update baseline outputs

[mediawiki_dump_tools.git] / wikiq

diff --git a/wikiq b/wikiq
index d7bc0bd22e941ae0faa38262bb302a7c0343bd62..632b05cfcad7d7544cf802db1ef37511293f68cf 100755 (executable)
--- a/wikiq
+++ b/wikiq
@@ -379,13 +379,13 @@ parser.add_argument('--collapse-user', dest="collapse_user", action="store_true"
                     help="Operate only on the final revision made by user a user within all sequences of consecutive edits made by a user. This can be useful for addressing issues with text persistence measures.")
 
 parser.add_argument('-p', '--persistence', dest="persist", default=None, const='', type=str, choices = ['','segment','sequence','legacy'], nargs='?',
-                    help="Compute and report measures of content persistent: (1) persistent token revisions, (2) tokens added, and (3) number of revision used in computing the first measure. This may by slow.  Use -p=segment for advanced persistence calculation method that is robust to content moves. This might be very slow. Use -p=legacy for legacy behavior.")
+                    help="Compute and report measures of content persistent: (1) persistent token revisions, (2) tokens added, and (3) number of revision used in computing the first measure. This may by slow.  The defualt is -p=sequence, which uses the same algorithm as in the past, but with improvements to wikitext parsing. Use -p=legacy for old behavior used in older research projects. Use -p=segment for advanced persistence calculation method that is robust to content moves, but prone to bugs, and slower.")
 
 parser.add_argument('-u', '--url-encode', dest="urlencode", action="store_true",
                     help="Output url encoded text strings. This works around some data issues like newlines in editor names. In the future it may be used to output other text data.")
 
 parser.add_argument('-n', '--namespace-include', dest="namespace_filter", type=int, action='append',
-                    help="Id number of namspace to include.")
+                    help="Id number of namspace to include. Can be specified more than once.")