Annotation of documentViewer/documentViewer.py, revision 1.35
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:
1.32 dwinter 86: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 87: security.declareProtected('View management screens','changeDocumentViewerForm')
88: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
89:
1.1 dwinter 90:
1.18 dwinter 91: def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
1.1 dwinter 92: """init document viewer"""
93: self.id=id
94: self.title=title
95: self.imageViewerUrl=imageViewerUrl
1.18 dwinter 96: self.textViewerUrl=textViewerUrl
97:
1.4 casties 98: if not digilibBaseUrl:
1.3 casties 99: self.digilibBaseUrl = self.findDigilibUrl()
1.4 casties 100: else:
101: self.digilibBaseUrl = digilibBaseUrl
102: self.thumbcols = thumbcols
103: self.thumbrows = thumbrows
1.8 casties 104: # authgroups is list of authorized groups (delimited by ,)
105: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 106: # add template folder so we can always use template.something
107: self.manage_addFolder('template')
108:
109:
1.32 dwinter 110: security.declareProtected('View','thumbs_rss')
111: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
112: '''
113: view it
114: @param mode: defines how to access the document behind url
115: @param url: url which contains display information
116: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
117:
118: '''
119: logging.info("HHHHHHHHHHHHHH:load the rss")
120: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
121:
122: if not hasattr(self, 'template'):
123: # create template folder if it doesn't exist
124: self.manage_addFolder('template')
125:
126: if not self.digilibBaseUrl:
127: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
128:
129: docinfo = self.getDocinfo(mode=mode,url=url)
130: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
131: pt = getattr(self.template, 'thumbs_main_rss')
132:
133: if viewMode=="auto": # automodus gewaehlt
134: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
135: viewMode="text"
136: else:
137: viewMode="images"
138:
139: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
140:
1.3 casties 141: security.declareProtected('View','index_html')
1.21 dwinter 142: def index_html(self,mode,url,viewMode="auto",start=None,pn=1):
1.3 casties 143: '''
144: view it
1.26 casties 145: @param mode: defines how to access the document behind url
1.3 casties 146: @param url: url which contains display information
1.26 casties 147: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
1.18 dwinter 148:
1.3 casties 149: '''
150:
1.22 dwinter 151: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 152:
1.3 casties 153: if not hasattr(self, 'template'):
154: # create template folder if it doesn't exist
155: self.manage_addFolder('template')
156:
157: if not self.digilibBaseUrl:
158: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
159:
1.4 casties 160: docinfo = self.getDocinfo(mode=mode,url=url)
161: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.3 casties 162: pt = getattr(self.template, 'viewer_main')
1.21 dwinter 163:
164: if viewMode=="auto": # automodus gewaehlt
165: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
166: viewMode="text"
167: else:
168: viewMode="images"
1.22 dwinter 169:
1.18 dwinter 170: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
1.1 dwinter 171:
172:
1.4 casties 173: def getLink(self,param=None,val=None):
174: """link to documentviewer with parameter param set to val"""
1.9 casties 175: params=self.REQUEST.form.copy()
1.4 casties 176: if param is not None:
1.7 casties 177: if val is None:
178: if params.has_key(param):
179: del params[param]
1.4 casties 180: else:
1.9 casties 181: params[param] = str(val)
1.7 casties 182:
1.9 casties 183: # quote values and assemble into query string
184: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
185: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 186: return url
187:
1.32 dwinter 188: def getLinkAmp(self,param=None,val=None):
189: """link to documentviewer with parameter param set to val"""
190: params=self.REQUEST.form.copy()
191: if param is not None:
192: if val is None:
193: if params.has_key(param):
194: del params[param]
195: else:
196: params[param] = str(val)
197:
198: # quote values and assemble into query string
199: logging.info("XYXXXXX: %s"%repr(params.items()))
200: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
201: url=self.REQUEST['URL1']+"?"+ps
202: return url
1.26 casties 203: def getInfo_xml(self,url,mode):
204: """returns info about the document as XML"""
205:
206: if not self.digilibBaseUrl:
207: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
208:
209: docinfo = self.getDocinfo(mode=mode,url=url)
210: pt = getattr(self.template, 'info_xml')
211: return pt(docinfo=docinfo)
212:
1.4 casties 213:
1.3 casties 214: def getStyle(self, idx, selected, style=""):
1.4 casties 215: """returns a string with the given style and append 'sel' if path == selected."""
