Add wrong-keyboard–transformed language models for "Cyrillic English" (en_cyr) and "Latin Russian" (ru_lat) to TextCat, both to the query-based (LM-query/) and wikitext-based (LM/) models. Also add Windows-1251 wrong-encoding model (ru_win1251) to the wikitext-based models.
|Open||None||T118278 EPIC: Improve Language Identification for use in Cirrus Search|
|Open||TJones||T138958 Detect "wrong keyboard" queries for Russian/American keyboards on EN/RU Wikipedias|
|Resolved||TJones||T213931 Update TextCat with wrong-keyboard models|
|Declined||TJones||T213935 Revert changes to TextCat that add dependency on autoload.php|