Annotation of documentViewer/documentViewer.py, revision 1.48
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:
9: from Ft.Xml.Domlette import NonvalidatingReader
10: from Ft.Xml.Domlette import PrettyPrint, Print
1.11 casties 11: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.1 dwinter 12:
1.47 abukhman 13: from xml.dom.minidom import parse, parseString
14:
15:
1.42 abukhman 16:
1.1 dwinter 17: import Ft.Xml.XPath
1.43 casties 18: import cStringIO
1.42 abukhman 19: import xmlrpclib
1.1 dwinter 20: import os.path
1.7 casties 21: import sys
1.1 dwinter 22: import cgi
23: import urllib
1.20 dwinter 24: import logging
1.28 casties 25: import math
1.22 dwinter 26:
1.18 dwinter 27: import urlparse
1.37 dwinter 28: from types import *
1.43 casties 29:
1.22 dwinter 30: def logger(txt,method,txt2):
31: """logging"""
32: logging.info(txt+ txt2)
33:
34:
1.4 casties 35: def getInt(number, default=0):
36: """returns always an int (0 in case of problems)"""
37: try:
38: return int(number)
39: except:
1.29 casties 40: return int(default)
1.4 casties 41:
1.1 dwinter 42: def getTextFromNode(nodename):
1.18 dwinter 43: """get the cdata content of a node"""
1.8 casties 44: if nodename is None:
45: return ""
1.1 dwinter 46: nodelist=nodename.childNodes
47: rc = ""
48: for node in nodelist:
49: if node.nodeType == node.TEXT_NODE:
50: rc = rc + node.data
51: return rc
52:
1.43 casties 53: def serializeNode(node, encoding='utf-8'):
54: """returns a string containing node as XML"""
55: buf = cStringIO.StringIO()
56: Print(node, stream=buf, encoding=encoding)
57: s = buf.getvalue()
58: buf.close()
59: return s
60:
1.9 casties 61:
62: def getParentDir(path):
63: """returns pathname shortened by one"""
64: return '/'.join(path.split('/')[0:-1])
65:
66:
1.1 dwinter 67: import socket
68:
1.8 casties 69: def urlopen(url,timeout=2):
1.1 dwinter 70: """urlopen mit timeout"""
1.8 casties 71: socket.setdefaulttimeout(timeout)
1.1 dwinter 72: ret=urllib.urlopen(url)
73: socket.setdefaulttimeout(5)
74: return ret
75:
76:
1.3 casties 77: ##
78: ## documentViewer class
79: ##
80: class documentViewer(Folder):
1.1 dwinter 81: """document viewer"""
1.20 dwinter 82: #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
1.18 dwinter 83:
1.1 dwinter 84: meta_type="Document viewer"
85:
86: security=ClassSecurityInfo()
1.3 casties 87: manage_options=Folder.manage_options+(
1.1 dwinter 88: {'label':'main config','action':'changeDocumentViewerForm'},
89: )
90:
1.3 casties 91: # templates and forms
92: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 93: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
94: toc_text = PageTemplateFile('zpt/toc_text', globals())
95: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 96: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
97: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 98: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.48 ! abukhman 99: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 100: head_main = PageTemplateFile('zpt/head_main', globals())
101: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 102: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.3 casties 103:
1.32 dwinter 104: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 105: security.declareProtected('View management screens','changeDocumentViewerForm')
106: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
107:
1.1 dwinter 108:
1.45 abukhman 109: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 110: """init document viewer"""
111: self.id=id
112: self.title=title
1.4 casties 113: self.thumbcols = thumbcols
114: self.thumbrows = thumbrows
1.8 casties 115: # authgroups is list of authorized groups (delimited by ,)
116: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 117: # create template folder so we can always use template.something
118:
119: templateFolder = Folder('template')
120: #self['template'] = templateFolder # Zope-2.12 style
121: self._setObject('template',templateFolder) # old style
122: try:
123: from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy
124: xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)
125: #templateFolder['fulltextclient'] = xmlRpcClient
126: templateFolder._setObject('fulltextclient',xmlRpcClient)
127: except Exception, e:
128: logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))
129: try:
130: from Products.zogiLib.zogiLib import zogiLib
131: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
132: #templateFolder['zogilib'] = zogilib
133: templateFolder._setObject('zogilib',zogilib)
134: except Exception, e:
135: logging.error("Unable to create zogiLib for zogilib: "+str(e))
136:
1.3 casties 137:
1.32 dwinter 138: security.declareProtected('View','thumbs_rss')
139: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
140: '''
141: view it
142: @param mode: defines how to access the document behind url
143: @param url: url which contains display information
144: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
145:
146: '''
1.43 casties 147: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 148: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
149:
150: if not hasattr(self, 'template'):
151: # create template folder if it doesn't exist
152: self.manage_addFolder('template')
153:
154: if not self.digilibBaseUrl:
155: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
156:
157: docinfo = self.getDocinfo(mode=mode,url=url)
158: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
159: pt = getattr(self.template, 'thumbs_main_rss')
160:
161: if viewMode=="auto": # automodus gewaehlt
162: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
163: viewMode="text"
164: else:
165: viewMode="images"
166:
167: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
168:
1.3 casties 169: security.declareProtected('View','index_html')
1.45 abukhman 170: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3 casties 171: '''
172: view it
1.26 casties 173: @param mode: defines how to access the document behind url
1.3 casties 174: @param url: url which contains display information
1.44 casties 175: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 ! abukhman 176: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.45 abukhman 177: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph)
1.3 casties 178: '''
179:
1.43 casties 180: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 181:
1.3 casties 182: if not hasattr(self, 'template'):
1.43 casties 183: # this won't work
184: logging.error("template folder missing!")
185: return "ERROR: template folder missing!"
1.3 casties 186:
1.43 casties 187: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 188: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
189:
1.4 casties 190: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 191:
192:
1.44 casties 193: if tocMode != "thumbs":
194: # get table of contents
195: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 196:
197: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
198:
1.21 dwinter 199: if viewMode=="auto": # automodus gewaehlt
1.43 casties 200: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.21 dwinter 201: viewMode="text"
202: else:
203: viewMode="images"
1.44 casties 204:
205: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 206: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 207:
1.36 dwinter 208: def generateMarks(self,mk):
209: ret=""
1.44 casties 210: if mk is None:
211: return ""
212: if type(mk) is not ListType:
213: mk=[mk]
1.36 dwinter 214: for m in mk:
1.37 dwinter 215: ret+="mk=%s"%m
1.36 dwinter 216: return ret
1.43 casties 217:
1.44 casties 218:
1.43 casties 219: def findDigilibUrl(self):
220: """try to get the digilib URL from zogilib"""
221: url = self.template.zogilib.getDLBaseUrl()
222: return url
223:
224: def getStyle(self, idx, selected, style=""):
225: """returns a string with the given style and append 'sel' if path == selected."""
226: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
227: if idx == selected:
228: return style + 'sel'
229: else:
230: return style
1.36 dwinter 231:
1.4 casties 232: def getLink(self,param=None,val=None):
233: """link to documentviewer with parameter param set to val"""
1.9 casties 234: params=self.REQUEST.form.copy()
1.4 casties 235: if param is not None:
1.7 casties 236: if val is None:
237: if params.has_key(param):
238: del params[param]
1.4 casties 239: else:
1.9 casties 240: params[param] = str(val)
1.43 casties 241:
242: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 243: params["mode"] = "imagepath"
244: params["url"] = getParentDir(params["url"])
1.7 casties 245:
