snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-08-02 11:50:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make max_position_per_attributes changable

Browse Source
This commit is contained in:
many
2021-10-06 12:11:07 +02:00
parent 360c5ff3df
commit c5a6075484
6 changed files with 31 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
milli/src/update/index_documents/extract/extract_docid_word_positions.rs
View File

@ -23,7 +23,10 @@ pub fn extract_docid_word_positions<R: io::Read>(
indexer: GrenadParameters,
searchable_fields: &Option<HashSet<FieldId>>,
stop_words: Option<&fst::Set<&[u8]>>,
max_positions_per_attributes: Option<u32>,
) -> Result<(RoaringBitmap, grenad::Reader<File>)> {
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();
@ -62,7 +65,7 @@ pub fn extract_docid_word_positions<R: io::Read>(
if let Some(field) = json_to_string(&value, &mut field_buffer) {
let analyzed = analyzer.analyze(field);
let tokens = process_tokens(analyzed.tokens())
.take_while(|(p, _)| (*p as u32) < MAX_POSITION_PER_ATTRIBUTE);
.take_while(|(p, _)| (*p as u32) < max_positions_per_attributes);
for (index, token) in tokens {
let token = token.text().trim();

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

@ -42,6 +42,7 @@ pub(crate) fn data_from_obkv_documents(
primary_key_id: FieldId,
geo_field_id: Option<FieldId>,
stop_words: Option<fst::Set<&[u8]>>,
max_positions_per_attributes: Option<u32>,
) -> Result<()> {
let result: Result<(Vec<_>, (Vec<_>, Vec<_>))> = obkv_chunks
.par_bridge()
@ -55,6 +56,7 @@ pub(crate) fn data_from_obkv_documents(
primary_key_id,
geo_field_id,
&stop_words,
max_positions_per_attributes,
)
})
.collect();
@ -177,6 +179,7 @@ fn extract_documents_data(
primary_key_id: FieldId,
geo_field_id: Option<FieldId>,
stop_words: &Option<fst::Set<&[u8]>>,
max_positions_per_attributes: Option<u32>,
) -> Result<(
grenad::Reader<CursorClonableMmap>,
(grenad::Reader<CursorClonableMmap>, grenad::Reader<CursorClonableMmap>),
@ -206,6 +209,7 @@ fn extract_documents_data(
indexer.clone(),
searchable_fields,
stop_words.as_ref(),
max_positions_per_attributes,
)?;
// send documents_ids to DB writer

4
milli/src/update/index_documents/mod.rs
View File

@ -68,6 +68,7 @@ pub struct IndexDocuments<'t, 'u, 'i, 'a> {
pub(crate) chunk_compression_type: CompressionType,
pub(crate) chunk_compression_level: Option<u32>,
pub(crate) thread_pool: Option<&'a ThreadPool>,
pub(crate) max_positions_per_attributes: Option<u32>,
facet_level_group_size: Option<NonZeroUsize>,
facet_min_level_size: Option<NonZeroUsize>,
words_prefix_threshold: Option<u32>,
@ -104,6 +105,7 @@ impl<'t, 'u, 'i, 'a> IndexDocuments<'t, 'u, 'i, 'a> {
update_method: IndexDocumentsMethod::ReplaceDocuments,
autogenerate_docids: false,
update_id,
max_positions_per_attributes: None,
}
}
@ -262,6 +264,7 @@ impl<'t, 'u, 'i, 'a> IndexDocuments<'t, 'u, 'i, 'a> {
primary_key_id,
geo_field_id,
stop_words,
self.max_positions_per_attributes,
)
});
@ -284,6 +287,7 @@ impl<'t, 'u, 'i, 'a> IndexDocuments<'t, 'u, 'i, 'a> {
chunk_compression_type: self.chunk_compression_type,
chunk_compression_level: self.chunk_compression_level,
thread_pool: self.thread_pool,
max_positions_per_attributes: self.max_positions_per_attributes,
update_id: self.update_id,
};
let mut deletion_builder = update_builder.delete_documents(self.wtxn, self.index)?;