Annotation of documentViewer/documentViewer.py, revision 1.29
1.18 dwinter 1:
2:
1.1 dwinter 3: from OFS.Folder import Folder
4: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
1.22 dwinter 5: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
1.1 dwinter 6: from AccessControl import ClassSecurityInfo
1.8 casties 7: from AccessControl import getSecurityManager
1.1 dwinter 8: from Globals import package_home
9:
10: from Ft.Xml.Domlette import NonvalidatingReader
11: from Ft.Xml.Domlette import PrettyPrint, Print
1.11 casties 12: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.1 dwinter 13:
14: import Ft.Xml.XPath
15:
16: import os.path
1.7 casties 17: import sys
1.1 dwinter 18: import cgi
19: import urllib
1.20 dwinter 20: import logging
1.28 casties 21: import math
1.22 dwinter 22:
1.18 dwinter 23: import urlparse
1.1 dwinter 24:
1.22 dwinter 25: def logger(txt,method,txt2):
26: """logging"""
27: logging.info(txt+ txt2)
28:
29:
1.4 casties 30: def getInt(number, default=0):
31: """returns always an int (0 in case of problems)"""
32: try:
33: return int(number)
34: except:
1.29 ! casties 35: return int(default)
1.4 casties 36:
1.1 dwinter 37: def getTextFromNode(nodename):
1.18 dwinter 38: """get the cdata content of a node"""
1.8 casties 39: if nodename is None:
40: return ""
1.1 dwinter 41: nodelist=nodename.childNodes
42: rc = ""
43: for node in nodelist:
44: if node.nodeType == node.TEXT_NODE:
45: rc = rc + node.data
46: return rc
47:
1.9 casties 48:
49: def getParentDir(path):
50: """returns pathname shortened by one"""
51: return '/'.join(path.split('/')[0:-1])
52:
53:
1.1 dwinter 54: import socket
55:
1.8 casties 56: def urlopen(url,timeout=2):
1.1 dwinter 57: """urlopen mit timeout"""
1.8 casties 58: socket.setdefaulttimeout(timeout)
1.1 dwinter 59: ret=urllib.urlopen(url)
60: socket.setdefaulttimeout(5)
61: return ret
62:
63:
1.3 casties 64: ##
65: ## documentViewer class
66: ##
67: class documentViewer(Folder):
1.1 dwinter 68: """document viewer"""
1.20 dwinter 69: #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
1.18 dwinter 70:
1.1 dwinter 71: meta_type="Document viewer"
72:
73: security=ClassSecurityInfo()
1.3 casties 74: manage_options=Folder.manage_options+(
1.1 dwinter 75: {'label':'main config','action':'changeDocumentViewerForm'},
76: )
77:
1.3 casties 78: # templates and forms
79: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
80: thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())
81: image_main = PageTemplateFile('zpt/image_main', globals())
82: head_main = PageTemplateFile('zpt/head_main', globals())
83: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 84: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.3 casties 85:
86: security.declareProtected('View management screens','changeDocumentViewerForm')
87: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
88:
1.1 dwinter 89:
1.18 dwinter 90: def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
1.1 dwinter 91: """init document viewer"""
92: self.id=id
93: self.title=title
94: self.imageViewerUrl=imageViewerUrl
1.18 dwinter 95: self.textViewerUrl=textViewerUrl
96:
1.4 casties 97: if not digilibBaseUrl:
1.3 casties 98: self.digilibBaseUrl = self.findDigilibUrl()
1.4 casties 99: else:
100: self.digilibBaseUrl = digilibBaseUrl
101: self.thumbcols = thumbcols
102: self.thumbrows = thumbrows
1.8 casties 103: # authgroups is list of authorized groups (delimited by ,)
104: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 105: # add template folder so we can always use template.something
106: self.manage_addFolder('template')
107:
108:
109: security.declareProtected('View','index_html')
1.21 dwinter 110: def index_html(self,mode,url,viewMode="auto",start=None,pn=1):
1.3 casties 111: '''
112: view it
1.26 casties 113: @param mode: defines how to access the document behind url
1.3 casties 114: @param url: url which contains display information
1.26 casties 115: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
1.18 dwinter 116:
1.3 casties 117: '''
118:
1.22 dwinter 119: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 120:
1.3 casties 121: if not hasattr(self, 'template'):
122: # create template folder if it doesn't exist
123: self.manage_addFolder('template')
124:
125: if not self.digilibBaseUrl:
126: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
127:
1.4 casties 128: docinfo = self.getDocinfo(mode=mode,url=url)
129: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.3 casties 130: pt = getattr(self.template, 'viewer_main')
1.21 dwinter 131:
132: if viewMode=="auto": # automodus gewaehlt
133: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
134: viewMode="text"
135: else:
136: viewMode="images"
1.22 dwinter 137:
1.18 dwinter 138: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
1.1 dwinter 139:
140:
1.4 casties 141: def getLink(self,param=None,val=None):
142: """link to documentviewer with parameter param set to val"""
1.9 casties 143: params=self.REQUEST.form.copy()
1.4 casties 144: if param is not None:
1.7 casties 145: if val is None:
146: if params.has_key(param):
147: del params[param]
1.4 casties 148: else:
1.9 casties 149: params[param] = str(val)
1.7 casties 150:
1.9 casties 151: # quote values and assemble into query string
152: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
153: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 154: return url
155:
1.26 casties 156:
157: def getInfo_xml(self,url,mode):
158: """returns info about the document as XML"""
159:
160: if not self.digilibBaseUrl:
161: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
162:
163: docinfo = self.getDocinfo(mode=mode,url=url)
164: pt = getattr(self.template, 'info_xml')
165: return pt(docinfo=docinfo)
166:
1.4 casties 167:
1.3 casties 168: def getStyle(self, idx, selected, style=""):
1.4 casties 169: """returns a string with the given style and append 'sel' if path == selected."""
