Mercurial > hg > purlService

changeset 28:246049db5466

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
getImagePath askes now the md server for the image path new module image.py to handle this
author dwinter
date Wed, 13 Mar 2013 15:15:27 +0100
parents cbae1998a2a9
children 7027fbf1d141
files managePurls/manageIndexMetaPURLs.py restService/images.py restService/restService.py
diffstat 3 files changed, 107 insertions(+), 77 deletions(-) [+]
line wrap: on
line diff
--- a/managePurls/manageIndexMetaPURLs.py	Wed Mar 13 11:02:20 2013 +0100
+++ b/managePurls/manageIndexMetaPURLs.py	Wed Mar 13 15:15:27 2013 +0100
@@ -17,6 +17,8 @@
 VALID=1
 TEMP_NON_VALID=0
 PERM_NON_VALID=-1
+NO_METADATA_FOUND=-2
+NO_IMAGE_PATH_FOUND=-3
     
 class IndexMetaPURLManager:
     
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/restService/images.py	Wed Mar 13 15:15:27 2013 +0100
@@ -0,0 +1,103 @@
+'''
+handels the image path
+Created on 13.03.2013
+
+@author: dwinter
+'''
+
+import web
+import managePurls.manageIndexMetaPURLs as manageIndexMetaPURLs
+import logging
+import urllib
+import urllib2
+import sunburnt
+import os.path
+
+#SOLR_URL="http://127.0.0.1:8983/solr/mpiwgSources"
+SOLR_URL="http://md.mpiwg-berlin.mpg.de:8983/solr/mpiwgSources"
+SCALERPATH="http://digilib.mpiwg-berlin.mpg.de/digitallibrary/servlet/Scaler?fn=%s"
+
+
+
+class imageBasic:
+    def __init__(self):
+        self.md=manageIndexMetaPURLs.IndexMetaPURLManager()
+        self.solr = sunburnt.SolrInterface(SOLR_URL)
+        
+    def getImagePathFromMetaData(self,purl):
+        query=self.solr.query(**{'mpiwg-dri':purl})
+        
+        res = query.execute()
+        
+        if res.result.numFound == 0:
+            return "",manageIndexMetaPURLs.NO_METADATA_FOUND
+        
+        doc=res.result.docs[0]
+        
+        path=doc.get('TT_image',None)
+        
+        if not isinstance(path, basestring): #TT_image was  defined as multiple , shouldn't be the case ?
+            path=path[0]
+        
+      
+        archivePath=doc.get('archive-path',None)
+       
+        if (path == None) or (archivePath==None):
+            return "",manageIndexMetaPURLs.NO_IMAGE_PATH_FOUND
+        
+        path = os.path.join(archivePath,path)
+        path = path.replace("/mpiwg/online",'')
+        return path,manageIndexMetaPURLs.VALID
+        
+    def getPath(self,purl):
+        
+        #first try check if path stored
+        path,validity=self.md.getImagePathValidity(purl)
+        
+        if path=="":
+           
+            #second try gessing
+            
+            path,validity=self.getImagePathFromMetaData(purl)
+           
+            if path=="":
+            
+                path,validity=self.md.getPathValidity(purl)
+                
+                path=path.replace("index.meta","pageimg") #hope that images are stored at the required place
+                 
+                if path.startswith("http"): # there is a url stored, than this cannot be a path for the image server
+                    raise web.notfound("NO IMAGE PATH STORED FOUND AN URL(%s)!"%path)
+    
+
+
+        if validity is manageIndexMetaPURLs.PERM_NON_VALID:
+            raise web.notfound("PURL NON VALID ANYMORE!")
+         
+        if validity is manageIndexMetaPURLs.TEMP_NON_VALID:
+            raise web.notfound("PURL currently not VALID try later!")
+        
+        
+        data = web.input()
+        
+        if not 'dw' in data.keys():
+            data['dw']="100"
+       
+        if not 'dh' in data.keys():
+            data['dh']="100"
+          
+       
+        return SCALERPATH%path+"&"+"&".join(["%s=%s"%(key,value) for key,value in data.items()])
+
+
+class imageURL(imageBasic):
+    def GET(self,purl):
+        return self.getPath(purl)
+        
+class image(imageBasic):     
+    def GET(self,purl):
+        path = self.getPath(purl)
+        print path
+        raise web.redirect(path,"302 found")
+    
+        
\ No newline at end of file
--- a/restService/restService.py	Wed Mar 13 11:02:20 2013 +0100
+++ b/restService/restService.py	Wed Mar 13 15:15:27 2013 +0100
@@ -13,6 +13,8 @@
 from searchService.searchLines import searchLines
 from getPurls import getPurls
 from searchService.searchSolr import searchSolr
+from images import image
+from images import imageURL
 
 import config
 
@@ -116,84 +118,7 @@
         return path
         
     
-class imageURL:
-    def __init__(self):
-        self.md=manageIndexMetaPURLs.IndexMetaPURLManager()
-        
-    def GET(self,purl):
-        
-        #first try check if path stored
-        path,validity=self.md.getImagePathValidity(purl)
-        
-        if path=="":
-            print "no path"
-            #second try gessing
-            path,validity=self.md.getPathValidity(purl)
-            
-            path=path.replace("index.meta","pageimg") #hope that images are stored at the required place
-             
-            if path.startswith("http"): # there is a url stored, than this cannot be a path for the image server
-                raise web.notfound("NO IMAGE PATH STORED FOUND AN URL(%s)!"%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!")
-        
-        
-        data = web.input()
-        
-        if not 'dw' in data.keys():
-            data['dw']="100"
-       
-        if not 'dh' in data.keys():
-            data['dh']="100"
-          
-        
-        return SCALERPATH%path+"&"+"&".join(["%s=%s"%(key,value) for key,value in data.items()])
-
-class image:
-    def __init__(self):
-        self.md=manageIndexMetaPURLs.IndexMetaPURLManager()
-        
-    def GET(self,purl):
-        
-        #first try check if path stored
-        path,validity=self.md.getImagePathValidity(purl)
-        
-        if path=="":
-            print "no path"
-            #second try gessing
-            path,validity=self.md.getPathValidity(purl)
-            
-            path=path.replace("index.meta","pageimg") #hope that images are stored at the required place
-             
-            if path.startswith("http"): # there is a url stored, than this cannot be a path for the image server
-                raise web.notfound("NO IMAGE PATH STORED FOUND AN URL(%s)!"%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!")
-        
-        
-        data = web.input()
-        
-        if not 'dw' in data.keys():
-            data['dw']="100"
-       
-        if not 'dh' in data.keys():
-            data['dh']="100"
-          
-        
-        raise web.redirect(SCALERPATH%path+"&"+"&".join(["%s=%s"%(key,value) for key,value in data.items()]))
-        
  #http://digilib.mpiwg-berlin.mpg.de/digitallibrary/servlet/Scaler?fn=/permanent/echo/hellinomnimon/Gazis-Gram_A/img&dw=1298&dh=915&pn=3       
        
 if __name__ == "__main__":