mirror of
https://github.com/meilisearch/meilisearch.git
synced 2025-11-30 01:35:36 +00:00
Compare commits
7 Commits
v1.1.0-rc.
...
prototype-
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a94e78ffb0 | ||
|
|
950f73b8bb | ||
|
|
e7153e0a97 | ||
|
|
37a24a4a05 | ||
|
|
6592746337 | ||
|
|
efea1e5837 | ||
|
|
b744f33530 |
@@ -311,18 +311,9 @@ impl BatchKind {
|
||||
})
|
||||
}
|
||||
(
|
||||
BatchKind::DocumentOperation { method, allow_index_creation, primary_key, mut operation_ids },
|
||||
this @ BatchKind::DocumentOperation { .. },
|
||||
K::DocumentDeletion,
|
||||
) => {
|
||||
operation_ids.push(id);
|
||||
|
||||
Continue(BatchKind::DocumentOperation {
|
||||
method,
|
||||
allow_index_creation,
|
||||
primary_key,
|
||||
operation_ids,
|
||||
})
|
||||
}
|
||||
) => Break(this),
|
||||
// but we can't autobatch documents if it's not the same kind
|
||||
// this match branch MUST be AFTER the previous one
|
||||
(
|
||||
@@ -345,35 +336,7 @@ impl BatchKind {
|
||||
deletion_ids.push(id);
|
||||
Continue(BatchKind::DocumentClear { ids: deletion_ids })
|
||||
}
|
||||
// we can autobatch the deletion and import if the index already exists
|
||||
(
|
||||
BatchKind::DocumentDeletion { mut deletion_ids },
|
||||
K::DocumentImport { method, allow_index_creation, primary_key }
|
||||
) if index_already_exists => {
|
||||
deletion_ids.push(id);
|
||||
|
||||
Continue(BatchKind::DocumentOperation {
|
||||
method,
|
||||
allow_index_creation,
|
||||
primary_key,
|
||||
operation_ids: deletion_ids,
|
||||
})
|
||||
}
|
||||
// we can autobatch the deletion and import if both can't create an index
|
||||
(
|
||||
BatchKind::DocumentDeletion { mut deletion_ids },
|
||||
K::DocumentImport { method, allow_index_creation, primary_key }
|
||||
) if !allow_index_creation => {
|
||||
deletion_ids.push(id);
|
||||
|
||||
Continue(BatchKind::DocumentOperation {
|
||||
method,
|
||||
allow_index_creation,
|
||||
primary_key,
|
||||
operation_ids: deletion_ids,
|
||||
})
|
||||
}
|
||||
// we can't autobatch a deletion and an import if the index does not exists but would be created by an addition
|
||||
// we can't autobatch a deletion and an import
|
||||
(
|
||||
this @ BatchKind::DocumentDeletion { .. },
|
||||
K::DocumentImport { .. }
|
||||
@@ -674,36 +637,36 @@ mod tests {
|
||||
debug_snapshot!(autobatch_from(false,None, [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(false,None, [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false))");
|
||||
|
||||
// We can autobatch document addition with document deletion
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
|
||||
// And the other way around
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
|
||||
// We can't autobatch document addition with document deletion
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
|
||||
// we also can't do the only way around
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -1869,105 +1869,6 @@ mod tests {
|
||||
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "both_task_succeeded");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn document_addition_and_document_deletion() {
|
||||
let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
|
||||
|
||||
let content = r#"[
|
||||
{ "id": 1, "doggo": "jean bob" },
|
||||
{ "id": 2, "catto": "jorts" },
|
||||
{ "id": 3, "doggo": "bork" }
|
||||
]"#;
|
||||
|
||||
let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap();
|
||||
let documents_count = read_json(content.as_bytes(), file.as_file_mut()).unwrap();
|
||||
file.persist().unwrap();
|
||||
index_scheduler
|
||||
.register(KindWithContent::DocumentAdditionOrUpdate {
|
||||
index_uid: S("doggos"),
|
||||
primary_key: Some(S("id")),
|
||||
