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
526: except:
527: docinfo['lang']=''
1.27 casties 528:
1.3 casties 529: return docinfo
1.42 abukhman 530:
531:
1.43 casties 532: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
533: """parse texttool tag in index meta"""
1.95 abukhman 534: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 535: if docinfo is None:
536: docinfo = {}
537: if docinfo.get('lang', None) is None:
538: docinfo['lang'] = '' # default keine Sprache gesetzt
539: if dom is None:
1.99 ! dwinter 540: dom = self.getDomFromIndexMeta(url)
1.43 casties 541:
542: archivePath = None
543: archiveName = None
544:
545: archiveNames = dom.xpath("//resource/name")
546: if archiveNames and (len(archiveNames) > 0):
547: archiveName = getTextFromNode(archiveNames[0])
548: else:
1.70 casties 549: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 550:
551: archivePaths = dom.xpath("//resource/archive-path")
552: if archivePaths and (len(archivePaths) > 0):
553: archivePath = getTextFromNode(archivePaths[0])
554: # clean up archive path
555: if archivePath[0] != '/':
556: archivePath = '/' + archivePath
557: if archiveName and (not archivePath.endswith(archiveName)):
558: archivePath += "/" + archiveName
559: else:
560: # try to get archive-path from url
1.95 abukhman 561: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 562: if (not url.startswith('http')):
563: archivePath = url.replace('index.meta', '')
564:
565: if archivePath is None:
566: # we balk without archive-path
567: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
568:
569: imageDirs = dom.xpath("//texttool/image")
570: if imageDirs and (len(imageDirs) > 0):
571: imageDir = getTextFromNode(imageDirs[0])
572:
573: else:
574: # we balk with no image tag / not necessary anymore because textmode is now standard
575: #raise IOError("No text-tool info in %s"%(url))
576: imageDir = ""
577: #xquery="//pb"
578: docinfo['imagePath'] = "" # keine Bilder
579: docinfo['imageURL'] = ""
580:
581: if imageDir and archivePath:
582: #print "image: ", imageDir, " archivepath: ", archivePath
583: imageDir = os.path.join(archivePath, imageDir)
584: imageDir = imageDir.replace("/mpiwg/online", '')
585: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
586: docinfo['imagePath'] = imageDir
587:
588: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
589:
590: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
591: if viewerUrls and (len(viewerUrls) > 0):
592: viewerUrl = getTextFromNode(viewerUrls[0])
593: docinfo['viewerURL'] = viewerUrl
1.70 casties 594:
595: # old style text URL
1.43 casties 596: textUrls = dom.xpath("//texttool/text")
597: if textUrls and (len(textUrls) > 0):
598: textUrl = getTextFromNode(textUrls[0])
599: if urlparse.urlparse(textUrl)[0] == "": #keine url
600: textUrl = os.path.join(archivePath, textUrl)
601: # fix URLs starting with /mpiwg/online
602: if textUrl.startswith("/mpiwg/online"):
603: textUrl = textUrl.replace("/mpiwg/online", '', 1)
604:
605: docinfo['textURL'] = textUrl
606:
1.70 casties 607: # new style text-url-path
1.43 casties 608: textUrls = dom.xpath("//texttool/text-url-path")
609: if textUrls and (len(textUrls) > 0):
610: textUrl = getTextFromNode(textUrls[0])
1.51 casties 611: docinfo['textURLPath'] = textUrl
612: if not docinfo['imagePath']:
613: # text-only, no page images
1.72 casties 614: docinfo = self.getNumPages(docinfo)
1.43 casties 615:
616: presentationUrls = dom.xpath("//texttool/presentation")
617: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
618:
619: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
620: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
621: # durch den relativen Pfad auf die presentation infos
622: presentationPath = getTextFromNode(presentationUrls[0])
623: if url.endswith("index.meta"):
624: presentationUrl = url.replace('index.meta', presentationPath)
625: else:
626: presentationUrl = url + "/" + presentationPath
1.51 casties 627:
1.43 casties 628: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
629:
630: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 631:
1.43 casties 632: return docinfo
1.3 casties 633:
1.20 dwinter 634:
635: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
636: """gets the bibliographical information from the preseantion entry in texttools
637: """
638: dom=self.getPresentationInfoXML(url)
1.29 casties 639: try:
640: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
641: except:
642: pass
643: try:
644: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
645: except:
646: pass
647: try:
648: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
649: except:
650: pass
1.20 dwinter 651: return docinfo
652:
1.33 dwinter 653: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 654: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 655: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 656: if docinfo is None:
657: docinfo = {}
1.6 casties 658: path=path.replace("/mpiwg/online","")
1.3 casties 659: docinfo['imagePath'] = path
1.35 dwinter 660: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 661:
1.39 dwinter 662: pathorig=path
1.38 dwinter 663: for x in range(cut):
664: path=getParentDir(path)
1.95 abukhman 665: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 666: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 667: docinfo['imageURL'] = imageUrl
668:
1.39 dwinter 669: #path ist the path to the images it assumes that the index.meta file is one level higher.