1.22 dwinter 216: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
1.3 casties 217: if idx == selected:
218: return style + 'sel'
219: else:
1.9 casties 220: return style
1.26 casties 221:
1.2 dwinter 222:
1.9 casties 223: def isAccessible(self, docinfo):
1.8 casties 224: """returns if access to the resource is granted"""
225: access = docinfo.get('accessType', None)
1.22 dwinter 226: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
1.17 casties 227: if access is not None and access == 'free':
1.22 dwinter 228: logger("documentViewer (accessOK)", logging.INFO, "access is free")
1.8 casties 229: return True
1.17 casties 230: elif access is None or access in self.authgroups:
1.9 casties 231: # only local access -- only logged in users
232: user = getSecurityManager().getUser()
233: if user is not None:
234: #print "user: ", user
235: return (user.getUserName() != "Anonymous User")
236: else:
237: return False
1.8 casties 238:
1.22 dwinter 239: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
1.8 casties 240: return False
1.9 casties 241:
1.8 casties 242:
1.35 ! dwinter 243: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 244: """gibt param von dlInfo aus"""
1.13 casties 245: num_retries = 3
1.7 casties 246: if docinfo is None:
247: docinfo = {}
1.35 ! dwinter 248:
! 249: for x in range(cut):
! 250: path=getParentDir(path)
1.13 casties 251: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 252:
1.22 dwinter 253: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
1.6 casties 254:
1.13 casties 255: for cnt in range(num_retries):
1.9 casties 256: try:
1.13 casties 257: # dom = NonvalidatingReader.parseUri(imageUrl)
258: txt=urllib.urlopen(infoUrl).read()
259: dom = Parse(txt)
1.9 casties 260: break
261: except:
1.22 dwinter 262: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9 casties 263: else:
1.13 casties 264: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6 casties 265:
1.10 casties 266: sizes=dom.xpath("//dir/size")
1.22 dwinter 267: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
1.6 casties 268:
1.10 casties 269: if sizes:
270: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 271: else:
272: docinfo['numPages'] = 0
273:
274: return docinfo
1.8 casties 275:
1.6 casties 276:
1.9 casties 277: def getIndexMeta(self, url):
278: """returns dom of index.meta document at url"""
1.12 casties 279: num_retries = 3
1.9 casties 280: dom = None
1.12 casties 281: metaUrl = None
1.9 casties 282: if url.startswith("http://"):
283: # real URL
1.12 casties 284: metaUrl = url
1.9 casties 285: else:
286: # online path
287: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 288: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 289: if not metaUrl.endswith("index.meta"):
290: metaUrl += "/index.meta"
1.18 dwinter 291: print metaUrl
1.13 casties 292: for cnt in range(num_retries):
1.9 casties 293: try:
1.12 casties 294: # patch dirk encoding fehler treten dann nicht mehr auf
1.11 casties 295: # dom = NonvalidatingReader.parseUri(metaUrl)
1.12 casties 296: txt=urllib.urlopen(metaUrl).read()
297: dom = Parse(txt)
1.13 casties 298: break
1.9 casties 299: except:
1.22 dwinter 300: logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.12 casties 301:
302: if dom is None:
303: raise IOError("Unable to read index meta from %s"%(url))
1.9 casties 304:
305: return dom
1.20 dwinter 306:
307: def getPresentationInfoXML(self, url):
308: """returns dom of info.xml document at url"""
309: num_retries = 3
310: dom = None
311: metaUrl = None
312: if url.startswith("http://"):
313: # real URL
314: metaUrl = url
315: else:
316: # online path
317: server=self.digilibBaseUrl+"/servlet/Texter?fn="
318: metaUrl=server+url.replace("/mpiwg/online","")
319:
320:
321: for cnt in range(num_retries):
322: try:
323: # patch dirk encoding fehler treten dann nicht mehr auf
324: # dom = NonvalidatingReader.parseUri(metaUrl)
325: txt=urllib.urlopen(metaUrl).read()
326: dom = Parse(txt)
327: break
328: except:
1.22 dwinter 329: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.20 dwinter 330:
331: if dom is None:
332: raise IOError("Unable to read infoXMLfrom %s"%(url))
333:
334: return dom
1.9 casties 335:
336:
1.33 dwinter 337: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 338: """gets authorization info from the index.meta file at path or given by dom"""
1.22 dwinter 339: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
1.8 casties 340:
341: access = None
342:
343: if docinfo is None:
344: docinfo = {}
345:
346: if dom is None:
1.33 dwinter 347: for x in range(cut+1):
348: path=getParentDir(path)
349: dom = self.getIndexMeta(path)
1.18 dwinter 350:
1.8 casties 351: acctype = dom.xpath("//access-conditions/access/@type")
352: if acctype and (len(acctype)>0):
353: access=acctype[0].value
1.9 casties 354: if access in ['group', 'institution']:
1.8 casties 355: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
356:
357: docinfo['accessType'] = access
358: return docinfo
1.6 casties 359:
1.8 casties 360:
1.33 dwinter 361: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 362: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 363: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 364:
1.3 casties 365: if docinfo is None:
366: docinfo = {}
367:
368: if dom is None:
1.33 dwinter 369: for x in range(cut+1):
370: path=getParentDir(path)
371: dom = self.getIndexMeta(path)
1.9 casties 372:
1.27 casties 373: # put in all raw bib fields as dict "bib"
374: bib = dom.xpath("//bib/*")
375: if bib and len(bib)>0:
376: bibinfo = {}
377: for e in bib:
378: bibinfo[e.localName] = getTextFromNode(e)
379: docinfo['bib'] = bibinfo
380:
381: # extract some fields (author, title, year) according to their mapping
1.4 casties 382: metaData=self.metadata.main.meta.bib
383: bibtype=dom.xpath("//bib/@type")
384: if bibtype and (len(bibtype)>0):
385: bibtype=bibtype[0].value
1.2 dwinter 386: else:
1.4 casties 387: bibtype="generic"
1.27 casties 388:
1.4 casties 389: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 390: docinfo['bib_type'] = bibtype
1.4 casties 391: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 392: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 393: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 394: try:
395: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
396: except: pass
397: try:
398: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
399: except: pass
400: try:
401: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
402: except: pass
1.27 casties 403: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 404: try:
405: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
406: except:
407: docinfo['lang']=''
1.27 casties 408:
1.3 casties 409: return docinfo
410:
411:
1.8 casties 412: def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
1.3 casties 413: """parse texttool tag in index meta"""
1.22 dwinter 414: logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url))
1.3 casties 415: if docinfo is None:
416: docinfo = {}
417:
1.22 dwinter 418: if docinfo.get('lang',None) is None:
419: docinfo['lang']='' # default keine Sprache gesetzt
1.8 casties 420: if dom is None:
1.9 casties 421: dom = self.getIndexMeta(url)
1.8 casties 422:
1.16 casties 423: archivePath = None
424: archiveName = None
425:
1.8 casties 426: archiveNames=dom.xpath("//resource/name")
427: if archiveNames and (len(archiveNames)>0):
428: archiveName=getTextFromNode(archiveNames[0])
1.16 casties 429: else:
1.22 dwinter 430: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url))
1.3 casties 431:
432: archivePaths=dom.xpath("//resource/archive-path")
433: if archivePaths and (len(archivePaths)>0):
434: archivePath=getTextFromNode(archivePaths[0])
1.8 casties 435: # clean up archive path
436: if archivePath[0] != '/':
437: archivePath = '/' + archivePath
1.16 casties 438: if archiveName and (not archivePath.endswith(archiveName)):
1.8 casties 439: archivePath += "/" + archiveName
1.3 casties 440: else:
1.16 casties 441: # try to get archive-path from url
1.22 dwinter 442: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url))
1.16 casties 443: if (not url.startswith('http')):
444: archivePath = url.replace('index.meta', '')
445:
446: if archivePath is None:
447: # we balk without archive-path
448: raise IOError("Missing archive-path (for text-tool) in %s"%(url))
1.3 casties 449:
1.9 casties 450: imageDirs=dom.xpath("//texttool/image")
451: if imageDirs and (len(imageDirs)>0):
452: imageDir=getTextFromNode(imageDirs[0])
1.3 casties 453: else:
1.22 dwinter 454: # we balk with no image tag / not necessary anymore because textmode is now standard
455: #raise IOError("No text-tool info in %s"%(url))
456: imageDir=""
457: docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
458:
459: docinfo['imagePath'] = "" # keine Bilder
460: docinfo['imageURL'] = ""
461:
1.9 casties 462: if imageDir and archivePath:
463: #print "image: ", imageDir, " archivepath: ", archivePath
