Update Charabia

This commit is contained in:
ManyTheFish 2023-06-28 18:52:32 +02:00
parent 9deeec88e0
commit 84845de9ef
9 changed files with 150 additions and 140 deletions

View file

@ -128,10 +128,10 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
.map(|reader| (documents_ids, reader, script_language_docids))
}
fn extract_tokens_from_document<T: AsRef<[u8]>>(
fn extract_tokens_from_document(
obkv: &KvReader<FieldId>,
searchable_fields: &Option<HashSet<FieldId>>,
tokenizer: &Tokenizer<T>,
tokenizer: &Tokenizer,
max_positions_per_attributes: u32,
buffers: &mut Buffers,
script_language_word_count: &mut HashMap<Script, Vec<(Language, usize)>>,