1.22 dwinter 170: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
1.3 casties 171: if idx == selected:
172: return style + 'sel'
173: else:
1.9 casties 174: return style
1.26 casties 175:
1.2 dwinter 176:
1.9 casties 177: def isAccessible(self, docinfo):
1.8 casties 178: """returns if access to the resource is granted"""
179: access = docinfo.get('accessType', None)
1.22 dwinter 180: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
1.17 casties 181: if access is not None and access == 'free':
1.22 dwinter 182: logger("documentViewer (accessOK)", logging.INFO, "access is free")
1.8 casties 183: return True
1.17 casties 184: elif access is None or access in self.authgroups:
1.9 casties 185: # only local access -- only logged in users
186: user = getSecurityManager().getUser()
187: if user is not None:
188: #print "user: ", user
189: return (user.getUserName() != "Anonymous User")
190: else:
191: return False
1.8 casties 192:
1.22 dwinter 193: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
1.8 casties 194: return False
1.9 casties 195:
1.8 casties 196:
1.7 casties 197: def getDirinfoFromDigilib(self,path,docinfo=None):
1.6 casties 198: """gibt param von dlInfo aus"""
1.13 casties 199: num_retries = 3
1.7 casties 200: if docinfo is None:
201: docinfo = {}
202:
1.13 casties 203: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 204:
1.22 dwinter 205: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
1.6 casties 206:
1.13 casties 207: for cnt in range(num_retries):
1.9 casties 208: try:
1.13 casties 209: # dom = NonvalidatingReader.parseUri(imageUrl)
210: txt=urllib.urlopen(infoUrl).read()
211: dom = Parse(txt)
1.9 casties 212: break
213: except:
1.22 dwinter 214: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9 casties 215: else:
1.13 casties 216: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6 casties 217:
1.10 casties 218: sizes=dom.xpath("//dir/size")
1.22 dwinter 219: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
1.6 casties 220:
1.10 casties 221: if sizes:
222: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 223: else:
224: docinfo['numPages'] = 0
225:
226: return docinfo
1.8 casties 227:
1.6 casties 228:
1.9 casties 229: def getIndexMeta(self, url):
230: """returns dom of index.meta document at url"""
1.12 casties 231: num_retries = 3
1.9 casties 232: dom = None
1.12 casties 233: metaUrl = None
1.9 casties 234: if url.startswith("http://"):
235: # real URL
1.12 casties 236: metaUrl = url
1.9 casties 237: else:
238: # online path
239: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 240: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 241: if not metaUrl.endswith("index.meta"):
242: metaUrl += "/index.meta"
1.18 dwinter 243: print metaUrl
1.13 casties 244: for cnt in range(num_retries):
1.9 casties 245: try:
1.12 casties 246: # patch dirk encoding fehler treten dann nicht mehr auf
1.11 casties 247: # dom = NonvalidatingReader.parseUri(metaUrl)
1.12 casties 248: txt=urllib.urlopen(metaUrl).read()
249: dom = Parse(txt)
1.13 casties 250: break
1.9 casties 251: except:
1.22 dwinter 252: logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.12 casties 253:
254: if dom is None:
255: raise IOError("Unable to read index meta from %s"%(url))
1.9 casties 256:
257: return dom
1.20 dwinter 258:
259: def getPresentationInfoXML(self, url):
260: """returns dom of info.xml document at url"""
261: num_retries = 3
262: dom = None
263: metaUrl = None
264: if url.startswith("http://"):
265: # real URL
266: metaUrl = url
267: else:
268: # online path
269: server=self.digilibBaseUrl+"/servlet/Texter?fn="
270: metaUrl=server+url.replace("/mpiwg/online","")
271:
272:
273: for cnt in range(num_retries):
274: try:
275: # patch dirk encoding fehler treten dann nicht mehr auf
276: # dom = NonvalidatingReader.parseUri(metaUrl)
277: txt=urllib.urlopen(metaUrl).read()
278: dom = Parse(txt)
279: break
280: except:
1.22 dwinter 281: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.20 dwinter 282:
283: if dom is None:
284: raise IOError("Unable to read infoXMLfrom %s"%(url))
285:
286: return dom
1.9 casties 287:
288:
1.8 casties 289: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):
1.9 casties 290: """gets authorization info from the index.meta file at path or given by dom"""
1.22 dwinter 291: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
