From: groceryheist Date: Sun, 22 Sep 2019 22:11:59 +0000 (-0700) Subject: elaborate docstring for persistence X-Git-Url: https://code.communitydata.science/mediawiki_dump_tools.git/commitdiff_plain/e871023ff54425af61097a4a95174a42c8245c99?ds=inline;hp=7d62ff9fb779a204912080574b859b8ca4e60a9f elaborate docstring for persistence --- diff --git a/wikiq b/wikiq index ae6b40f..8b741e3 100755 --- a/wikiq +++ b/wikiq @@ -378,8 +378,8 @@ parser.add_argument('-s', '--stdout', dest="stdout", action="store_true", 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.") +parser.add_argument('-p', '--persistence', dest="persist", default="sequence", 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. 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.")