method: ReplaceDocuments,
|
||||
content_file: uuid,
|
||||
documents_count,
|
||||
allow_index_creation: true,
|
||||
})
|
||||
.unwrap();
|
||||
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_first_task");
|
||||
index_scheduler
|
||||
.register(KindWithContent::DocumentDeletion {
|
||||
index_uid: S("doggos"),
|
||||
documents_ids: vec![S("1"), S("2")],
|
||||
})
|
||||
.unwrap();
|
||||
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_second_task");
|
||||
|
||||
handle.advance_one_successful_batch(); // The addition AND deletion should've been batched together
|
||||
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_processing_the_batch");
|
||||
|
||||
let index = index_scheduler.index("doggos").unwrap();
|
||||
let rtxn = index.read_txn().unwrap();
|
||||
let field_ids_map = index.fields_ids_map(&rtxn).unwrap();
|
||||
let field_ids = field_ids_map.ids().collect::<Vec<_>>();
|
||||
let documents = index
|
||||
.all_documents(&rtxn)
|
||||
.unwrap()
|
||||
.map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap())
|
||||
.collect::<Vec<_>>();
|
||||
snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn document_deletion_and_document_addition() {
|
||||
let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
|
||||
index_scheduler
|
||||
.register(KindWithContent::DocumentDeletion {
|
||||
index_uid: S("doggos"),
|
||||
documents_ids: vec![S("1"), S("2")],
|
||||
})
|
||||
.unwrap();
|
||||
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_first_task");
|
||||
|
||||
let content = r#"[
|
||||
{ "id": 1, "doggo": "jean bob" },
|
||||
{ "id": 2, "catto": "jorts" },
|
||||
{ "id": 3, "doggo": "bork" }
|
||||
]"#;
|
||||
|
||||
let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap();
|
||||
let documents_count = read_json(content.as_bytes(), file.as_file_mut()).unwrap();
|
||||
file.persist().unwrap();
|
||||
index_scheduler
|
||||
.register(KindWithContent::DocumentAdditionOrUpdate {
|
||||
index_uid: S("doggos"),
|
||||
primary_key: Some(S("id")),
|
||||
method: ReplaceDocuments,
|
||||
content_file: uuid,
|
||||
documents_count,
|
||||
allow_index_creation: true,
|
||||
})
|
||||
.unwrap();
|
||||
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_second_task");
|
||||
|
||||
// The deletion should have failed because it can't create an index
|
||||
handle.advance_one_failed_batch();
|
||||
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_failing_the_deletion");
|
||||
|
||||
// The addition should works
|
||||
handle.advance_one_successful_batch();
|
||||
snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_last_successful_addition");
|
||||
|
||||
let index = index_scheduler.index("doggos").unwrap();
|
||||
let rtxn = index.read_txn().unwrap();
|
||||
let field_ids_map = index.fields_ids_map(&rtxn).unwrap();
|
||||
let field_ids = field_ids_map.ids().collect::<Vec<_>>();
|
||||
let documents = index
|
||||
.all_documents(&rtxn)
|
||||
.unwrap()
|
||||
.map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap())
|
||||
.collect::<Vec<_>>();
|
||||
snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn do_not_batch_task_of_different_indexes() {
|
||||
let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
|
||||
|
||||
@@ -115,5 +115,5 @@ japanese = ["meilisearch-types/japanese"]
|
||||
thai = ["meilisearch-types/thai"]
|
||||
|
||||
[package.metadata.mini-dashboard]
|
||||
assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.6/build.zip"
|
||||
sha1 = "dce0aba16bceab5549edf9f01de89858800f7422"
|
||||
assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.7/build.zip"
|
||||
sha1 = "28b45bf772c84f9a6e16bc1689b393bfce8da7d6"
|
||||
|
||||
@@ -14,7 +14,7 @@ async fn formatted_contain_wildcard() {
|
||||