1.8 casties 292:
293: access = None
294:
295: if docinfo is None:
296: docinfo = {}
297:
298: if dom is None:
1.9 casties 299: dom = self.getIndexMeta(getParentDir(path))
1.18 dwinter 300:
1.8 casties 301: acctype = dom.xpath("//access-conditions/access/@type")
302: if acctype and (len(acctype)>0):
303: access=acctype[0].value
1.9 casties 304: if access in ['group', 'institution']:
1.8 casties 305: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
306:
307: docinfo['accessType'] = access
308: return docinfo
1.6 casties 309:
1.8 casties 310:
1.3 casties 311: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):
1.9 casties 312: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 313: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 314:
1.3 casties 315: if docinfo is None:
316: docinfo = {}
317:
318: if dom is None:
1.9 casties 319: dom = self.getIndexMeta(getParentDir(path))
320:
1.27 casties 321: # put in all raw bib fields as dict "bib"
322: bib = dom.xpath("//bib/*")
323: if bib and len(bib)>0:
324: bibinfo = {}
325: for e in bib:
326: bibinfo[e.localName] = getTextFromNode(e)
327: docinfo['bib'] = bibinfo
328:
329: # extract some fields (author, title, year) according to their mapping
1.4 casties 330: metaData=self.metadata.main.meta.bib
331: bibtype=dom.xpath("//bib/@type")
332: if bibtype and (len(bibtype)>0):
333: bibtype=bibtype[0].value
1.2 dwinter 334: else:
1.4 casties 335: bibtype="generic"
1.27 casties 336:
1.4 casties 337: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 338: docinfo['bib_type'] = bibtype
1.4 casties 339: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 340: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 341: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.4 casties 342: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
343: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
344: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
1.27 casties 345: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 346: try:
347: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
348: except:
349: docinfo['lang']=''
1.27 casties 350:
1.3 casties 351: return docinfo
352:
353:
1.8 casties 354: def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
1.3 casties 355: """parse texttool tag in index meta"""
1.22 dwinter 356: logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url))
1.3 casties 357: if docinfo is None:
358: docinfo = {}
359:
1.22 dwinter 360: if docinfo.get('lang',None) is None:
361: docinfo['lang']='' # default keine Sprache gesetzt
1.8 casties 362: if dom is None:
1.9 casties 363: dom = self.getIndexMeta(url)
1.8 casties 364:
1.16 casties 365: archivePath = None
366: archiveName = None
367:
1.8 casties 368: archiveNames=dom.xpath("//resource/name")
369: if archiveNames and (len(archiveNames)>0):
370: archiveName=getTextFromNode(archiveNames[0])
1.16 casties 371: else:
1.22 dwinter 372: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url))
1.3 casties 373:
374: archivePaths=dom.xpath("//resource/archive-path")
375: if archivePaths and (len(archivePaths)>0):
376: archivePath=getTextFromNode(archivePaths[0])
1.8 casties 377: # clean up archive path
378: if archivePath[0] != '/':
379: archivePath = '/' + archivePath
1.16 casties 380: if archiveName and (not archivePath.endswith(archiveName)):
1.8 casties 381: archivePath += "/" + archiveName
1.3 casties 382: else:
1.16 casties 383: # try to get archive-path from url
1.22 dwinter 384: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url))
1.16 casties 385: if (not url.startswith('http')):
386: archivePath = url.replace('index.meta', '')
387:
388: if archivePath is None:
389: # we balk without archive-path
390: raise IOError("Missing archive-path (for text-tool) in %s"%(url))
1.3 casties 391:
1.9 casties 392: imageDirs=dom.xpath("//texttool/image")
393: if imageDirs and (len(imageDirs)>0):
394: imageDir=getTextFromNode(imageDirs[0])
1.3 casties 395: else:
1.22 dwinter 396: # we balk with no image tag / not necessary anymore because textmode is now standard
397: #raise IOError("No text-tool info in %s"%(url))
398: imageDir=""
399: docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
400:
401: docinfo['imagePath'] = "" # keine Bilder
402: docinfo['imageURL'] = ""
403:
1.9 casties 404: if imageDir and archivePath:
405: #print "image: ", imageDir, " archivepath: ", archivePath