1.9 casties 246: # quote values and assemble into query string
247: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
248: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 249: return url
250:
1.32 dwinter 251: def getLinkAmp(self,param=None,val=None):
252: """link to documentviewer with parameter param set to val"""
253: params=self.REQUEST.form.copy()
254: if param is not None:
255: if val is None:
256: if params.has_key(param):
257: del params[param]
258: else:
259: params[param] = str(val)
260:
261: # quote values and assemble into query string
262: logging.info("XYXXXXX: %s"%repr(params.items()))
263: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
264: url=self.REQUEST['URL1']+"?"+ps
265: return url
1.40 casties 266:
1.26 casties 267: def getInfo_xml(self,url,mode):
268: """returns info about the document as XML"""
269:
270: if not self.digilibBaseUrl:
271: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
272:
273: docinfo = self.getDocinfo(mode=mode,url=url)
274: pt = getattr(self.template, 'info_xml')
275: return pt(docinfo=docinfo)
276:
1.4 casties 277:
1.9 casties 278: def isAccessible(self, docinfo):
1.8 casties 279: """returns if access to the resource is granted"""
280: access = docinfo.get('accessType', None)
1.22 dwinter 281: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
1.17 casties 282: if access is not None and access == 'free':
1.22 dwinter 283: logger("documentViewer (accessOK)", logging.INFO, "access is free")
1.8 casties 284: return True
1.17 casties 285: elif access is None or access in self.authgroups:
1.9 casties 286: # only local access -- only logged in users
287: user = getSecurityManager().getUser()
288: if user is not None:
289: #print "user: ", user
290: return (user.getUserName() != "Anonymous User")
291: else:
292: return False
1.8 casties 293:
1.22 dwinter 294: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
1.8 casties 295: return False
1.9 casties 296:
1.8 casties 297:
1.35 dwinter 298: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 299: """gibt param von dlInfo aus"""
1.13 casties 300: num_retries = 3
1.7 casties 301: if docinfo is None:
302: docinfo = {}
1.35 dwinter 303:
304: for x in range(cut):
1.38 dwinter 305:
1.35 dwinter 306: path=getParentDir(path)
1.38 dwinter 307:
1.13 casties 308: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 309:
1.22 dwinter 310: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
1.6 casties 311:
1.13 casties 312: for cnt in range(num_retries):
1.9 casties 313: try:
1.13 casties 314: # dom = NonvalidatingReader.parseUri(imageUrl)
315: txt=urllib.urlopen(infoUrl).read()
316: dom = Parse(txt)
1.9 casties 317: break
318: except:
1.22 dwinter 319: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9 casties 320: else:
1.13 casties 321: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6 casties 322:
1.10 casties 323: sizes=dom.xpath("//dir/size")
1.22 dwinter 324: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
1.6 casties 325:
1.10 casties 326: if sizes:
327: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 328: else:
329: docinfo['numPages'] = 0
1.43 casties 330:
331: # TODO: produce and keep list of image names and numbers
1.7 casties 332:
333: return docinfo
1.8 casties 334:
1.6 casties 335:
1.9 casties 336: def getIndexMeta(self, url):
337: """returns dom of index.meta document at url"""
1.12 casties 338: num_retries = 3
1.9 casties 339: dom = None
1.12 casties 340: metaUrl = None
1.9 casties 341: if url.startswith("http://"):
342: # real URL
1.12 casties 343: metaUrl = url
1.9 casties 344: else:
345: # online path
346: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 347: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 348: if not metaUrl.endswith("index.meta"):
349: metaUrl += "/index.meta"
1.37 dwinter 350: logging.debug("METAURL: %s"%metaUrl)
1.13 casties 351: for cnt in range(num_retries):
1.9 casties 352: try:
1.12 casties 353: # patch dirk encoding fehler treten dann nicht mehr auf
1.11 casties 354: # dom = NonvalidatingReader.parseUri(metaUrl)
1.12 casties 355: txt=urllib.urlopen(metaUrl).read()
356: dom = Parse(txt)
1.13 casties 357: break
1.9 casties 358: except:
1.44 casties 359: logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.12 casties 360:
361: if dom is None:
362: raise IOError("Unable to read index meta from %s"%(url))
1.9 casties 363:
364: return dom
1.20 dwinter 365:
366: def getPresentationInfoXML(self, url):
367: """returns dom of info.xml document at url"""
368: num_retries = 3
369: dom = None
370: metaUrl = None
371: if url.startswith("http://"):
372: # real URL
373: metaUrl = url
374: else:
375: # online path
376: server=self.digilibBaseUrl+"/servlet/Texter?fn="
377: metaUrl=server+url.replace("/mpiwg/online","")
378:
379: for cnt in range(num_retries):
380: try:
381: # patch dirk encoding fehler treten dann nicht mehr auf
382: # dom = NonvalidatingReader.parseUri(metaUrl)
383: txt=urllib.urlopen(metaUrl).read()
384: dom = Parse(txt)
385: break
386: except:
1.22 dwinter 387: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.20 dwinter 388:
389: if dom is None:
390: raise IOError("Unable to read infoXMLfrom %s"%(url))
391:
392: return dom
1.9 casties 393:
394:
1.33 dwinter 395: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 396: """gets authorization info from the index.meta file at path or given by dom"""
1.22 dwinter 397: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
1.8 casties 398:
399: access = None
400:
401: if docinfo is None:
402: docinfo = {}
403:
404: if dom is None:
1.38 dwinter 405: for x in range(cut):
1.33 dwinter 406: path=getParentDir(path)
407: dom = self.getIndexMeta(path)
1.18 dwinter 408:
1.8 casties 409: acctype = dom.xpath("//access-conditions/access/@type")
410: if acctype and (len(acctype)>0):
411: access=acctype[0].value
1.9 casties 412: if access in ['group', 'institution']:
1.8 casties 413: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
414:
415: docinfo['accessType'] = access
416: return docinfo
1.6 casties 417:
1.8 casties 418:
1.33 dwinter 419: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 420: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 421: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 422:
1.3 casties 423: if docinfo is None:
424: docinfo = {}
1.38 dwinter 425:
1.3 casties 426: if dom is None:
1.38 dwinter 427: for x in range(cut):
1.33 dwinter 428: path=getParentDir(path)
429: dom = self.getIndexMeta(path)
1.39 dwinter 430:
431: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 432: # put in all raw bib fields as dict "bib"
433: bib = dom.xpath("//bib/*")
434: if bib and len(bib)>0:
435: bibinfo = {}
436: for e in bib:
437: bibinfo[e.localName] = getTextFromNode(e)
438: docinfo['bib'] = bibinfo
439:
440: # extract some fields (author, title, year) according to their mapping
1.4 casties 441: metaData=self.metadata.main.meta.bib
442: bibtype=dom.xpath("//bib/@type")
443: if bibtype and (len(bibtype)>0):
444: bibtype=bibtype[0].value
1.2 dwinter 445: else:
1.4 casties 446: bibtype="generic"
1.27 casties 447:
1.4 casties 448: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 449: docinfo['bib_type'] = bibtype
1.4 casties 450: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 451: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 452: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 453: try:
454: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
455: except: pass
456: try:
457: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
458: except: pass
459: try:
460: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
461: except: pass
1.27 casties 462: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 463: try:
464: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
465: except:
466: docinfo['lang']=''
1.27 casties 467:
1.3 casties 468: return docinfo
1.42 abukhman 469:
470:
1.43 casties 471: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
472: """parse texttool tag in index meta"""
473: logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))
474: if docinfo is None:
475: docinfo = {}
476: if docinfo.get('lang', None) is None:
477: docinfo['lang'] = '' # default keine Sprache gesetzt
478: if dom is None:
479: dom = self.getIndexMeta(url)
480:
481: archivePath = None
482: archiveName = None
483:
484: archiveNames = dom.xpath("//resource/name")
485: if archiveNames and (len(archiveNames) > 0):
486: archiveName = getTextFromNode(archiveNames[0])
487: else:
488: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url))
489:
490: archivePaths = dom.xpath("//resource/archive-path")