670: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
671: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 672: return docinfo
673:
1.2 dwinter 674:
1.3 casties 675: def getDocinfo(self, mode, url):
676: """returns docinfo depending on mode"""
1.95 abukhman 677: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 678: # look for cached docinfo in session
1.21 dwinter 679: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 680: docinfo = self.REQUEST.SESSION['docinfo']
681: # check if its still current
682: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 683: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 684: return docinfo
685: # new docinfo
686: docinfo = {'mode': mode, 'url': url}
687: if mode=="texttool": #index.meta with texttool information
688: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
689: elif mode=="imagepath":
690: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 691: elif mode=="filepath":
1.37 dwinter 692: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 693: else:
1.95 abukhman 694: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 695: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 696:
1.95 abukhman 697: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 698: self.REQUEST.SESSION['docinfo'] = docinfo
699: return docinfo
1.69 abukhman 700:
1.97 abukhman 701: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
1.3 casties 702: """returns pageinfo with the given parameters"""
703: pageinfo = {}
1.4 casties 704: current = getInt(current)
705: pageinfo['current'] = current
706: rows = int(rows or self.thumbrows)
707: pageinfo['rows'] = rows
708: cols = int(cols or self.thumbcols)
709: pageinfo['cols'] = cols
710: grpsize = cols * rows
711: pageinfo['groupsize'] = grpsize
1.28 casties 712: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
713: # int(current / grpsize) * grpsize +1))
1.3 casties 714: pageinfo['start'] = start
1.4 casties 715: pageinfo['end'] = start + grpsize
1.44 casties 716: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 717: np = int(docinfo['numPages'])
718: pageinfo['end'] = min(pageinfo['end'], np)
719: pageinfo['numgroups'] = int(np / grpsize)
720: if np % grpsize > 0:
1.69 abukhman 721: pageinfo['numgroups'] += 1
1.44 casties 722: pageinfo['viewMode'] = viewMode
723: pageinfo['tocMode'] = tocMode
1.98 abukhman 724: #pageinfo['characterNormalization'] =characterNormalization
725: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
1.45 abukhman 726: pageinfo['query'] = self.REQUEST.get('query',' ')
727: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
728: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 729: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 730: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 731: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 732: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 733: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 734: toc = int (pageinfo['tocPN'])
735: pageinfo['textPages'] =int (toc)
1.90 abukhman 736:
1.48 abukhman 737: if 'tocSize_%s'%tocMode in docinfo:
738: tocSize = int(docinfo['tocSize_%s'%tocMode])
739: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 740: # cached toc
1.48 abukhman 741: if tocSize%tocPageSize>0:
742: tocPages=tocSize/tocPageSize+1
743: else:
744: tocPages=tocSize/tocPageSize
1.69 abukhman 745: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 746: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 747: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 748: return pageinfo
749:
1.69 abukhman 750: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 751: """init document viewer"""
752: self.title=title
753: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 754: self.thumbrows = thumbrows
755: self.thumbcols = thumbcols
1.8 casties 756: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 757: if RESPONSE is not None:
758: RESPONSE.redirect('manage_main')
1.1 dwinter 759:
760: def manage_AddDocumentViewerForm(self):
761: """add the viewer form"""
1.3 casties 762: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 763: return pt()
764:
1.43 casties 765: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 766: """add the viewer"""
1.43 casties 767: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 768: self._setObject(id,newObj)
769:
770: if RESPONSE is not None:
771: RESPONSE.redirect('manage_main')
1.3 casties 772:
773: ## DocumentViewerTemplate class
774: class DocumentViewerTemplate(ZopePageTemplate):
775: """Template for document viewer"""
776: meta_type="DocumentViewer Template"
777:
778:
779: def manage_addDocumentViewerTemplateForm(self):
780: """Form for adding"""
781: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
782: return pt()
783:
784: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
785: REQUEST=None, submit=None):
786: "Add a Page Template with optional file content."
787:
788: self._setObject(id, DocumentViewerTemplate(id))
789: ob = getattr(self, id)
1.23 dwinter 790: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 791: logging.info("txt %s:"%txt)
1.23 dwinter 792: ob.pt_edit(txt,"text/html")
1.3 casties 793: if title:
794: ob.pt_setTitle(title)
795: try:
796: u = self.DestinationURL()
797: except AttributeError:
798: u = REQUEST['URL1']
799:
800: u = "%s/%s" % (u, urllib.quote(id))
801: REQUEST.RESPONSE.redirect(u+'/manage_main')
802: return ''
803:
804:
1.14 casties 805:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to documentViewer.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / documentViewer