Mercurial > hg > purlService
changeset 5:3ebe37d81071
addDri added
reorganisation of the packafes
| author | dwinter |
|---|---|
| date | Fri, 02 Nov 2012 09:01:35 +0100 |
| parents | 107f13ca333b |
| children | f0417a01690a |
| files | addDriToIndexMeta.py manageIndexMetaPURLs.py redirector.py restService.py restService/__init__.py restService/redirector.py restService/restService.py restService/viewer.config viewer.config |
| diffstat | 8 files changed, 206 insertions(+), 141 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/addDriToIndexMeta.py Fri Nov 02 09:01:35 2012 +0100 @@ -0,0 +1,65 @@ +''' +Created on 01.11.2012 + +@author: dwinter +''' +import os +import manageIndexMetaPURLs +import re +from lxml import etree + +from os.path import join, getsize + + +def addPURL(fl,purl,test=False): + tree = etree.parse(fl) + + dris = tree.xpath("/resource/meta/dri[@type='mpiwg']") + + if len(dris)==0: # erzeuge neu + newDri = etree.Element("dri",type="mpiwg") + newDri.text=purl + metas=tree.xpath("/resource/meta") + if len(metas)==0: + print "no resource/meta in %s"%fl + return False + else: + metas[0].append(newDri) + else: + dris[0].text=purl + + print etree.tostring(tree, pretty_print=True) + + if not test: + os.rename(fl, fl+"_mpiwg_dri") + out = etree.tostring(tree, encoding="UTF-8",xml_declaration=False) + fo = file(fl,"w") + fo.write(out) + fo.close + return True + +def addDriToIndexMeta(path,delpath="",replacepath="", update=False,test=False): + + + + for root, dirs, files in os.walk(path): + + + for name in files: + if name.endswith(".meta"): + fl=join(root, name) + shortPath=re.sub("^"+delpath,replacepath,fl) + purl=manageIndexMetaPURLs.IndexMetaPURLManager().getPurl(shortPath) + + addPURL(fl,purl,test) + + if 'pageimg' in dirs: + dirs.remove('pageimg') # don't visit pageimf + for dir in dirs: + if dir== "pageimg": + dirs.remove('pageimg') + if dir.startswith("."): + dirs.remove(dir) + +if __name__ == '__main__': + addDriToIndexMeta("/mpiwg/online/permanent/annalen",delpath="/mpiwg/online") \ No newline at end of file
--- a/manageIndexMetaPURLs.py Thu Nov 01 17:08:10 2012 +0100 +++ b/manageIndexMetaPURLs.py Fri Nov 02 09:01:35 2012 +0100 @@ -38,7 +38,7 @@ def __init__(self): - self.purlDB = web.database(dbn="postgres", db="purlDB",user="purlUSER",password="p*lWa55eR", host="localhost") + self.purlDB = web.database(dbn="postgres", db="purlDB",user="purlUSER",password="3333", host="localhost")
--- a/redirector.py Thu Nov 01 17:08:10 2012 +0100 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,95 +0,0 @@ -''' -redirects depending on a configuration file an index.meta purl to an viewer -Created on 01.11.2012 - -@author: dwinter -''' - -import web -import manageIndexMetaPURLs -import logging - -class redirector: - - viewers={} # hash mit allen viewer name --> urls - purlHandler=None - def __init__(self): - #read config file for the viewers - confFile= file("viewer.config") - - self.purlHandler = manageIndexMetaPURLs.IndexMetaPURLManager() - - for line in confFile.readlines(): - splitted=line.split(",") - - list=[] - if splitted[1]=="": - list.append(None) # index.meta werden von dieser einstellung nicht interpretiert - else: - list.append(splitted[1]) - - if len(splitted)>1: # url fur image viewer - if splitted[2]=="": - list.append(None) # index.meta werden von dieser einstellung nicht interpretiert - else: - list.append(splitted[2]) - else: - list.append(None) # null wenn keiner konfiguriert wird. TODO: handle this - - - self.viewers[splitted[0]]=list - - def GET(self,path): - - splitted=path.split("/") - if len(splitted)!=2: #pfrad sollte zwei anteile habe "flavour/purl" - raise web.notfound("not found") - - purl = splitted[1] - flavour = splitted[0] - - if flavour not in self.viewers.keys(): - raise web.notfound("no viewer for %s"%flavour) - - formats = self.viewers[flavour] - - viewerWithIndexMetaFormatString = formats[0]; - viewerWithImagePathFormatString = formats[1]; - - - # checke ob es einen Image path gibt - path,validity = self.purlHandler.getImagePathValidity(purl) - if path is not None and path!="": - return self.handlePath(path,validity,viewerWithImagePathFormatString) - - - path,validity = self.purlHandler.getPathValidity(purl) - - if path is not None and path !="": - return self.handlePath(path,validity,viewerWithIndexMetaFormatString) - - - - #handle path - def handlePath(self,path,validity,viewerFormatString): - - if viewerFormatString is None or viewerFormatString=="": - raise web.internalerror("no viewer configure for indexMeta for this flavour") - - if path is None: - raise web.notfound("Cannnot find a URL to this path") - - if validity is manageIndexMetaPURLs.PERM_NON_VALID: - raise web.notfound("PURL NON VALID ANYMORE!") - - if validity is manageIndexMetaPURLs.TEMP_NON_VALID: - return web.notfound("PURL currently not VALID try later!") - - - viewerUrl = viewerFormatString%path - - print viewerUrl - raise web.redirect(viewerUrl,"302 found") - -if __name__ == '__main__': - pass \ No newline at end of file