491: if archivePaths and (len(archivePaths) > 0):
492: archivePath = getTextFromNode(archivePaths[0])
493: # clean up archive path
494: if archivePath[0] != '/':
495: archivePath = '/' + archivePath
496: if archiveName and (not archivePath.endswith(archiveName)):
497: archivePath += "/" + archiveName
498: else:
499: # try to get archive-path from url
500: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url))
501: if (not url.startswith('http')):
502: archivePath = url.replace('index.meta', '')
503:
504: if archivePath is None:
505: # we balk without archive-path
506: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
507:
508: imageDirs = dom.xpath("//texttool/image")
509: if imageDirs and (len(imageDirs) > 0):
510: imageDir = getTextFromNode(imageDirs[0])
511:
512: else:
513: # we balk with no image tag / not necessary anymore because textmode is now standard
514: #raise IOError("No text-tool info in %s"%(url))
515: imageDir = ""
516: #xquery="//pb"
517: docinfo['imagePath'] = "" # keine Bilder
518: docinfo['imageURL'] = ""
519:
520: if imageDir and archivePath:
521: #print "image: ", imageDir, " archivepath: ", archivePath
522: imageDir = os.path.join(archivePath, imageDir)
523: imageDir = imageDir.replace("/mpiwg/online", '')
524: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
525: docinfo['imagePath'] = imageDir
526:
527: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
528:
529: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
530: if viewerUrls and (len(viewerUrls) > 0):
531: viewerUrl = getTextFromNode(viewerUrls[0])
532: docinfo['viewerURL'] = viewerUrl
533:
534: textUrls = dom.xpath("//texttool/text")
535: if textUrls and (len(textUrls) > 0):
536: textUrl = getTextFromNode(textUrls[0])
537: if urlparse.urlparse(textUrl)[0] == "": #keine url
538: textUrl = os.path.join(archivePath, textUrl)
539: # fix URLs starting with /mpiwg/online
540: if textUrl.startswith("/mpiwg/online"):
541: textUrl = textUrl.replace("/mpiwg/online", '', 1)
542:
543: docinfo['textURL'] = textUrl
544:
545: textUrls = dom.xpath("//texttool/text-url-path")
546: if textUrls and (len(textUrls) > 0):
547: textUrl = getTextFromNode(textUrls[0])
548: docinfo['textURLPath'] = textUrl
549:
550: presentationUrls = dom.xpath("//texttool/presentation")
551: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
552:
553: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
554: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
555: # durch den relativen Pfad auf die presentation infos
556: presentationPath = getTextFromNode(presentationUrls[0])
557: if url.endswith("index.meta"):
558: presentationUrl = url.replace('index.meta', presentationPath)
559: else:
560: presentationUrl = url + "/" + presentationPath
561: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
562: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
563:
564: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 565:
1.43 casties 566: return docinfo
1.3 casties 567:
1.20 dwinter 568:
569: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
570: """gets the bibliographical information from the preseantion entry in texttools
571: """
572: dom=self.getPresentationInfoXML(url)
1.29 casties 573: try:
574: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
575: except:
576: pass
577: try:
578: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
579: except:
580: pass
581: try:
582: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
583: except:
584: pass
1.20 dwinter 585: return docinfo
586:
1.33 dwinter 587: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 588: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.22 dwinter 589: logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
1.3 casties 590: if docinfo is None:
591: docinfo = {}
1.6 casties 592: path=path.replace("/mpiwg/online","")
1.3 casties 593: docinfo['imagePath'] = path
1.35 dwinter 594: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 595:
1.39 dwinter 596: pathorig=path
1.38 dwinter 597: for x in range(cut):
598: path=getParentDir(path)
599: logging.error("PATH:"+path)
1.7 casties 600: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 601: docinfo['imageURL'] = imageUrl
602:
1.39 dwinter 603: #path ist the path to the images it assumes that the index.meta file is one level higher.
