From 8d594658ab1b394a24f62528e761b54bacde482c Mon Sep 17 00:00:00 2001 From: Vincent Ambo Date: Tue, 24 Jan 2023 01:54:29 +0300 Subject: feat(corp/data-import): map OC word grammemes to OR form types This table maps the grammemes for individual word forms (*not* for lemmata in either corpus!) to the corresponding grammemes from the other dataset. These have drastically different shapes, so the mapping is not perfect, but will help in determining which forms are intended to be the same on both sides. Change-Id: Ib0717e2f7a79d96bcb5e955a20f551e391fcd759 Reviewed-on: https://cl.tvl.fyi/c/depot/+/7918 Reviewed-by: tazjin Tested-by: BuildkiteCI Autosubmit: tazjin --- corp/russian/data-import/src/main.rs | 1 + 1 file changed, 1 insertion(+) (limited to 'corp/russian/data-import/src/main.rs') diff --git a/corp/russian/data-import/src/main.rs b/corp/russian/data-import/src/main.rs index 95a38e6e93d1..21da48e8d8f4 100644 --- a/corp/russian/data-import/src/main.rs +++ b/corp/russian/data-import/src/main.rs @@ -111,6 +111,7 @@ use std::fs::File; use std::io::BufReader; mod db_setup; +mod mappings; mod oc_parser; mod or_parser; -- cgit 1.4.1