Annotation of documentViewer/documentViewer.py, revision 1.38
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
1.37 dwinter 24: from types import *
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')
1.36 dwinter 142: def index_html(self,mode,url,viewMode="auto",start=None,pn=1,mk=None):
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:
1.37 dwinter 170: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 171:
1.36 dwinter 172: def generateMarks(self,mk):
173: ret=""
1.37 dwinter 174: if mk is None:
175: return ""
176:
177: if type(mk) is not ListType:
178: mk=[mk]
1.36 dwinter 179: for m in mk:
1.37 dwinter 180: ret+="mk=%s"%m
1.36 dwinter 181: return ret
182:
1.4 casties 183: def getLink(self,param=None,val=None):
184: """link to documentviewer with parameter param set to val"""
1.9 casties 185: params=self.REQUEST.form.copy()
1.4 casties 186: if param is not None:
1.7 casties 187: if val is None:
188: if params.has_key(param):
189: del params[param]
1.4 casties 190: else:
1.9 casties 191: params[param] = str(val)
1.38 ! dwinter 192: if params["mode"] == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
! 193: params["mode"] = "imagepath"
! 194: params["url"] = getParentDir(params["url"])
1.7 casties 195:
1.9 casties 196: # quote values and assemble into query string
197: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
198: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 199: return url
200:
1.32 dwinter 201: def getLinkAmp(self,param=None,val=None):
202: """link to documentviewer with parameter param set to val"""
203: params=self.REQUEST.form.copy()
204: if param is not None:
205: if val is None:
206: if params.has_key(param):
207: del params[param]
208: else:
209: params[param] = str(val)
210:
211: # quote values and assemble into query string
212: logging.info("XYXXXXX: %s"%repr(params.items()))
213: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
214: url=self.REQUEST['URL1']+"?"+ps
215: return url
1.26 casties 216: def getInfo_xml(self,url,mode):
217: """returns info about the document as XML"""
218:
219: if not self.digilibBaseUrl:
220: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
221:
222: docinfo = self.getDocinfo(mode=mode,url=url)
223: pt = getattr(self.template, 'info_xml')
224: return pt(docinfo=docinfo)
225:
1.4 casties 226:
1.3 casties 227: def getStyle(self, idx, selected, style=""):
1.4 casties 228: """returns a string with the given style and append 'sel' if path == selected."""
1.22 dwinter 229: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
1.3 casties 230: if idx == selected:
231: return style + 'sel'
232: else:
1.9 casties 233: return style
1.26 casties 234:
1.2 dwinter 235:
1.9 casties 236: def isAccessible(self, docinfo):
1.8 casties 237: """returns if access to the resource is granted"""
238: access = docinfo.get('accessType', None)
1.22 dwinter 239: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
1.17 casties 240: if access is not None and access == 'free':
1.22 dwinter 241: logger("documentViewer (accessOK)", logging.INFO, "access is free")
1.8 casties 242: return True
1.17 casties 243: elif access is None or access in self.authgroups:
1.9 casties 244: # only local access -- only logged in users
245: user = getSecurityManager().getUser()
246: if user is not None:
247: #print "user: ", user
248: return (user.getUserName() != "Anonymous User")
249: else:
250: return False
1.8 casties 251:
1.22 dwinter 252: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
1.8 casties 253: return False
1.9 casties 254:
1.8 casties 255:
1.35 dwinter 256: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 257: """gibt param von dlInfo aus"""
1.13 casties 258: num_retries = 3
1.7 casties 259: if docinfo is None:
260: docinfo = {}
1.35 dwinter 261:
262: for x in range(cut):
1.38 ! dwinter 263:
1.35 dwinter 264: path=getParentDir(path)
1.38 ! dwinter 265:
1.13 casties 266: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 267:
1.22 dwinter 268: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
1.6 casties 269:
1.13 casties 270: for cnt in range(num_retries):
1.9 casties 271: try:
1.13 casties 272: # dom = NonvalidatingReader.parseUri(imageUrl)
273: txt=urllib.urlopen(infoUrl).read()
274: dom = Parse(txt)
1.9 casties 275: break
276: except:
1.22 dwinter 277: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9 casties 278: else:
1.13 casties 279: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6 casties 280:
1.10 casties 281: sizes=dom.xpath("//dir/size")
1.22 dwinter 282: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
1.6 casties 283:
1.10 casties 284: if sizes:
285: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 286: else:
287: docinfo['numPages'] = 0
288:
289: return docinfo
1.8 casties 290:
1.6 casties 291:
1.9 casties 292: def getIndexMeta(self, url):
293: """returns dom of index.meta document at url"""
1.12 casties 294: num_retries = 3
1.9 casties 295: dom = None
1.12 casties 296: metaUrl = None
1.9 casties 297: if url.startswith("http://"):
298: # real URL
1.12 casties 299: metaUrl = url
1.9 casties 300: else:
301: # online path
302: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 303: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 304: if not metaUrl.endswith("index.meta"):
305: metaUrl += "/index.meta"
1.37 dwinter 306: logging.debug("METAURL: %s"%metaUrl)
1.13 casties 307: for cnt in range(num_retries):
1.9 casties 308: try:
1.12 casties 309: # patch dirk encoding fehler treten dann nicht mehr auf
1.11 casties 310: # dom = NonvalidatingReader.parseUri(metaUrl)
1.12 casties 311: txt=urllib.urlopen(metaUrl).read()
312: dom = Parse(txt)
1.13 casties 313: break
1.9 casties 314: except:
1.22 dwinter 315: logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.12 casties 316:
317: if dom is None:
318: raise IOError("Unable to read index meta from %s"%(url))
1.9 casties 319:
320: return dom
1.20 dwinter 321:
322: def getPresentationInfoXML(self, url):
323: """returns dom of info.xml document at url"""
324: num_retries = 3
325: dom = None
326: metaUrl = None
327: if url.startswith("http://"):
328: # real URL
329: metaUrl = url
330: else:
331: # online path
332: server=self.digilibBaseUrl+"/servlet/Texter?fn="
333: metaUrl=server+url.replace("/mpiwg/online","")
334:
335:
336: for cnt in range(num_retries):
337: try:
338: # patch dirk encoding fehler treten dann nicht mehr auf
339: # dom = NonvalidatingReader.parseUri(metaUrl)
340: txt=urllib.urlopen(metaUrl).read()
341: dom = Parse(txt)
342: break
343: except:
1.22 dwinter 344: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.20 dwinter 345:
346: if dom is None:
347: raise IOError("Unable to read infoXMLfrom %s"%(url))
348:
349: return dom
1.9 casties 350:
351:
1.33 dwinter 352: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 353: """gets authorization info from the index.meta file at path or given by dom"""
1.22 dwinter 354: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
1.8 casties 355:
356: access = None
357:
358: if docinfo is None:
359: docinfo = {}
360:
361: if dom is None:
1.38 ! dwinter 362: for x in range(cut):
1.33 dwinter 363: path=getParentDir(path)
364: dom = self.getIndexMeta(path)
1.18 dwinter 365:
1.8 casties 366: acctype = dom.xpath("//access-conditions/access/@type")
367: if acctype and (len(acctype)>0):
368: access=acctype[0].value
1.9 casties 369: if access in ['group', 'institution']:
1.8 casties 370: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
371:
372: docinfo['accessType'] = access
373: return docinfo
1.6 casties 374:
1.8 casties 375:
1.33 dwinter 376: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 377: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 378: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 379:
1.3 casties 380: if docinfo is None:
381: docinfo = {}
1.38 ! dwinter 382:
1.3 casties 383: if dom is None:
1.38 ! dwinter 384: for x in range(cut):
1.33 dwinter 385: path=getParentDir(path)
386: dom = self.getIndexMeta(path)
1.9 casties 387:
1.27 casties 388: # put in all raw bib fields as dict "bib"
389: bib = dom.xpath("//bib/*")
390: if bib and len(bib)>0:
391: bibinfo = {}
392: for e in bib:
393: bibinfo[e.localName] = getTextFromNode(e)
394: docinfo['bib'] = bibinfo
395:
396: # extract some fields (author, title, year) according to their mapping
1.4 casties 397: metaData=self.metadata.main.meta.bib
398: bibtype=dom.xpath("//bib/@type")
399: if bibtype and (len(bibtype)>0):
400: bibtype=bibtype[0].value
1.2 dwinter 401: else:
1.4 casties 402: bibtype="generic"
1.27 casties 403:
1.4 casties 404: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 405: docinfo['bib_type'] = bibtype
1.4 casties 406: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 407: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 408: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 409: try:
410: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
411: except: pass
412: try:
413: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
414: except: pass
415: try:
416: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
417: except: pass
1.27 casties 418: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 419: try:
420: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
421: except:
422: docinfo['lang']=''
1.27 casties 423:
1.3 casties 424: return docinfo
425:
426:
1.8 casties 427: def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
1.3 casties 428: """parse texttool tag in index meta"""
1.22 dwinter 429: logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url))
1.3 casties 430: if docinfo is None:
431: docinfo = {}
432:
1.22 dwinter 433: if docinfo.get('lang',None) is None:
434: docinfo['lang']='' # default keine Sprache gesetzt
1.8 casties 435: if dom is None:
1.9 casties 436: dom = self.getIndexMeta(url)
1.8 casties 437:
1.16 casties 438: archivePath = None
439: archiveName = None
440:
1.8 casties 441: archiveNames=dom.xpath("//resource/name")
442: if archiveNames and (len(archiveNames)>0):
443: archiveName=getTextFromNode(archiveNames[0])
1.16 casties 444: else:
1.22 dwinter 445: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url))
1.3 casties 446:
447: archivePaths=dom.xpath("//resource/archive-path")
448: if archivePaths and (len(archivePaths)>0):
449: archivePath=getTextFromNode(archivePaths[0])
1.8 casties 450: # clean up archive path
451: if archivePath[0] != '/':
452: archivePath = '/' + archivePath
1.16 casties 453: if archiveName and (not archivePath.endswith(archiveName)):
1.8 casties 454: archivePath += "/" + archiveName
1.3 casties 455: else:
1.16 casties 456: # try to get archive-path from url
1.22 dwinter 457: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url))
1.16 casties 458: if (not url.startswith('http')):
459: archivePath = url.replace('index.meta', '')
460:
461: if archivePath is None:
462: # we balk without archive-path
463: raise IOError("Missing archive-path (for text-tool) in %s"%(url))
1.3 casties 464:
1.9 casties 465: imageDirs=dom.xpath("//texttool/image")
466: if imageDirs and (len(imageDirs)>0):
467: imageDir=getTextFromNode(imageDirs[0])
1.3 casties 468: else:
1.22 dwinter 469: # we balk with no image tag / not necessary anymore because textmode is now standard
470: #raise IOError("No text-tool info in %s"%(url))
471: imageDir=""
472: docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
473:
474: docinfo['imagePath'] = "" # keine Bilder
475: docinfo['imageURL'] = ""
476:
1.9 casties 477: if imageDir and archivePath:
478: #print "image: ", imageDir, " archivepath: ", archivePath
479: imageDir=os.path.join(archivePath,imageDir)
480: imageDir=imageDir.replace("/mpiwg/online",'')
481: docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)
482: docinfo['imagePath'] = imageDir
1.38 ! dwinter 483:
1.9 casties 484: docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir
1.3 casties 485:
486: viewerUrls=dom.xpath("//texttool/digiliburlprefix")
487: if viewerUrls and (len(viewerUrls)>0):
488: viewerUrl=getTextFromNode(viewerUrls[0])
1.7 casties 489: docinfo['viewerURL'] = viewerUrl
1.3 casties 490:
491: textUrls=dom.xpath("//texttool/text")
492: if textUrls and (len(textUrls)>0):
493: textUrl=getTextFromNode(textUrls[0])
1.19 dwinter 494: if urlparse.urlparse(textUrl)[0]=="": #keine url
495: textUrl=os.path.join(archivePath,textUrl)
1.31 casties 496: # fix URLs starting with /mpiwg/online