604: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
605: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 606: return docinfo
607:
1.2 dwinter 608:
1.3 casties 609: def getDocinfo(self, mode, url):
610: """returns docinfo depending on mode"""
1.22 dwinter 611: logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
1.3 casties 612: # look for cached docinfo in session
1.21 dwinter 613: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 614: docinfo = self.REQUEST.SESSION['docinfo']
615: # check if its still current
616: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.22 dwinter 617: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
1.3 casties 618: return docinfo
619: # new docinfo
620: docinfo = {'mode': mode, 'url': url}
621: if mode=="texttool": #index.meta with texttool information
622: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
623: elif mode=="imagepath":
624: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 625: elif mode=="filepath":
1.37 dwinter 626: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 627: else:
1.22 dwinter 628: logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
1.44 casties 629: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 630:
1.22 dwinter 631: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
1.3 casties 632: self.REQUEST.SESSION['docinfo'] = docinfo
633: return docinfo
1.2 dwinter 634:
635:
1.44 casties 636: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 637: """returns pageinfo with the given parameters"""
638: pageinfo = {}
1.4 casties 639: current = getInt(current)
640: pageinfo['current'] = current
641: rows = int(rows or self.thumbrows)
642: pageinfo['rows'] = rows
643: cols = int(cols or self.thumbcols)
644: pageinfo['cols'] = cols
645: grpsize = cols * rows
646: pageinfo['groupsize'] = grpsize
1.28 casties 647: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
648: # int(current / grpsize) * grpsize +1))
1.3 casties 649: pageinfo['start'] = start
1.4 casties 650: pageinfo['end'] = start + grpsize
1.44 casties 651: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 652: np = int(docinfo['numPages'])
653: pageinfo['end'] = min(pageinfo['end'], np)
654: pageinfo['numgroups'] = int(np / grpsize)
655: if np % grpsize > 0:
656: pageinfo['numgroups'] += 1
1.48 ! abukhman 657:
! 658:
1.44 casties 659: pageinfo['viewMode'] = viewMode
660: pageinfo['tocMode'] = tocMode
1.45 abukhman 661: pageinfo['query'] = self.REQUEST.get('query',' ')
662: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
663: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 ! abukhman 664:
! 665: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
! 666:
1.45 abukhman 667: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
668: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '20')
1.44 casties 669: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 ! abukhman 670: toc = int (pageinfo['tocPN'])
! 671: pageinfo['textPages'] =int (toc)
! 672:
! 673: if 'tocSize_%s'%tocMode in docinfo:
! 674: tocSize = int(docinfo['tocSize_%s'%tocMode])
! 675: tocPageSize = int(pageinfo['tocPageSize'])
1.47 abukhman 676: # cached toc
1.48 ! abukhman 677:
! 678: if tocSize%tocPageSize>0:
! 679: tocPages=tocSize/tocPageSize+1
! 680: else:
! 681: tocPages=tocSize/tocPageSize
! 682: pageinfo['tocPN'] = min (tocPages,toc)
! 683:
1.45 abukhman 684: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
685: pageinfo['sn'] =self.REQUEST.get('sn','1')
1.38 dwinter 686:
1.3 casties 687: return pageinfo
688:
1.45 abukhman 689: def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None):
690: """get search list"""
691: docpath = docinfo['textURLPath']
692: pagesize = pageinfo['queryPageSize']
693: pn = pageinfo['searchPN']
694: sn = pageinfo['sn']
695: query =pageinfo['query']
696: queryType =pageinfo['queryType']
1.46 abukhman 697: viewMode= pageinfo['viewMode']
698: tocMode = pageinfo['tocMode']
699: tocPN = pageinfo['tocPN']
1.48 ! abukhman 700:
! 701: page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn) ,outputUnicode=False)
! 702: pagexm = page.replace('?document=/echo/la/Benedetti_1585.xml','?url=/mpiwg/online/permanent/library/163127KK')
! 703: pagexml=pagexm.replace('mode=text','mode=texttool')
1.45 abukhman 704: pagedom = Parse(pagexml)
1.47 abukhman 705:
1.48 ! abukhman 706: if (queryType=="fulltext")or(queryType=="fulltextMorph")or(queryType=="xpath")or(queryType=="xquery"):
! 707: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
! 708: selfurl = self.absolute_url()
! 709: page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s&query=%s&queryType=%s'%(selfurl, viewMode, tocMode, tocPN, query, queryType))
! 710: text =page.replace('mode=text','mode=texttool')
! 711: return text
! 712:
! 713: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
! 714: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
! 715: if len(pagedivs)>0:
! 716: pagenode=pagedivs[0]
! 717: links=pagenode.xpath("//a")
! 718: for l in links:
! 719: hrefNode = l.getAttributeNodeNS(None, u"href")
! 720: if hrefNode:
! 721: href = hrefNode.nodeValue
! 722: if href.startswith('../lt/lex.xql'):
! 723: selfurl = self.absolute_url()
! 724: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
! 725:
! 726:
! 727:
! 728: l.setAttributeNS(None, 'target', '_blank')
! 729: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=200, scrollbars=1'); return false;")
! 730: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
! 731: if href.startswith('../lt/lemma.xql'):
! 732: selfurl = self.absolute_url()
! 733: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
! 734: l.setAttributeNS(None, 'target', '_blank')
! 735: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=200, scrollbars=1'); return false;")
! 736: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
! 737: return serializeNode(pagenode)
1.47 abukhman 738:
1.48 ! abukhman 739: return "no text here"
1.47 abukhman 740:
1.43 casties 741: def getNumPages(self,docinfo=None):
742: """get list of pages from fulltext and put in docinfo"""
743: xquery = '//pb'
744: text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
745: # TODO: better processing of the page list. do we need the info somewhere else also?