index.add_documents(documents, None).await;
|
||||
index.wait_task(1).await;
|
||||
|
||||
index.search(json!({ "q": "pesti", "attributesToRetrieve": ["father", "mother"], "attributesToHighlight": ["father", "mother", "*"], "attributesToCrop": ["doggos"], "showMatchesPosition": true }),
|
||||
index.search(json!({ "q": "pésti", "attributesToRetrieve": ["father", "mother"], "attributesToHighlight": ["father", "mother", "*"], "attributesToCrop": ["doggos"], "showMatchesPosition": true }),
|
||||
|response, code|
|
||||
{
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
@@ -23,7 +23,7 @@ async fn formatted_contain_wildcard() {
|
||||
json!({
|
||||
"_formatted": {
|
||||
"id": "852",
|
||||
"cattos": "<em>pesti</em>",
|
||||
"cattos": "<em>pésti</em>",
|
||||
},
|
||||
"_matchesPosition": {"cattos": [{"start": 0, "length": 5}]},
|
||||
})
|
||||
@@ -33,13 +33,13 @@ async fn formatted_contain_wildcard() {
|
||||
.await;
|
||||
|
||||
index
|
||||
.search(json!({ "q": "pesti", "attributesToRetrieve": ["*"] }), |response, code| {
|
||||
.search(json!({ "q": "pésti", "attributesToRetrieve": ["*"] }), |response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(
|
||||
response["hits"][0],
|
||||
json!({
|
||||
"id": 852,
|
||||
"cattos": "pesti",
|
||||
"cattos": "pésti",
|
||||
})
|
||||
);
|
||||
})
|
||||
@@ -47,17 +47,17 @@ async fn formatted_contain_wildcard() {
|
||||
|
||||
index
|
||||
.search(
|
||||
json!({ "q": "pesti", "attributesToRetrieve": ["*"], "attributesToHighlight": ["id"], "showMatchesPosition": true }),
|
||||
json!({ "q": "pésti", "attributesToRetrieve": ["*"], "attributesToHighlight": ["id"], "showMatchesPosition": true }),
|
||||
|response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(
|
||||
response["hits"][0],
|
||||
json!({
|
||||
"id": 852,
|
||||
"cattos": "pesti",
|
||||
"cattos": "pésti",
|
||||
"_formatted": {
|
||||
"id": "852",
|
||||
"cattos": "pesti",
|
||||
"cattos": "pésti",
|
||||
},
|
||||
"_matchesPosition": {"cattos": [{"start": 0, "length": 5}]},
|
||||
})
|
||||
@@ -68,17 +68,17 @@ async fn formatted_contain_wildcard() {
|
||||
|
||||
index
|
||||
.search(
|
||||
json!({ "q": "pesti", "attributesToRetrieve": ["*"], "attributesToCrop": ["*"] }),
|
||||
json!({ "q": "pésti", "attributesToRetrieve": ["*"], "attributesToCrop": ["*"] }),
|
||||
|response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(
|
||||
response["hits"][0],
|
||||
json!({
|
||||
"id": 852,
|
||||
"cattos": "pesti",
|
||||
"cattos": "pésti",
|
||||
"_formatted": {
|
||||
"id": "852",
|
||||
"cattos": "pesti",
|
||||
"cattos": "pésti",
|
||||
}
|
||||
})
|
||||
);
|
||||
@@ -87,16 +87,16 @@ async fn formatted_contain_wildcard() {
|
||||
.await;
|
||||
|
||||
index
|
||||
.search(json!({ "q": "pesti", "attributesToCrop": ["*"] }), |response, code| {
|
||||
.search(json!({ "q": "pésti", "attributesToCrop": ["*"] }), |response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(
|
||||
response["hits"][0],
|
||||
json!({
|
||||
"id": 852,
|
||||
"cattos": "pesti",
|
||||
"cattos": "pésti",
|
||||
"_formatted": {
|
||||
"id": "852",
|
||||
"cattos": "pesti",
|
||||
"cattos": "pésti",
|
||||
}
|
||||
})
|
||||
);
|
||||
@@ -114,7 +114,7 @@ async fn format_nested() {
|
||||
index.wait_task(0).await;
|
||||
|
||||
index
|
||||
.search(json!({ "q": "pesti", "attributesToRetrieve": ["doggos"] }), |response, code| {
|
||||
.search(json!({ "q": "pésti", "attributesToRetrieve": ["doggos"] }), |response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(
|
||||
response["hits"][0],
|
||||
@@ -136,7 +136,7 @@ async fn format_nested() {
|
||||
|
||||
index
|
||||
.search(
|
||||
json!({ "q": "pesti", "attributesToRetrieve": ["doggos.name"] }),
|
||||