464: imageDir=os.path.join(archivePath,imageDir)
465: imageDir=imageDir.replace("/mpiwg/online",'')
466: docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)
467: docinfo['imagePath'] = imageDir
468: docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir
1.3 casties 469:
470: viewerUrls=dom.xpath("//texttool/digiliburlprefix")
471: if viewerUrls and (len(viewerUrls)>0):
472: viewerUrl=getTextFromNode(viewerUrls[0])
1.7 casties 473: docinfo['viewerURL'] = viewerUrl
1.3 casties 474:
475: textUrls=dom.xpath("//texttool/text")
476: if textUrls and (len(textUrls)>0):
477: textUrl=getTextFromNode(textUrls[0])
1.19 dwinter 478: if urlparse.urlparse(textUrl)[0]=="": #keine url
479: textUrl=os.path.join(archivePath,textUrl)
1.31 casties 480: # fix URLs starting with /mpiwg/online
481: if textUrl.startswith("/mpiwg/online"):
482: textUrl = textUrl.replace("/mpiwg/online",'',1)
483:
1.7 casties 484: docinfo['textURL'] = textUrl
1.20 dwinter 485:
486: presentationUrls=dom.xpath("//texttool/presentation")
1.22 dwinter 487: docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag
488:
489: if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen
1.30 casties 490: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
1.20 dwinter 491: # durch den relativen Pfad auf die presentation infos
492: presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0]))
493: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom)
1.22 dwinter 494:
1.25 casties 495: docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info
1.3 casties 496: return docinfo
497:
1.20 dwinter 498:
499: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
500: """gets the bibliographical information from the preseantion entry in texttools
501: """
502: dom=self.getPresentationInfoXML(url)
1.29 casties 503: try:
504: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
505: except:
506: pass
507: try:
508: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
509: except:
510: pass
511: try:
512: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
513: except:
514: pass
1.20 dwinter 515: return docinfo
516:
1.33 dwinter 517: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 518: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.22 dwinter 519: logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
1.3 casties 520: if docinfo is None:
521: docinfo = {}
1.6 casties 522: path=path.replace("/mpiwg/online","")
1.3 casties 523: docinfo['imagePath'] = path
1.35 ! dwinter 524: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.7 casties 525: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 526: docinfo['imageURL'] = imageUrl
527:
1.33 dwinter 528: docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo,cut=cut)
529: docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo,cut=cut)
1.3 casties 530: return docinfo
531:
1.2 dwinter 532:
1.3 casties 533: def getDocinfo(self, mode, url):
534: """returns docinfo depending on mode"""
1.22 dwinter 535: logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
1.3 casties 536: # look for cached docinfo in session
1.21 dwinter 537: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 538: docinfo = self.REQUEST.SESSION['docinfo']
539: # check if its still current
540: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.22 dwinter 541: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
1.3 casties 542: return docinfo
543: # new docinfo
544: docinfo = {'mode': mode, 'url': url}
545: if mode=="texttool": #index.meta with texttool information
546: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
547: elif mode=="imagepath":
548: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 549: elif mode=="filepath":
1.34 dwinter 550: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=2)
1.3 casties 551: else:
1.22 dwinter 552: logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
1.10 casties 553: raise ValueError("Unknown mode %s"%(mode))
554:
1.22 dwinter 555: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
1.3 casties 556: self.REQUEST.SESSION['docinfo'] = docinfo
557: return docinfo
1.2 dwinter 558:
559:
1.4 casties 560: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):
1.3 casties 561: """returns pageinfo with the given parameters"""
562: pageinfo = {}
1.4 casties 563: current = getInt(current)
564: pageinfo['current'] = current
565: rows = int(rows or self.thumbrows)
566: pageinfo['rows'] = rows
567: cols = int(cols or self.thumbcols)
568: pageinfo['cols'] = cols