746: docinfo['numPages'] = text.count("<pb ")
747: return docinfo
748:
1.46 abukhman 749: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None,):
1.43 casties 750: """returns single page from fulltext"""
1.44 casties 751: docpath = docinfo['textURLPath']
752: if mode == "text_dict":
753: textmode = "textPollux"
754: else:
755: textmode = mode
756:
1.46 abukhman 757: #selfurl = self.absolute_url()
758: #viewMode= pageinfo['viewMode']
759: #tocMode = pageinfo['tocMode']
760: #tocPN = pageinfo['tocPN']
761:
1.44 casties 762: pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False)
1.43 casties 763: # post-processing downloaded xml
764: pagedom = Parse(pagexml)
765: # plain text mode
766: if mode == "text":
767: # first div contains text
768: pagedivs = pagedom.xpath("/div")
1.45 abukhman 769: #queryResultPage
1.43 casties 770: if len(pagedivs) > 0:
771: pagenode = pagedivs[0]
772: return serializeNode(pagenode)
1.48 ! abukhman 773: if mode == "xml":
! 774: # first div contains text
! 775: pagedivs = pagedom.xpath("/div")
! 776: if len(pagedivs) > 0:
! 777: pagenode = pagedivs[0]
! 778: return serializeNode(pagenode)
1.43 casties 779: # text-with-links mode
1.44 casties 780: if mode == "text_dict":
1.43 casties 781: # first div contains text
782: pagedivs = pagedom.xpath("/div")
783: if len(pagedivs) > 0:
784: pagenode = pagedivs[0]
785: # check all a-tags
786: links = pagenode.xpath("//a")
787: for l in links:
788: hrefNode = l.getAttributeNodeNS(None, u"href")
789: if hrefNode:
790: # is link with href
791: href = hrefNode.nodeValue
792: if href.startswith('lt/lex.xql'):
793: # is pollux link
794: selfurl = self.absolute_url()
795: # change href
1.46 abukhman 796: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
1.43 casties 797: # add target
798: l.setAttributeNS(None, 'target', '_blank')
1.48 ! abukhman 799: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
! 800: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.46 abukhman 801:
802: if href.startswith('lt/lemma.xql'):
803: selfurl = self.absolute_url()
804: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
805: l.setAttributeNS(None, 'target', '_blank')
1.48 ! abukhman 806: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
! 807: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.43 casties 808: return serializeNode(pagenode)
1.1 dwinter 809:
1.43 casties 810: return "no text here"
1.3 casties 811:
1.46 abukhman 812: def getTranslate(self, query=None, language=None):
813: """translate into another languages"""
814: pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","query=%s&language=%s"%(query,language),outputUnicode=False)
815: return pagexml
816:
1.47 abukhman 817: def getLemma(self, lemma=None, language=None):
1.48 ! abukhman 818: """simular words lemma """
1.47 abukhman 819: pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False)
1.46 abukhman 820: return pagexml
821:
1.47 abukhman 822: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
823: """number of"""
824: docpath = docinfo['textURLPath']
825: pagesize = pageinfo['queryPageSize']
826: pn = pageinfo['searchPN']
827: query =pageinfo['query']
828: queryType =pageinfo['queryType']
829:
830: tocSearch = 0
831: tocDiv = None
832: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False)
833:
834: pagedom = Parse(pagexml)
835: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
836: tocSearch = int(getTextFromNode(numdivs[0]))
837: tc=int((tocSearch/20)+1)
838: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
839: return tc
840:
1.44 casties 841: def getToc(self, mode="text", docinfo=None):
842: """loads table of contents and stores in docinfo"""
843: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
844: if 'tocSize_%s'%mode in docinfo:
845: # cached toc
1.47 abukhman 846: return docinfo
1.44 casties 847: docpath = docinfo['textURLPath']