406: imageDir=os.path.join(archivePath,imageDir)
407: imageDir=imageDir.replace("/mpiwg/online",'')
408: docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)
409: docinfo['imagePath'] = imageDir
410: docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir
1.3 casties 411:
412: viewerUrls=dom.xpath("//texttool/digiliburlprefix")
413: if viewerUrls and (len(viewerUrls)>0):
414: viewerUrl=getTextFromNode(viewerUrls[0])
1.7 casties 415: docinfo['viewerURL'] = viewerUrl
1.3 casties 416:
417: textUrls=dom.xpath("//texttool/text")
418: if textUrls and (len(textUrls)>0):
419: textUrl=getTextFromNode(textUrls[0])
1.19 dwinter 420: if urlparse.urlparse(textUrl)[0]=="": #keine url
421: textUrl=os.path.join(archivePath,textUrl)
422:
1.7 casties 423: docinfo['textURL'] = textUrl
1.20 dwinter 424:
425: presentationUrls=dom.xpath("//texttool/presentation")
1.22 dwinter 426: docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag
427:
428: if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen
1.20 dwinter 429: # presentation url ergiebt sich ersetzen von index.meta in der url der fŸr die Metadaten
430: # durch den relativen Pfad auf die presentation infos
431: presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0]))
432: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom)
1.22 dwinter 433:
1.25 casties 434: docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info
1.3 casties 435: return docinfo
436:
1.20 dwinter 437:
438: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
439: """gets the bibliographical information from the preseantion entry in texttools
440: """
441: dom=self.getPresentationInfoXML(url)
1.29 ! casties 442: try:
! 443: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
! 444: except:
! 445: pass
! 446: try:
! 447: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
! 448: except:
! 449: pass
! 450: try:
! 451: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
! 452: except:
! 453: pass
1.20 dwinter 454: return docinfo
455:
1.3 casties 456: def getDocinfoFromImagePath(self,path,docinfo=None):
457: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.22 dwinter 458: logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
1.3 casties 459: if docinfo is None:
460: docinfo = {}
1.6 casties 461: path=path.replace("/mpiwg/online","")
1.3 casties 462: docinfo['imagePath'] = path
1.7 casties 463: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo)
464: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 465: docinfo['imageURL'] = imageUrl
466:
467: docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)
1.8 casties 468: docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo)
1.3 casties 469: return docinfo
470:
1.2 dwinter 471:
1.3 casties 472: def getDocinfo(self, mode, url):
473: """returns docinfo depending on mode"""
1.22 dwinter 474: logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
1.3 casties 475: # look for cached docinfo in session
1.21 dwinter 476: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 477: docinfo = self.REQUEST.SESSION['docinfo']
478: # check if its still current
479: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.22 dwinter 480: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
1.3 casties 481: return docinfo
482: # new docinfo
483: docinfo = {'mode': mode, 'url': url}
484: if mode=="texttool": #index.meta with texttool information
485: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
486: elif mode=="imagepath":
487: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
488: else:
1.22 dwinter 489: logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
1.10 casties 490: raise ValueError("Unknown mode %s"%(mode))
491:
1.22 dwinter 492: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
1.3 casties 493: self.REQUEST.SESSION['docinfo'] = docinfo
494: return docinfo
1.2 dwinter 495:
496:
1.4 casties 497: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):
1.3 casties 498: """returns pageinfo with the given parameters"""
499: pageinfo = {}
1.4 casties 500: current = getInt(current)
501: pageinfo['current'] = current
502: rows = int(rows or self.thumbrows)
503: pageinfo['rows'] = rows
504: cols = int(cols or self.thumbcols)
505: pageinfo['cols'] = cols
506: grpsize = cols * rows
507: pageinfo['groupsize'] = grpsize
1.28 casties 508: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