497: if textUrl.startswith("/mpiwg/online"):
498: textUrl = textUrl.replace("/mpiwg/online",'',1)
499:
1.7 casties 500: docinfo['textURL'] = textUrl
1.20 dwinter 501:
502: presentationUrls=dom.xpath("//texttool/presentation")
1.22 dwinter 503: docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag
504:
505: if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen
1.30 casties 506: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
1.20 dwinter 507: # durch den relativen Pfad auf die presentation infos
508: presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0]))
509: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom)
1.22 dwinter 510:
1.25 casties 511: docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info
1.3 casties 512: return docinfo
513:
1.20 dwinter 514:
515: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
516: """gets the bibliographical information from the preseantion entry in texttools
517: """
518: dom=self.getPresentationInfoXML(url)
1.29 casties 519: try:
520: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
521: except:
522: pass
523: try:
524: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
525: except:
526: pass
527: try:
528: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
529: except:
530: pass
1.20 dwinter 531: return docinfo
532:
1.33 dwinter 533: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 534: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.22 dwinter 535: logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
1.3 casties 536: if docinfo is None:
537: docinfo = {}
1.6 casties 538: path=path.replace("/mpiwg/online","")
1.3 casties 539: docinfo['imagePath'] = path
1.35 dwinter 540: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 ! dwinter 541:
! 542: for x in range(cut):
! 543: path=getParentDir(path)
! 544: logging.error("PATH:"+path)
1.7 casties 545: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 546: docinfo['imageURL'] = imageUrl
547:
1.33 dwinter 548: docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo,cut=cut)
549: docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo,cut=cut)
1.3 casties 550: return docinfo
551:
1.2 dwinter 552:
1.3 casties 553: def getDocinfo(self, mode, url):
554: """returns docinfo depending on mode"""
1.22 dwinter 555: logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
1.3 casties 556: # look for cached docinfo in session
1.21 dwinter 557: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 558: docinfo = self.REQUEST.SESSION['docinfo']
559: # check if its still current
560: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.22 dwinter 561: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
1.3 casties 562: return docinfo
563: # new docinfo
564: docinfo = {'mode': mode, 'url': url}
565: if mode=="texttool": #index.meta with texttool information
566: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
567: elif mode=="imagepath":
568: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 569: elif mode=="filepath":
1.37 dwinter 570: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 571: else:
1.22 dwinter 572: logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
1.10 casties 573: raise ValueError("Unknown mode %s"%(mode))
574:
1.22 dwinter 575: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
1.3 casties 576: self.REQUEST.SESSION['docinfo'] = docinfo
577: return docinfo
1.2 dwinter 578:
579:
1.4 casties 580: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):
1.3 casties 581: """returns pageinfo with the given parameters"""
582: pageinfo = {}
1.4 casties 583: current = getInt(current)
584: pageinfo['current'] = current
585: rows = int(rows or self.thumbrows)
586: pageinfo['rows'] = rows
587: cols = int(cols or self.thumbcols)
588: pageinfo['cols'] = cols
589: grpsize = cols * rows
590: pageinfo['groupsize'] = grpsize
1.28 casties 591: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
592: # int(current / grpsize) * grpsize +1))
1.3 casties 593: pageinfo['start'] = start
1.4 casties 594: pageinfo['end'] = start + grpsize
595: if docinfo is not None:
596: np = int(docinfo['numPages'])