848: # we need to set a result set size
849: pagesize = 1000
850: pn = 1
851: if mode == "text":
852: queryType = "toc"
853: else:
854: queryType = mode
855: # number of entries in toc
856: tocSize = 0
857: tocDiv = None
858: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
859: # post-processing downloaded xml
860: pagedom = Parse(pagexml)
861: # get number of entries
862: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
863: if len(numdivs) > 0:
864: tocSize = int(getTextFromNode(numdivs[0]))
865: # div contains text
866: #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
867: #if len(pagedivs) > 0:
868: # tocDiv = pagedivs[0]
869:
870: docinfo['tocSize_%s'%mode] = tocSize
871: #docinfo['tocDiv_%s'%mode] = tocDiv
872: return docinfo
873:
1.45 abukhman 874: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
1.44 casties 875: """returns single page from the table of contents"""
876: # TODO: this should use the cached TOC
877: if mode == "text":
878: queryType = "toc"
879: else:
880: queryType = mode
881: docpath = docinfo['textURLPath']
882: pagesize = pageinfo['tocPageSize']
883: pn = pageinfo['tocPN']
1.46 abukhman 884:
885: selfurl = self.absolute_url()
886: viewMode= pageinfo['viewMode']
887: tocMode = pageinfo['tocMode']
888: tocPN = pageinfo['tocPN']
889:
1.45 abukhman 890: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False)
1.46 abukhman 891: page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl, viewMode, tocMode, tocPN))
892: text = page.replace('mode=image','mode=texttool')
893: return text
1.44 casties 894: # post-processing downloaded xml
1.46 abukhman 895: #pagedom = Parse(text)
1.44 casties 896: # div contains text
1.46 abukhman 897: #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
898: #if len(pagedivs) > 0:
899: # pagenode = pagedivs[0]
900: # return serializeNode(pagenode)
901: #else:
902: # return "No TOC!"
1.44 casties 903:
1.3 casties 904:
1.45 abukhman 905: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 906: """init document viewer"""
907: self.title=title
908: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 909: self.thumbrows = thumbrows
910: self.thumbcols = thumbcols
1.8 casties 911: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 912: if RESPONSE is not None:
913: RESPONSE.redirect('manage_main')
1.1 dwinter 914:
915:
916:
917: def manage_AddDocumentViewerForm(self):
918: """add the viewer form"""
1.3 casties 919: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 920: return pt()
921:
1.43 casties 922: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 923: """add the viewer"""
1.43 casties 924: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 925: self._setObject(id,newObj)
926:
927: if RESPONSE is not None:
928: RESPONSE.redirect('manage_main')
1.3 casties 929:
930:
931: ##
932: ## DocumentViewerTemplate class
933: ##
934: class DocumentViewerTemplate(ZopePageTemplate):
935: """Template for document viewer"""
936: meta_type="DocumentViewer Template"
937:
938:
939: def manage_addDocumentViewerTemplateForm(self):
940: """Form for adding"""
941: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
942: return pt()
943:
944: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
945: REQUEST=None, submit=None):
946: "Add a Page Template with optional file content."
947:
948: self._setObject(id, DocumentViewerTemplate(id))
949: ob = getattr(self, id)
1.23 dwinter 950: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
951: logging.info("txt %s:"%txt)
952: ob.pt_edit(txt,"text/html")
1.3 casties 953: if title:
954: ob.pt_setTitle(title)
955: try:
956: u = self.DestinationURL()
957: except AttributeError:
958: u = REQUEST['URL1']
959:
960: u = "%s/%s" % (u, urllib.quote(id))
961: REQUEST.RESPONSE.redirect(u+'/manage_main')
962: return ''
963:
964:
1.14 casties 965:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>