json!({ "q": "pésti", "attributesToRetrieve": ["doggos.name"] }),
|
||||
|response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(
|
||||
@@ -180,7 +180,7 @@ async fn format_nested() {
|
||||
.await;
|
||||
|
||||
index
|
||||
.search(json!({ "q": "pesti", "attributesToRetrieve": [], "attributesToHighlight": ["doggos.name"] }),
|
||||
.search(json!({ "q": "pésti", "attributesToRetrieve": [], "attributesToHighlight": ["doggos.name"] }),
|
||||
|response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(
|
||||
@@ -202,7 +202,7 @@ async fn format_nested() {
|
||||
.await;
|
||||
|
||||
index
|
||||
.search(json!({ "q": "pesti", "attributesToRetrieve": [], "attributesToCrop": ["doggos.name"] }),
|
||||
.search(json!({ "q": "pésti", "attributesToRetrieve": [], "attributesToCrop": ["doggos.name"] }),
|
||||
|response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(
|
||||
@@ -224,7 +224,7 @@ async fn format_nested() {
|
||||
.await;
|
||||
|
||||
index
|
||||
.search(json!({ "q": "pesti", "attributesToRetrieve": ["doggos.name"], "attributesToHighlight": ["doggos.age"] }),
|
||||
.search(json!({ "q": "pésti", "attributesToRetrieve": ["doggos.name"], "attributesToHighlight": ["doggos.age"] }),
|
||||
|response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(
|
||||
@@ -256,7 +256,7 @@ async fn format_nested() {
|
||||
.await;
|
||||
|
||||
index
|
||||
.search(json!({ "q": "pesti", "attributesToRetrieve": [], "attributesToHighlight": ["doggos.age"], "attributesToCrop": ["doggos.name"] }),
|
||||
.search(json!({ "q": "pésti", "attributesToRetrieve": [], "attributesToHighlight": ["doggos.age"], "attributesToCrop": ["doggos.name"] }),
|
||||
|response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(
|
||||
|
||||
@@ -30,7 +30,7 @@ pub(self) static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
|
||||
"id": "166428",
|
||||
},
|
||||
{
|
||||
"title": "Glass",
|
||||
"title": "Gläss",
|
||||
"id": "450465",
|
||||
}
|
||||
])
|
||||
@@ -52,7 +52,7 @@ pub(self) static NESTED_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
|
||||
"age": 4,
|
||||
},
|
||||
],
|
||||
"cattos": "pesti",
|
||||
"cattos": "pésti",
|
||||
},
|
||||
{
|
||||
"id": 654,
|
||||
@@ -142,7 +142,7 @@ async fn simple_search() {
|
||||
index.wait_task(1).await;
|
||||
|
||||
index
|
||||
.search(json!({"q": "pesti"}), |response, code| {
|
||||
.search(json!({"q": "pésti"}), |response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
assert_eq!(response["hits"].as_array().unwrap().len(), 2);
|
||||
})
|
||||
@@ -250,7 +250,7 @@ async fn search_multiple_params() {
|
||||
index
|
||||
.search(
|
||||
json!({
|
||||
"q": "pesti",
|
||||
"q": "pésti",
|
||||
"attributesToCrop": ["catto:2"],
|
||||
"attributesToHighlight": ["catto"],
|
||||
"limit": 2,
|
||||
@@ -281,7 +281,7 @@ async fn search_with_filter_string_notation() {
|
||||
index
|
||||
.search(
|
||||
json!({
|
||||
"filter": "title = Glass"
|
||||
"filter": "title = Gläss"
|
||||
}),
|
||||
|response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
@@ -305,7 +305,7 @@ async fn search_with_filter_string_notation() {
|
||||
index
|
||||
.search(
|
||||
json!({
|
||||
"filter": "cattos = pesti"
|
||||
"filter": "cattos = pésti"
|
||||
}),
|
||||
|response, code| {
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
@@ -343,7 +343,7 @@ async fn search_with_filter_array_notation() {
|
||||
|
||||
let (response, code) = index
|
||||
.search_post(json!({
|
||||
"filter": ["title = Glass"]
|
||||
"filter": ["title = Gläss"]
|
||||
}))
|
||||
.await;
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
@@ -351,7 +351,7 @@ async fn search_with_filter_array_notation() {
|
||||
|
||||
let (response, code) = index
|
||||
.search_post(json!({
