DB BREAKING: Count the number of words in field_id_word_count_docids

This commit is contained in:
Louis Dureuil 2023-06-08 11:30:35 +02:00
parent 9dcf1da59d
commit c15c076da9
No known key found for this signature in database

View File

@ -1,6 +1,6 @@
use std::collections::HashMap; use std::collections::HashMap;
use std::fs::File; use std::fs::File;
use std::{cmp, io}; use std::io;
use grenad::Sorter; use grenad::Sorter;
@ -54,11 +54,10 @@ pub fn extract_fid_word_count_docids<R: io::Read + io::Seek>(
} }
for position in read_u32_ne_bytes(value) { for position in read_u32_ne_bytes(value) {
let (field_id, position) = relative_from_absolute_position(position); let (field_id, _) = relative_from_absolute_position(position);
let word_count = position as u32 + 1;
let value = document_fid_wordcount.entry(field_id as FieldId).or_insert(0); let value = document_fid_wordcount.entry(field_id as FieldId).or_insert(0);
*value = cmp::max(*value, word_count); *value += 1;
} }
} }