597: pageinfo['end'] = min(pageinfo['end'], np)
598: pageinfo['numgroups'] = int(np / grpsize)
599: if np % grpsize > 0:
600: pageinfo['numgroups'] += 1
1.38 ! dwinter 601:
1.3 casties 602: return pageinfo
603:
1.1 dwinter 604: def text(self,mode,url,pn):
605: """give text"""
606: if mode=="texttool": #index.meta with texttool information
607: (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
608:
1.9 casties 609: #print textpath
1.1 dwinter 610: try:
611: dom = NonvalidatingReader.parseUri(textpath)
612: except:
613: return None
614:
615: list=[]
616: nodes=dom.xpath("//pb")
617:
618: node=nodes[int(pn)-1]
619:
620: p=node
621:
622: while p.tagName!="p":
623: p=p.parentNode
624:
625:
626: endNode=nodes[int(pn)]
627:
628:
629: e=endNode
630:
631: while e.tagName!="p":
632: e=e.parentNode
633:
634:
635: next=node.parentNode
636:
637: #sammle s
638: while next and (next!=endNode.parentNode):
639: list.append(next)
640: next=next.nextSibling
641: list.append(endNode.parentNode)
642:
643: if p==e:# beide im selben paragraphen
1.2 dwinter 644: pass
645: # else:
646: # next=p
647: # while next!=e:
648: # print next,e
649: # list.append(next)
650: # next=next.nextSibling
651: #
652: # for x in list:
653: # PrettyPrint(x)
654: #
655: # return list
1.3 casties 656: #
657:
658: def findDigilibUrl(self):
659: """try to get the digilib URL from zogilib"""
660: url = self.imageViewerUrl[:-1] + "/getScalerUrl"
1.20 dwinter 661: #print urlparse.urlparse(url)[0]
662: #print urlparse.urljoin(self.absolute_url(),url)
663: logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0])
664: logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url))
665:
1.3 casties 666: try:
1.18 dwinter 667: if urlparse.urlparse(url)[0]=='': #relative path
668: url=urlparse.urljoin(self.absolute_url()+"/",url)
669:
1.3 casties 670: scaler = urlopen(url).read()
671: return scaler.replace("/servlet/Scaler?", "")
672: except:
673: return None
674:
1.18 dwinter 675: def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
1.3 casties 676: """init document viewer"""
677: self.title=title
678: self.imageViewerUrl=imageViewerUrl
1.18 dwinter 679: self.textViewerUrl=textViewerUrl
1.3 casties 680: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 681: self.thumbrows = thumbrows
682: self.thumbcols = thumbcols
1.8 casties 683: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 684: if RESPONSE is not None:
685: RESPONSE.redirect('manage_main')
1.1 dwinter 686:
687:
688:
689:
690: # security.declareProtected('View management screens','renameImageForm')
691:
692: def manage_AddDocumentViewerForm(self):
693: """add the viewer form"""
1.3 casties 694: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 695: return pt()
696:
1.18 dwinter 697: def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None):
1.1 dwinter 698: """add the viewer"""
1.18 dwinter 699: newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl)
1.1 dwinter 700: self._setObject(id,newObj)
701:
702: if RESPONSE is not None:
703: RESPONSE.redirect('manage_main')
1.3 casties 704:
705:
706: ##
707: ## DocumentViewerTemplate class
708: ##
709: class DocumentViewerTemplate(ZopePageTemplate):
710: """Template for document viewer"""
711: meta_type="DocumentViewer Template"
712:
713:
714: def manage_addDocumentViewerTemplateForm(self):
715: """Form for adding"""
716: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
717: return pt()
718:
719: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
720: REQUEST=None, submit=None):
721: "Add a Page Template with optional file content."
722:
723: self._setObject(id, DocumentViewerTemplate(id))
724: ob = getattr(self, id)
1.23 dwinter 725: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
726: logging.info("txt %s:"%txt)
727: ob.pt_edit(txt,"text/html")
1.3 casties 728: if title:
729: ob.pt_setTitle(title)
730: try:
731: u = self.DestinationURL()
732: except AttributeError:
733: u = REQUEST['URL1']
734:
735: u = "%s/%s" % (u, urllib.quote(id))
736: REQUEST.RESPONSE.redirect(u+'/manage_main')
737: return ''
738:
739:
1.14 casties 740:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>