--- a/restService.py Thu Nov 01 17:08:10 2012 +0100 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,42 +0,0 @@ -''' -Created on 31.10.2012 - -@author: dwinter -''' -import web -import manageIndexMetaPURLs -from redirector import redirector -import logging - -urls = ( - '/purl/(.+)','purl', - '/docuviewer/(.+)','redirector', -) - -app = web.application(urls, globals()) - - -class purl: - - def __init__(self): - self.md=manageIndexMetaPURLs.IndexMetaPURLManager() - - def GET(self,purl): - - path,validity=self.md.getPathValidity(purl) - - if path is None: - raise web.notfound("Cannnot find a URL to this path") - - if validity is manageIndexMetaPURLs.PERM_NON_VALID: - raise web.notfound("PURL NON VALID ANYMORE!") - - if validity is manageIndexMetaPURLs.TEMP_NON_VALID: - return web.notfound("PURL currently not VALID try later!") - - - return path - - -if __name__ == "__main__": - app.run() \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/restService/redirector.py Fri Nov 02 09:01:35 2012 +0100 @@ -0,0 +1,95 @@ +''' +redirects depending on a configuration file an index.meta purl to an viewer +Created on 01.11.2012 + +@author: dwinter +''' + +import web +import manageIndexMetaPURLs +import logging + +class redirector: + + viewers={} # hash mit allen viewer name --> urls + purlHandler=None + def __init__(self): + #read config file for the viewers + confFile= file("viewer.config") + + self.purlHandler = manageIndexMetaPURLs.IndexMetaPURLManager() + + for line in confFile.readlines(): + splitted=line.split(",") + + list=[] + if splitted[1]=="": + list.append(None) # index.meta werden von dieser einstellung nicht interpretiert + else: + list.append(splitted[1]) + + if len(splitted)>1: # url fur image viewer + if splitted[2]=="": + list.append(None) # index.meta werden von dieser einstellung nicht interpretiert + else: + list.append(splitted[2]) + else: + list.append(None) # null wenn keiner konfiguriert wird. TODO: handle this + + + self.viewers[splitted[0]]=list + + def GET(self,path): + + splitted=path.split("/") + if len(splitted)!=2: #pfrad sollte zwei anteile habe "flavour/purl" + raise web.notfound("not found") + + purl = splitted[1] + flavour = splitted[0] + + if flavour not in self.viewers.keys(): + raise web.notfound("no viewer for %s"%flavour) + + formats = self.viewers[flavour] + + viewerWithIndexMetaFormatString = formats[0]; + viewerWithImagePathFormatString = formats[1]; + + + # checke ob es einen Image path gibt + path,validity = self.purlHandler.getImagePathValidity(purl) + if path is not None and path!="": + return self.handlePath(path,validity,viewerWithImagePathFormatString) + + + path,validity = self.purlHandler.getPathValidity(purl) + + if path is not None and path !="": + return self.handlePath(path,validity,viewerWithIndexMetaFormatString) + + + + #handle path + def handlePath(self,path,validity,viewerFormatString): + + if viewerFormatString is None or viewerFormatString=="": + raise web.internalerror("no viewer configure for indexMeta for this flavour") + + if path is None: + raise web.notfound("Cannnot find a URL to this path") + + if validity is manageIndexMetaPURLs.PERM_NON_VALID: + raise web.notfound("PURL NON VALID ANYMORE!") + + if validity is manageIndexMetaPURLs.TEMP_NON_VALID: + return web.notfound("PURL currently not VALID try later!") + + + viewerUrl = viewerFormatString%path + + print viewerUrl + raise web.redirect(viewerUrl,"302 found") + +if __name__ == '__main__': + pass \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/restService/restService.py Fri Nov 02 09:01:35 2012 +0100 @@ -0,0 +1,42 @@ +''' +Created on 31.10.2012 + +@author: dwinter +''' +import web +import manageIndexMetaPURLs +from redirector import redirector +import logging + +urls = ( + '/purl/(.+)','purl', + '/docuviewer/(.+)','redirector', +) + +app = web.application(urls, globals()) + + +class purl: + + def __init__(self): + self.md=manageIndexMetaPURLs.IndexMetaPURLManager() + + def GET(self,purl): + + path,validity=self.md.getPathValidity(purl) + + if path is None: + raise web.notfound("Cannnot find a URL to this path") + + if validity is manageIndexMetaPURLs.PERM_NON_VALID: + raise web.notfound("PURL NON VALID ANYMORE!") + + if validity is manageIndexMetaPURLs.TEMP_NON_VALID: + return web.notfound("PURL currently not VALID try later!") + + + return path + + +if __name__ == "__main__": + app.run() \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/restService/viewer.config Fri Nov 02 09:01:35 2012 +0100 @@ -0,0 +1,3 @@ +echo,http://echo.mpiwg-berlin.mpg.de/ECHOdocuViewfull?url=%s,http://echo.mpiwg-berlin.mpg.de/ECHOdocuViewfull?mode=imagepath&url=%s&viewMode=images +libcoll,,http://libcoll.mpiwg-berlin.mpg.de/libview?url=%s&mode=imagepath +digilib,,http://digilib.mpiwg-berlin.mpg.de/digitallibrary/jquery/digilib.html?fn=%s
--- a/viewer.config Thu Nov 01 17:08:10 2012 +0100 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,3 +0,0 @@ -echo,http://echo.mpiwg-berlin.mpg.de/ECHOdocuViewfull?url=%s,http://echo.mpiwg-berlin.mpg.de/ECHOdocuViewfull?mode=imagepath&url=%s&viewMode=images -libcoll,,http://libcoll.mpiwg-berlin.mpg.de/libview?url=%s&mode=imagepath -digilib,,http://digilib.mpiwg-berlin.mpg.de/digitallibrary/jquery/digilib.html?fn=%s