feat(corp/data-import): add import of OR 'words_forms' table

This is the full morphological set table for all the words from the
lemmata table, which they don't call it that.

Change-Id: I6f5be673c5f59f11e36bd8c8c935844a7d4fd170
Reviewed-on: https://cl.tvl.fyi/c/depot/+/7894
Tested-by: BuildkiteCI
Reviewed-by: tazjin <tazjin@tvl.su>
This commit is contained in:
Vincent Ambo 2023-01-21 18:00:16 +03:00 committed by tazjin
parent 429c0d00c4
commit 8eeb5d3bcc
3 changed files with 69 additions and 6 deletions

View file

@ -210,12 +210,23 @@ fn open_russian(conn: &Connection, args: &Args) {
db_setup::initial_or_schema(conn);
let tx = conn
.unchecked_transaction()
.ensure("failed to start transaction");
{
let tx = conn
.unchecked_transaction()
.ensure("failed to start transaction");
db_setup::insert_or_words(&tx, parser.words());
tx.commit().ensure("OpenRussian words commit failed");
db_setup::insert_or_words(&tx, parser.words());
tx.commit().ensure("OpenRussian words commit failed");
}
{
let tx = conn
.unchecked_transaction()
.ensure("failed to start transaction");
db_setup::insert_or_word_forms(&tx, parser.words_forms());
tx.commit().ensure("OpenRussian word forms commit failed");
}
info!("finished OpenRussian import");
}