Merge branch 'master' of github.com:musically-ut/stackexchange-dump-to-postgres

Author: musically-ut

README.md

@@ -35,7 +35,7 @@ Schema hints are taken from [a post on Meta.StackExchange](http://meta.stackexch
 ## Caveats and TODOs
 
  - It prepares some indexes and views which may not be necessary for your analysis.
- - The `Body` field in `Posts` table is NOT populated.
+ - The `Body` field in `Posts` table is NOT populated by default. You have to use `--with-post-body` argument to include it.
  - The `EmailHash` field in `Users` table is NOT populated.
  - Some tables (e.g. `PostHistory` and `Comments`) are missing.
 

load_into_pg.py

@@ -152,6 +152,12 @@ def handleTable(table, keys, dbname, mbDbFile, mbHost, mbPort, mbUsername, mbPas
                    , default = None
                    )
 
+parser.add_argument( '--with-post-body'
+                   , help   = 'Import the posts with the post body. Only used if importing Posts.xml'
+                   , action = 'store_true'
+                   , default = False
+                   )
+
 args = parser.parse_args()
 
 table = args.table
@@ -213,6 +219,10 @@ def handleTable(table, keys, dbname, mbDbFile, mbHost, mbPort, mbUsername, mbPas
       , 'ClosedDate'
       , 'CommunityOwnedDate'
     ]
+
+    if args.with_post_body:
+        keys.append('Body')
+
 elif table == 'Tags':
     keys = [
         'Id'