searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-04 20:37:15 +02:00
Code Issues Releases Wiki Activity

Extract and index data

Browse source
This commit is contained in:
f3r10 2022-10-12 06:24:56 -05:00 • committed by ManyTheFish
parent c45d1e3610
commit d97fb6117e
3 changed files with 37 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

15
milli/src/update/index_documents/extract/extract_docid_word_positions.rs
View file

@ -1,9 +1,9 @@
use std::collections::HashSet;
use std::collections::{HashMap, HashSet};
use std::convert::TryInto;
use std::fs::File;
use std::{io, mem, str};
use charabia::{SeparatorKind, Token, TokenKind, TokenizerBuilder};
use charabia::{Language, Script, SeparatorKind, Token, TokenKind, TokenizerBuilder};
use roaring::RoaringBitmap;
use serde_json::Value;
@ -25,12 +25,13 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
searchable_fields: &Option<HashSet<FieldId>>,
stop_words: Option<&fst::Set<&[u8]>>,
max_positions_per_attributes: Option<u32>,
) -> Result<(RoaringBitmap, grenad::Reader<File>)> {
) -> Result<(RoaringBitmap, grenad::Reader<File>, HashMap<(Script, Language), RoaringBitmap>)> {
let max_positions_per_attributes = max_positions_per_attributes
.map_or(MAX_POSITION_PER_ATTRIBUTE, |max| max.min(MAX_POSITION_PER_ATTRIBUTE));
let max_memory = indexer.max_memory_by_thread();
let mut documents_ids = RoaringBitmap::new();
let mut script_language_pair = HashMap::new();
let mut docid_word_positions_sorter = create_sorter(
grenad::SortAlgorithm::Stable,
concat_u32s_array,
@ -70,6 +71,12 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
.take_while(|(p, _)| (*p as u32) < max_positions_per_attributes);
for (index, token) in tokens {
let script = token.script;
let language = token.language.unwrap_or_default();
let entry = script_language_pair
.entry((script, language))
.or_insert_with(RoaringBitmap::new);
entry.push(document_id);
let token = token.lemma().trim();
if !token.is_empty() && token.len() <= MAX_WORD_LENGTH {
key_buffer.truncate(mem::size_of::<u32>());
@ -88,7 +95,7 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
}
}
sorter_into_reader(docid_word_positions_sorter, indexer).map(|reader| (documents_ids, reader))
sorter_into_reader(docid_word_positions_sorter, indexer).map(|reader| (documents_ids, reader, script_language_pair))
}
/// Transform a JSON value into a string that can be indexed.

4
milli/src/update/index_documents/extract/mod.rs
View file

@ -257,7 +257,7 @@ fn send_and_extract_flattened_documents_data(
let (docid_word_positions_chunk, docid_fid_facet_values_chunks): (Result<_>, Result<_>) =
rayon::join(
|| {
let (documents_ids, docid_word_positions_chunk) = extract_docid_word_positions(
let (documents_ids, docid_word_positions_chunk, script_language_pair) = extract_docid_word_positions(
flattened_documents_chunk.clone(),
indexer,
searchable_fields,
@ -274,6 +274,8 @@ fn send_and_extract_flattened_documents_data(
let _ = lmdb_writer_sx
.send(Ok(TypedChunk::DocidWordPositions(docid_word_positions_chunk.clone())));
let _ = lmdb_writer_sx.send(Ok(TypedChunk::ScriptLanguageDocids(script_language_pair)));
Ok(docid_word_positions_chunk)
},
|| {