569: grpsize = cols * rows
570: pageinfo['groupsize'] = grpsize
1.28 casties 571: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
572: # int(current / grpsize) * grpsize +1))
1.3 casties 573: pageinfo['start'] = start
1.4 casties 574: pageinfo['end'] = start + grpsize
575: if docinfo is not None:
576: np = int(docinfo['numPages'])
577: pageinfo['end'] = min(pageinfo['end'], np)
578: pageinfo['numgroups'] = int(np / grpsize)
579: if np % grpsize > 0:
580: pageinfo['numgroups'] += 1
581:
1.3 casties 582: return pageinfo
583:
1.1 dwinter 584: def text(self,mode,url,pn):
585: """give text"""
586: if mode=="texttool": #index.meta with texttool information
587: (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
588:
1.9 casties 589: #print textpath
1.1 dwinter 590: try:
591: dom = NonvalidatingReader.parseUri(textpath)
592: except:
593: return None
594:
595: list=[]
596: nodes=dom.xpath("//pb")
597:
598: node=nodes[int(pn)-1]
599:
600: p=node
601:
602: while p.tagName!="p":
603: p=p.parentNode
604:
605:
606: endNode=nodes[int(pn)]
607:
608:
609: e=endNode
610:
611: while e.tagName!="p":
612: e=e.parentNode
613:
614:
615: next=node.parentNode
616:
617: #sammle s
618: while next and (next!=endNode.parentNode):
619: list.append(next)
620: next=next.nextSibling
621: list.append(endNode.parentNode)
622:
623: if p==e:# beide im selben paragraphen
1.2 dwinter 624: pass
625: # else:
626: # next=p
627: # while next!=e:
628: # print next,e
629: # list.append(next)
630: # next=next.nextSibling
631: #
632: # for x in list:
633: # PrettyPrint(x)
634: #
635: # return list
1.3 casties 636: #
637:
638: def findDigilibUrl(self):
639: """try to get the digilib URL from zogilib"""
640: url = self.imageViewerUrl[:-1] + "/getScalerUrl"
1.20 dwinter 641: #print urlparse.urlparse(url)[0]
642: #print urlparse.urljoin(self.absolute_url(),url)
643: logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0])
644: logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url))
645:
1.3 casties 646: try:
1.18 dwinter 647: if urlparse.urlparse(url)[0]=='': #relative path
648: url=urlparse.urljoin(self.absolute_url()+"/",url)
649:
1.3 casties 650: scaler = urlopen(url).read()
651: return scaler.replace("/servlet/Scaler?", "")
652: except:
653: return None
654:
1.18 dwinter 655: def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
1.3 casties 656: """init document viewer"""
657: self.title=title
658: self.imageViewerUrl=imageViewerUrl
1.18 dwinter 659: self.textViewerUrl=textViewerUrl
1.3 casties 660: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 661: self.thumbrows = thumbrows
662: self.thumbcols = thumbcols
1.8 casties 663: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 664: if RESPONSE is not None:
665: RESPONSE.redirect('manage_main')
1.1 dwinter 666:
667:
668:
669:
670: # security.declareProtected('View management screens','renameImageForm')
671:
672: def manage_AddDocumentViewerForm(self):
673: """add the viewer form"""
1.3 casties 674: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 675: return pt()
676:
1.18 dwinter 677: def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None):
1.1 dwinter 678: """add the viewer"""
1.18 dwinter 679: newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl)
1.1 dwinter 680: self._setObject(id,newObj)
681:
682: if RESPONSE is not None:
683: RESPONSE.redirect('manage_main')
1.3 casties 684:
685:
686: ##
687: ## DocumentViewerTemplate class
688: ##
689: class DocumentViewerTemplate(ZopePageTemplate):
690: """Template for document viewer"""
691: meta_type="DocumentViewer Template"
692:
693:
694: def manage_addDocumentViewerTemplateForm(self):
695: """Form for adding"""
696: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
697: return pt()
698:
699: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
700: REQUEST=None, submit=None):
701: "Add a Page Template with optional file content."
702:
703: self._setObject(id, DocumentViewerTemplate(id))
704: ob = getattr(self, id)
1.23 dwinter 705: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
706: logging.info("txt %s:"%txt)
707: ob.pt_edit(txt,"text/html")
1.3 casties 708: if title:
709: ob.pt_setTitle(title)
710: try:
711: u = self.DestinationURL()
712: except AttributeError:
713: u = REQUEST['URL1']
714:
715: u = "%s/%s" % (u, urllib.quote(id))
716: REQUEST.RESPONSE.redirect(u+'/manage_main')
717: return ''
718:
719:
1.14 casties 720:
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