web/blinkster/ldt/contentindexer.py
changeset 35 8b65c9054eac
parent 29 cc9b7e14412b
child 61 efeaf7b1c348
--- a/web/blinkster/ldt/contentindexer.py	Tue Jun 01 10:44:27 2010 +0200
+++ b/web/blinkster/ldt/contentindexer.py	Tue Jun 01 19:07:23 2010 +0200
@@ -17,7 +17,7 @@
 
 class ContentIndexer(object):
         
-        def __init__(self, contentList, writer, decoupage_blackList = settings.DECOUPAGE_BLACKLIST):
+        def __init__(self, contentList, writer, decoupage_blackList=settings.DECOUPAGE_BLACKLIST):
                 self.__contentList = contentList
                 self.__decoupage_blacklist = decoupage_blackList
                 self.__writer = writer
@@ -45,7 +45,7 @@
                 
         def index_content(self, content):
             
-            blinkster.utils.log.debug("Indexing content : "+str(content.iri_id))
+            blinkster.utils.log.debug("Indexing content : " + str(content.iri_id))
             filepath = content.iri_file_path()
             doc = xml.dom.minidom.parse(filepath)
             doc = Ft.Xml.Domlette.ConvertDocument(doc)        
@@ -57,23 +57,23 @@
             res = xml.xpath.Evaluate("/iri/body/ensembles/ensemble", context=con)
 
             for ensemble in res:
-                ensembleId = ensemble.getAttributeNS(None,"id")
+                ensembleId = ensemble.getAttributeNS(None, "id")
                 
                 for decoupageNode in ensemble.childNodes:
-                    blinkster.utils.log.debug("Indexing content decoupage : "+ repr(decoupageNode.nodeType) + " in " + repr(self.decoupage_blacklist))
-                    if decoupageNode.nodeType != xml.dom.Node.ELEMENT_NODE or decoupageNode.tagName != "decoupage"  or decoupageNode.getAttributeNS(None,"id") in self.decoupage_blacklist:
+                    blinkster.utils.log.debug("Indexing content decoupage : " + repr(decoupageNode.nodeType) + " in " + repr(self.decoupage_blacklist))
+                    if decoupageNode.nodeType != xml.dom.Node.ELEMENT_NODE or decoupageNode.tagName != "decoupage"  or decoupageNode.getAttributeNS(None, "id") in self.decoupage_blacklist:
                         continue
                     
-                    decoupId = decoupageNode.getAttributeNS(None,"id")
+                    decoupId = decoupageNode.getAttributeNS(None, "id")
                     res = xml.xpath.Evaluate("elements/element", decoupageNode)
                     for elementNode in res:
                         doc = lucene.Document()
-                        elementId = elementNode.getAttributeNS(None,"id")
-                        tags = elementNode.getAttributeNS(None,"tags")
-                        author = elementNode.getAttributeNS(None,"author")
-                        start_ts = int(elementNode.getAttributeNS(None,"begin"))
-                        duration = int(elementNode.getAttributeNS(None,"dur"))
-                        date_str = elementNode.getAttributeNS(None,"date")
+                        elementId = elementNode.getAttributeNS(None, "id")
+                        tags = elementNode.getAttributeNS(None, "tags")
+                        author = elementNode.getAttributeNS(None, "author")
+                        start_ts = int(elementNode.getAttributeNS(None, "begin"))
+                        duration = int(elementNode.getAttributeNS(None, "dur"))
+                        date_str = elementNode.getAttributeNS(None, "date")
                         
                         if tags is not None:                            
                             tags.replace(",", ";")
@@ -107,18 +107,18 @@
                         doc.add(lucene.Field("abstract", abstract, lucene.Field.Store.NO, lucene.Field.Index.ANALYZED))
                         doc.add(lucene.Field("all", " ".join([tags, title, abstract]), lucene.Field.Store.NO, lucene.Field.Index.ANALYZED))
             
-                        seg = Segment(content = content,
-                                      iri_id = content.iri_id,
-                                      ensemble_id = ensembleId,
-                                      cutting_id = decoupId,
-                                      element_id = elementId,
-                                      tags =  tags,
-                                      title = title,
-                                      abstract = abstract,
-                                      duration = duration,
-                                      author = author,
-                                      start_ts = start_ts,
-                                      date = date_str)
+                        seg = Segment(content=content,
+                                      iri_id=content.iri_id,
+                                      ensemble_id=ensembleId,
+                                      cutting_id=decoupId,
+                                      element_id=elementId,
+                                      tags=tags,
+                                      title=title,
+                                      abstract=abstract,
+                                      duration=duration,
+                                      author=author,
+                                      start_ts=start_ts,
+                                      date=date_str)
                         seg.save()
             
