Fix some tests but not all of them

This commit is contained in:
Clément Renault 2024-11-18 17:39:55 +01:00
parent 670aff5553
commit aba8a0e9e0
No known key found for this signature in database
GPG key ID: F250A4C4E3AE5F5F
20 changed files with 1211 additions and 881 deletions

View file

@ -407,7 +407,7 @@ mod tests {
use big_s::S;
use maplit::hashset;
use crate::documents::documents_batch_reader_from_objects;
use crate::documents::mmap_from_objects;
use crate::index::tests::TempIndex;
use crate::{milli_snap, FacetDistribution, OrderBy};
@ -508,8 +508,7 @@ mod tests {
documents.push(document);
}
let documents = documents_batch_reader_from_objects(documents);
let documents = mmap_from_objects(documents);
index.add_documents(documents).unwrap();
let txn = index.read_txn().unwrap();
@ -594,8 +593,7 @@ mod tests {
documents.push(document);
}
let documents = documents_batch_reader_from_objects(documents);
let documents = mmap_from_objects(documents);
index.add_documents(documents).unwrap();
let txn = index.read_txn().unwrap();
@ -654,8 +652,7 @@ mod tests {
documents.push(document);
}
let documents = documents_batch_reader_from_objects(documents);
let documents = mmap_from_objects(documents);
index.add_documents(documents).unwrap();
let txn = index.read_txn().unwrap();
@ -706,8 +703,7 @@ mod tests {
documents.push(document);
}
let documents = documents_batch_reader_from_objects(documents);
let documents = mmap_from_objects(documents);
index.add_documents(documents).unwrap();
let txn = index.read_txn().unwrap();
@ -758,8 +754,7 @@ mod tests {
documents.push(document);
}
let documents = documents_batch_reader_from_objects(documents);
let documents = mmap_from_objects(documents);
index.add_documents(documents).unwrap();
let txn = index.read_txn().unwrap();
@ -814,8 +809,7 @@ mod tests {
documents.push(document);
}
let documents = documents_batch_reader_from_objects(documents);
let documents = mmap_from_objects(documents);
index.add_documents(documents).unwrap();
let txn = index.read_txn().unwrap();

View file

@ -1,11 +1,16 @@
use std::io::Cursor;
use std::io::Write;
use big_s::S;
use bumpalo::Bump;
use heed::EnvOpenOptions;
use maplit::{btreemap, hashset};
use crate::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
use crate::update::{IndexDocuments, IndexDocumentsConfig, IndexerConfig, Settings};
use crate::update::new::indexer;
use crate::update::{
IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings,
};
use crate::vector::EmbeddingConfigs;
use crate::{db_snap, Criterion, Index, Object};
pub const CONTENT: &str = include_str!("../../../../tests/assets/test_set.ndjson");
@ -16,6 +21,7 @@ pub fn setup_search_index_with_criteria(criteria: &[Criterion]) -> Index {
let index = Index::new(options, &path).unwrap();
let mut wtxn = index.write_txn().unwrap();
let rtxn = index.read_txn().unwrap();
let config = IndexerConfig::default();
let mut builder = Settings::new(&mut wtxn, &index, &config);
@ -43,27 +49,41 @@ pub fn setup_search_index_with_criteria(criteria: &[Criterion]) -> Index {
// index documents
let config = IndexerConfig { max_memory: Some(10 * 1024 * 1024), ..Default::default() };
let indexing_config = IndexDocumentsConfig::default();
let builder =
IndexDocuments::new(&mut wtxn, &index, &config, indexing_config, |_| (), || false).unwrap();
let mut documents_builder = DocumentsBatchBuilder::new(Vec::new());
let reader = Cursor::new(CONTENT.as_bytes());
let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
let mut new_fields_ids_map = db_fields_ids_map.clone();
for result in serde_json::Deserializer::from_reader(reader).into_iter::<Object>() {
let object = result.unwrap();
documents_builder.append_json_object(&object).unwrap();
}
let embedders = EmbeddingConfigs::default();
let mut indexer = indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
let vector = documents_builder.into_inner().unwrap();
let mut file = tempfile::tempfile().unwrap();
file.write_all(CONTENT.as_bytes()).unwrap();
file.sync_all().unwrap();
let payload = unsafe { memmap2::Mmap::map(&file).unwrap() };
// index documents
let content = DocumentsBatchReader::from_reader(Cursor::new(vector)).unwrap();
let (builder, user_error) = builder.add_documents(content).unwrap();
user_error.unwrap();
builder.execute().unwrap();
indexer.add_documents(&payload).unwrap();
let indexer_alloc = Bump::new();
let (document_changes, _operation_stats, primary_key) =
indexer.into_changes(&indexer_alloc, &index, &rtxn, None, &mut new_fields_ids_map).unwrap();
indexer::index(
&mut wtxn,
&index,
config.grenad_parameters(),
&db_fields_ids_map,
new_fields_ids_map,
primary_key,
&document_changes,
embedders,
&|| false,
&|_| (),
)
.unwrap();
wtxn.commit().unwrap();
drop(rtxn);
index
}