snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-22 18:17:39 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Fix tokenizer test

Browse Source
This commit is contained in:
ManyTheFish 2024-09-03 14:24:37 +02:00
parent c1557734dc
commit fe69385bd7
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
milli/src/update/new/extract/tokenize_document.rs
View File

@ -270,10 +270,6 @@ mod test {
let value = obkv.into_inner().unwrap(); let value = obkv.into_inner().unwrap();
let obkv = KvReader::from_slice(value.as_slice()); let obkv = KvReader::from_slice(value.as_slice());
fields_ids_map.insert("doggo.age");
fields_ids_map.insert("catto.catto.name");
fields_ids_map.insert("catto.catto.age");
let mut tb = TokenizerBuilder::default(); let mut tb = TokenizerBuilder::default();
let document_tokenizer = DocumentTokenizer { let document_tokenizer = DocumentTokenizer {
tokenizer: &tb.build(), tokenizer: &tb.build(),
@ -282,9 +278,12 @@ mod test {
max_positions_per_attributes: 1000, max_positions_per_attributes: 1000,
}; };
let fields_ids_map_lock = std::sync::RwLock::new(fields_ids_map);
let mut global_fields_ids_map = GlobalFieldsIdsMap::new(&fields_ids_map_lock);
let mut words = std::collections::BTreeMap::new(); let mut words = std::collections::BTreeMap::new();
document_tokenizer document_tokenizer
.tokenize_document(obkv, &fields_ids_map, &mut |fid, pos, word| { .tokenize_document(obkv, &mut global_fields_ids_map, &mut |fid, pos, word| {
words.insert([fid, pos], word.to_string()); words.insert([fid, pos], word.to_string());
}) })
.unwrap(); .unwrap();