snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-09-14 00:36:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'filter/field-exist'

Browse Source
This commit is contained in:
Loïc Lecrenier
2022-07-21 14:51:41 +02:00
parent e1bc610d27 1506683705
commit 07003704a8
20 changed files with 479 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs
View File

@ -1,15 +1,19 @@
use std::collections::HashSet;
use std::collections::{BTreeMap, HashSet};
use std::convert::TryInto;
use std::fs::File;
use std::io;
use std::mem::size_of;
use heed::zerocopy::AsBytes;
use heed::BytesEncode;
use roaring::RoaringBitmap;
use serde_json::Value;
use super::helpers::{create_sorter, keep_first, sorter_into_reader, GrenadParameters};
use crate::error::InternalError;
use crate::facet::value_encoding::f64_into_bytes;
use crate::{DocumentId, FieldId, Result};
use crate::update::index_documents::{create_writer, writer_into_reader};
use crate::{CboRoaringBitmapCodec, DocumentId, FieldId, Result, BEU32};
/// Extracts the facet values of each faceted field of each document.
///
@ -20,7 +24,7 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
obkv_documents: grenad::Reader<R>,
indexer: GrenadParameters,
faceted_fields: &HashSet<FieldId>,
) -> Result<(grenad::Reader<File>, grenad::Reader<File>)> {
) -> Result<(grenad::Reader<File>, grenad::Reader<File>, grenad::Reader<File>)> {
let max_memory = indexer.max_memory_by_thread();
let mut fid_docid_facet_numbers_sorter = create_sorter(
@ -39,6 +43,8 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
max_memory.map(|m| m / 2),
);
let mut facet_exists_docids = BTreeMap::<FieldId, RoaringBitmap>::new();
let mut key_buffer = Vec::new();
let mut cursor = obkv_documents.into_cursor()?;
while let Some((docid_bytes, value)) = cursor.move_on_next()? {
@ -46,16 +52,26 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
for (field_id, field_bytes) in obkv.iter() {
if faceted_fields.contains(&field_id) {
let value =
serde_json::from_slice(field_bytes).map_err(InternalError::SerdeJson)?;
let (numbers, strings) = extract_facet_values(&value);
key_buffer.clear();
// prefix key with the field_id and the document_id
// Set key to the field_id
// Note: this encoding is consistent with FieldIdCodec
key_buffer.extend_from_slice(&field_id.to_be_bytes());
// Here, we know already that the document must be added to the “field id exists” database
let document: [u8; 4] = docid_bytes[..4].try_into().ok().unwrap();
let document = BEU32::from(document).get();
facet_exists_docids.entry(field_id).or_default().insert(document);
// For the other extraction tasks, prefix the key with the field_id and the document_id
key_buffer.extend_from_slice(&docid_bytes);
let value =
serde_json::from_slice(field_bytes).map_err(InternalError::SerdeJson)?;
let (numbers, strings) = extract_facet_values(&value);
// insert facet numbers in sorter
for number in numbers {
key_buffer.truncate(size_of::<FieldId>() + size_of::<DocumentId>());
@ -77,9 +93,21 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
}
}
let mut facet_exists_docids_writer = create_writer(
indexer.chunk_compression_type,
indexer.chunk_compression_level,
tempfile::tempfile()?,
);
for (fid, bitmap) in facet_exists_docids.into_iter() {
let bitmap_bytes = CboRoaringBitmapCodec::bytes_encode(&bitmap).unwrap();
facet_exists_docids_writer.insert(fid.to_be_bytes(), &bitmap_bytes)?;
}
let facet_exists_docids_reader = writer_into_reader(facet_exists_docids_writer)?;
Ok((
sorter_into_reader(fid_docid_facet_numbers_sorter, indexer.clone())?,
sorter_into_reader(fid_docid_facet_strings_sorter, indexer)?,
sorter_into_reader(fid_docid_facet_strings_sorter, indexer.clone())?,
facet_exists_docids_reader,
))
}

49
milli/src/update/index_documents/extract/mod.rs
View File

@ -53,7 +53,7 @@ pub(crate) fn data_from_obkv_documents(
})
.collect::<Result<()>>()?;
let result: Result<(Vec<_>, (Vec<_>, Vec<_>))> = flattened_obkv_chunks
let result: Result<(Vec<_>, (Vec<_>, (Vec<_>, Vec<_>)))> = flattened_obkv_chunks
.par_bridge()
.map(|flattened_obkv_chunks| {
send_and_extract_flattened_documents_data(
@ -72,9 +72,28 @@ pub(crate) fn data_from_obkv_documents(
let (
docid_word_positions_chunks,
(docid_fid_facet_numbers_chunks, docid_fid_facet_strings_chunks),
(
docid_fid_facet_numbers_chunks,
(docid_fid_facet_strings_chunks, facet_exists_docids_chunks),
),
) = result?;
// merge facet_exists_docids and send them as a typed chunk
{
let lmdb_writer_sx = lmdb_writer_sx.clone();
rayon::spawn(move || {
debug!("merge {} database", "facet-id-exists-docids");
match facet_exists_docids_chunks.merge(merge_cbo_roaring_bitmaps, &indexer) {
Ok(reader) => {
let _ = lmdb_writer_sx.send(Ok(TypedChunk::FieldIdFacetExistsDocids(reader)));
}
Err(e) => {
let _ = lmdb_writer_sx.send(Err(e));
}
}
});
}
spawn_extraction_task::<_, _, Vec<grenad::Reader<File>>>(
docid_word_positions_chunks.clone(),
indexer.clone(),
@ -197,6 +216,7 @@ fn send_original_documents_data(
/// - docid_word_positions
/// - docid_fid_facet_numbers
/// - docid_fid_facet_strings
/// - docid_fid_facet_exists
fn send_and_extract_flattened_documents_data(
flattened_documents_chunk: Result<grenad::Reader<File>>,
indexer: GrenadParameters,
@ -209,7 +229,10 @@ fn send_and_extract_flattened_documents_data(
max_positions_per_attributes: Option<u32>,
) -> Result<(
grenad::Reader<CursorClonableMmap>,
(grenad::Reader<CursorClonableMmap>, grenad::Reader<CursorClonableMmap>),
(
grenad::Reader<CursorClonableMmap>,
(grenad::Reader<CursorClonableMmap>, grenad::Reader<File>),
),
)> {
let flattened_documents_chunk =
flattened_documents_chunk.and_then(|c| unsafe { as_cloneable_grenad(&c) })?;
@ -250,12 +273,15 @@ fn send_and_extract_flattened_documents_data(
Ok(docid_word_positions_chunk)
},
|| {
let (docid_fid_facet_numbers_chunk, docid_fid_facet_strings_chunk) =
extract_fid_docid_facet_values(
flattened_documents_chunk.clone(),
indexer.clone(),
faceted_fields,
)?;
let (
docid_fid_facet_numbers_chunk,
docid_fid_facet_strings_chunk,
fid_facet_exists_docids_chunk,
) = extract_fid_docid_facet_values(
flattened_documents_chunk.clone(),
indexer.clone(),
faceted_fields,
)?;
// send docid_fid_facet_numbers_chunk to DB writer
let docid_fid_facet_numbers_chunk =
@ -273,7 +299,10 @@ fn send_and_extract_flattened_documents_data(
docid_fid_facet_strings_chunk.clone(),
)));
Ok((docid_fid_facet_numbers_chunk, docid_fid_facet_strings_chunk))
Ok((
docid_fid_facet_numbers_chunk,
(docid_fid_facet_strings_chunk, fid_facet_exists_docids_chunk),
))
},
);