snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-23 02:27:40 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Count the number of documents correctly

Browse Source
This commit is contained in:
Clément Renault 2024-11-19 15:02:37 +01:00
parent bce7ab614a
commit 0019ec74fe
No known key found for this signature in database
GPG Key ID: F250A4C4E3AE5F5F
1 changed files with 5 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
crates/milli/src/update/new/indexer/document_operation.rs
View File

@ -58,7 +58,6 @@ impl<'pl> DocumentOperation<'pl> {
for operation in operations { for operation in operations {
let mut bytes = 0; let mut bytes = 0;
let mut document_count = 0;
let result = match operation { let result = match operation {
Payload::Addition(payload) => extract_addition_payload_changes( Payload::Addition(payload) => extract_addition_payload_changes(
indexer, indexer,
@ -69,7 +68,6 @@ impl<'pl> DocumentOperation<'pl> {
new_fields_ids_map, new_fields_ids_map,
&mut available_docids, &mut available_docids,
&mut bytes, &mut bytes,
&mut document_count,
&docids_version_offsets, &docids_version_offsets,
method, method,
payload, payload,
@ -78,7 +76,6 @@ impl<'pl> DocumentOperation<'pl> {
index, index,
rtxn, rtxn,
&mut available_docids, &mut available_docids,
&mut document_count,
&docids_version_offsets, &docids_version_offsets,
method, method,
to_delete, to_delete,
@ -96,7 +93,11 @@ impl<'pl> DocumentOperation<'pl> {
Err(e) => return Err(e), Err(e) => return Err(e),
}; };
operations_stats.push(PayloadStats { document_count, bytes, error }); operations_stats.push(PayloadStats {
document_count: docids_version_offsets.len() as u64,
bytes,
error,
});
} }
// TODO We must drain the HashMap into a Vec because rayon::hash_map::IntoIter: !Clone // TODO We must drain the HashMap into a Vec because rayon::hash_map::IntoIter: !Clone
@ -128,7 +129,6 @@ fn extract_addition_payload_changes<'r, 'pl: 'r>(
new_fields_ids_map: &mut FieldsIdsMap, new_fields_ids_map: &mut FieldsIdsMap,
available_docids: &mut AvailableIds, available_docids: &mut AvailableIds,
bytes: &mut u64, bytes: &mut u64,
number_of_documents: &mut u64,
main_docids_version_offsets: &hashbrown::HashMap<&'pl str, PayloadOperations<'pl>>, main_docids_version_offsets: &hashbrown::HashMap<&'pl str, PayloadOperations<'pl>>,
method: MergeMethod, method: MergeMethod,
payload: &'pl [u8], payload: &'pl [u8],
@ -140,7 +140,6 @@ fn extract_addition_payload_changes<'r, 'pl: 'r>(
let mut iter = Deserializer::from_slice(payload).into_iter::<&RawValue>(); let mut iter = Deserializer::from_slice(payload).into_iter::<&RawValue>();
while let Some(doc) = iter.next().transpose().map_err(InternalError::SerdeJson)? { while let Some(doc) = iter.next().transpose().map_err(InternalError::SerdeJson)? {
*bytes = previous_offset as u64; *bytes = previous_offset as u64;
*number_of_documents = new_docids_version_offsets.len() as u64;
// Only guess the primary key if it is the first document // Only guess the primary key if it is the first document
let retrieved_primary_key = if previous_offset == 0 { let retrieved_primary_key = if previous_offset == 0 {
@ -238,7 +237,6 @@ fn extract_deletion_payload_changes<'s, 'pl: 's>(
index: &Index, index: &Index,
rtxn: &RoTxn, rtxn: &RoTxn,
available_docids: &mut AvailableIds, available_docids: &mut AvailableIds,
number_of_documents: &mut u64,
main_docids_version_offsets: &hashbrown::HashMap<&'s str, PayloadOperations<'pl>>, main_docids_version_offsets: &hashbrown::HashMap<&'s str, PayloadOperations<'pl>>,
method: MergeMethod, method: MergeMethod,
to_delete: &'pl [&'pl str], to_delete: &'pl [&'pl str],
@ -287,7 +285,6 @@ fn extract_deletion_payload_changes<'s, 'pl: 's>(
} }
}, },
} }
*number_of_documents += 1;
} }
Ok(new_docids_version_offsets) Ok(new_docids_version_offsets)