509: # int(current / grpsize) * grpsize +1))
1.3 casties 510: pageinfo['start'] = start
1.4 casties 511: pageinfo['end'] = start + grpsize
512: if docinfo is not None:
513: np = int(docinfo['numPages'])
514: pageinfo['end'] = min(pageinfo['end'], np)
515: pageinfo['numgroups'] = int(np / grpsize)
516: if np % grpsize > 0:
517: pageinfo['numgroups'] += 1
518:
1.3 casties 519: return pageinfo
520:
1.1 dwinter 521: def text(self,mode,url,pn):
522: """give text"""
523: if mode=="texttool": #index.meta with texttool information
524: (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
525:
1.9 casties 526: #print textpath
1.1 dwinter 527: try:
528: dom = NonvalidatingReader.parseUri(textpath)
529: except:
530: return None
531:
532: list=[]
533: nodes=dom.xpath("//pb")
534:
535: node=nodes[int(pn)-1]
536:
537: p=node
538:
539: while p.tagName!="p":
540: p=p.parentNode
541:
542:
543: endNode=nodes[int(pn)]
544:
545:
546: e=endNode
547:
548: while e.tagName!="p":
549: e=e.parentNode
550:
551:
552: next=node.parentNode
553:
554: #sammle s
555: while next and (next!=endNode.parentNode):
556: list.append(next)
557: next=next.nextSibling
558: list.append(endNode.parentNode)
559:
560: if p==e:# beide im selben paragraphen
1.2 dwinter 561: pass
562: # else:
563: # next=p
564: # while next!=e:
565: # print next,e
566: # list.append(next)
567: # next=next.nextSibling
568: #
569: # for x in list:
570: # PrettyPrint(x)
571: #
572: # return list
1.3 casties 573: #
574:
575: def findDigilibUrl(self):
576: """try to get the digilib URL from zogilib"""
577: url = self.imageViewerUrl[:-1] + "/getScalerUrl"
1.20 dwinter 578: #print urlparse.urlparse(url)[0]
579: #print urlparse.urljoin(self.absolute_url(),url)
580: logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0])
581: logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url))
582:
1.3 casties 583: try:
1.18 dwinter 584: if urlparse.urlparse(url)[0]=='': #relative path
585: url=urlparse.urljoin(self.absolute_url()+"/",url)
586:
1.3 casties 587: scaler = urlopen(url).read()
588: return scaler.replace("/servlet/Scaler?", "")
589: except:
590: return None
591:
1.18 dwinter 592: def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
1.3 casties 593: """init document viewer"""
594: self.title=title
595: self.imageViewerUrl=imageViewerUrl
1.18 dwinter 596: self.textViewerUrl=textViewerUrl
1.3 casties 597: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 598: self.thumbrows = thumbrows
599: self.thumbcols = thumbcols
1.8 casties 600: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 601: if RESPONSE is not None:
602: RESPONSE.redirect('manage_main')
1.1 dwinter 603:
604:
605:
606:
607: # security.declareProtected('View management screens','renameImageForm')
608:
609: def manage_AddDocumentViewerForm(self):
610: """add the viewer form"""
1.3 casties 611: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 612: return pt()
613:
1.18 dwinter 614: def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None):
1.1 dwinter 615: """add the viewer"""
1.18 dwinter 616: newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl)
1.1 dwinter 617: self._setObject(id,newObj)
618:
619: if RESPONSE is not None:
620: RESPONSE.redirect('manage_main')
1.3 casties 621:
622:
623: ##
624: ## DocumentViewerTemplate class
625: ##
626: class DocumentViewerTemplate(ZopePageTemplate):
627: """Template for document viewer"""
628: meta_type="DocumentViewer Template"
629:
630:
631: def manage_addDocumentViewerTemplateForm(self):
632: """Form for adding"""
633: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
634: return pt()
635:
636: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
637: REQUEST=None, submit=None):
638: "Add a Page Template with optional file content."
639:
640: self._setObject(id, DocumentViewerTemplate(id))
641: ob = getattr(self, id)
1.23 dwinter 642: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
643: logging.info("txt %s:"%txt)
644: ob.pt_edit(txt,"text/html")
1.3 casties 645: if title:
646: ob.pt_setTitle(title)
647: try:
648: u = self.DestinationURL()
649: except AttributeError:
650: u = REQUEST['URL1']
651:
652: u = "%s/%s" % (u, urllib.quote(id))
653: REQUEST.RESPONSE.redirect(u+'/manage_main')
654: return ''
655:
656:
1.14 casties 657:
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