                         self.__writer.addDocument(doc)
@@ -128,7 +128,7 @@
             
 class ProjectIndexer(object):
         
-        def __init__(self, projectList, writer, decoupage_blackList = settings.DECOUPAGE_BLACKLIST):
+        def __init__(self, projectList, writer, decoupage_blackList=settings.DECOUPAGE_BLACKLIST):
                 self.__projectList = projectList
                 self.__decoupage_blacklist = decoupage_blackList
                 self.__writer = writer
@@ -156,7 +156,7 @@
  
         def index_project(self, project):
             
-            blinkster.utils.log.debug("Indexing project : "+str(project.iri_id))
+            blinkster.utils.log.debug("Indexing project : " + str(project.iri_id))
             doc = xml.dom.minidom.parseString(project.ldt)
             doc = Ft.Xml.Domlette.ConvertDocument(doc)        
 
@@ -166,25 +166,25 @@
             res = xml.xpath.Evaluate("/iri/annotations/content", context=con)
 
             for content in res:
-                contentId = content.getAttributeNS(None,"id")
+                contentId = content.getAttributeNS(None, "id")
                 
                 ensembleId = "ens_perso"
                 
                 for decoupageNode in content.childNodes:
-                    blinkster.utils.log.debug("Indexing content decoupage : "+ repr(decoupageNode.nodeType) + " in " + repr(self.decoupage_blacklist))
-                    if decoupageNode.nodeType != xml.dom.Node.ELEMENT_NODE or decoupageNode.tagName != "decoupage"  or decoupageNode.getAttributeNS(None,"id") in self.decoupage_blacklist:
+                    blinkster.utils.log.debug("Indexing content decoupage : " + repr(decoupageNode.nodeType) + " in " + repr(self.decoupage_blacklist))
+                    if decoupageNode.nodeType != xml.dom.Node.ELEMENT_NODE or decoupageNode.tagName != "decoupage"  or decoupageNode.getAttributeNS(None, "id") in self.decoupage_blacklist:
                         continue
                     
-                    decoupId = decoupageNode.getAttributeNS(None,"id")
+                    decoupId = decoupageNode.getAttributeNS(None, "id")
                     res = xml.xpath.Evaluate("elements/element", decoupageNode)
                     for elementNode in res:
                         doc = lucene.Document()
-                        elementId = elementNode.getAttributeNS(None,"id")
-                        tags = elementNode.getAttributeNS(None,"tags")
-                        author = elementNode.getAttributeNS(None,"author")
-                        start_ts = int(elementNode.getAttributeNS(None,"begin"))
-                        duration = int(elementNode.getAttributeNS(None,"dur"))
-                        date_str = elementNode.getAttributeNS(None,"date")
+                        elementId = elementNode.getAttributeNS(None, "id")
+                        tags = elementNode.getAttributeNS(None, "tags")
+                        author = elementNode.getAttributeNS(None, "author")
+                        start_ts = int(elementNode.getAttributeNS(None, "begin"))
+                        duration = int(elementNode.getAttributeNS(None, "dur"))
+                        date_str = elementNode.getAttributeNS(None, "date")
                         
                         if tags is not None:                            
                             tags.replace(",", ";")
@@ -221,21 +221,21 @@
                         doc.add(lucene.Field("all", " ".join([tags, title, abstract]), lucene.Field.Store.NO, lucene.Field.Index.ANALYZED))
             
                         try:
-                            content = Content.objects.get(iri_id = contentId)
-                            seg = Segment( project_obj = project,
-                                      content = content,
-                                      project_id = project.ldt_id,
-                                      iri_id = contentId,
-                                      ensemble_id = ensembleId,
-                                      cutting_id = decoupId,
-                                      element_id = elementId,
-                                      tags =  tags,
-                                      title = title,
-                                      abstract = abstract,
-                                      duration = duration,
-                                      author = author,
-                                      start_ts = start_ts,
-                                      date = date_str)
+                            content = Content.objects.get(iri_id=contentId)
+                            seg = Segment(project_obj=project,
+                                      content=content,
+                                      project_id=project.ldt_id,
+                                      iri_id=contentId,
+                                      ensemble_id=ensembleId,
+                                      cutting_id=decoupId,
+                                      element_id=elementId,
+                                      tags=tags,
+                                      title=title,
+                                      abstract=abstract,
+                                      duration=duration,
+                                      author=author,
+                                      start_ts=start_ts,
+                                      date=date_str)
                             seg.save()
                         except:
                             blinkster.utils.log.error("unable to store segment")