|
||||
"filter": [["title = Glass", "title = \"Shazam!\"", "title = \"Escape Room\""]]
|
||||
"filter": [["title = Gläss", "title = \"Shazam!\"", "title = \"Escape Room\""]]
|
||||
}))
|
||||
.await;
|
||||
assert_eq!(code, 200, "{}", response);
|
||||
|
||||
@@ -71,7 +71,7 @@ async fn simple_search_single_index() {
|
||||
"indexUid": "test",
|
||||
"hits": [
|
||||
{
|
||||
"title": "Glass",
|
||||
"title": "Gläss",
|
||||
"id": "450465"
|
||||
}
|
||||
],
|
||||
@@ -166,7 +166,7 @@ async fn simple_search_two_indexes() {
|
||||
let (response, code) = server
|
||||
.multi_search(json!({"queries": [
|
||||
{"indexUid" : "test", "q": "glass"},
|
||||
{"indexUid": "nested", "q": "pesti"},
|
||||
{"indexUid": "nested", "q": "pésti"},
|
||||
]}))
|
||||
.await;
|
||||
snapshot!(code, @"200 OK");
|
||||
@@ -176,7 +176,7 @@ async fn simple_search_two_indexes() {
|
||||
"indexUid": "test",
|
||||
"hits": [
|
||||
{
|
||||
"title": "Glass",
|
||||
"title": "Gläss",
|
||||
"id": "450465"
|
||||
}
|
||||
],
|
||||
@@ -203,7 +203,7 @@ async fn simple_search_two_indexes() {
|
||||
"age": 4
|
||||
}
|
||||
],
|
||||
"cattos": "pesti"
|
||||
"cattos": "pésti"
|
||||
},
|
||||
{
|
||||
"id": 654,
|
||||
@@ -221,7 +221,7 @@ async fn simple_search_two_indexes() {
|
||||
]
|
||||
}
|
||||
],
|
||||
"query": "pesti",
|
||||
"query": "pésti",
|
||||
"processingTimeMs": "[time]",
|
||||
"limit": 20,
|
||||
"offset": 0,
|
||||
@@ -243,7 +243,7 @@ async fn search_one_index_doesnt_exist() {
|
||||
let (response, code) = server
|
||||
.multi_search(json!({"queries": [
|
||||
{"indexUid" : "test", "q": "glass"},
|
||||
{"indexUid": "nested", "q": "pesti"},
|
||||
{"indexUid": "nested", "q": "pésti"},
|
||||
]}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
@@ -264,7 +264,7 @@ async fn search_multiple_indexes_dont_exist() {
|
||||
let (response, code) = server
|
||||
.multi_search(json!({"queries": [
|
||||
{"indexUid" : "test", "q": "glass"},
|
||||
{"indexUid": "nested", "q": "pesti"},
|
||||
{"indexUid": "nested", "q": "pésti"},
|
||||
]}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
@@ -296,7 +296,7 @@ async fn search_one_query_error() {
|
||||
let (response, code) = server
|
||||
.multi_search(json!({"queries": [
|
||||
{"indexUid" : "test", "q": "glass", "facets": ["title"]},
|
||||
{"indexUid": "nested", "q": "pesti"},
|
||||
{"indexUid": "nested", "q": "pésti"},
|
||||
]}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
@@ -328,7 +328,7 @@ async fn search_multiple_query_errors() {
|
||||
let (response, code) = server
|
||||
.multi_search(json!({"queries": [
|
||||
{"indexUid" : "test", "q": "glass", "facets": ["title"]},
|
||||
{"indexUid": "nested", "q": "pesti", "facets": ["doggos"]},
|
||||
{"indexUid": "nested", "q": "pésti", "facets": ["doggos"]},
|
||||
]}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
|
||||
@@ -22,6 +22,7 @@ use std::collections::{BTreeMap, HashMap};
|
||||
use std::convert::{TryFrom, TryInto};
|
||||
use std::hash::BuildHasherDefault;
|
||||
|
||||
use charabia::normalizer::{CharNormalizer, CompatibilityDecompositionNormalizer};
|
||||
pub use filter_parser::{Condition, FilterCondition, Span, Token};
|
||||
use fxhash::{FxHasher32, FxHasher64};
|
||||
pub use grenad::CompressionType;
|
||||
@@ -252,6 +253,10 @@ pub fn is_faceted_by(field: &str, facet: &str) -> bool {
|
||||
&& field[facet.len()..].chars().next().map(|c| c == '.').unwrap_or(true)
|
||||
}
|
||||
|
||||
pub fn normalize_facet(original: &str) -> String {
|
||||
CompatibilityDecompositionNormalizer.normalize_str(original.trim()).to_lowercase()
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use serde_json::json;
|
||||
|
||||
@@ -230,7 +230,7 @@ impl<'a> Filter<'a> {
|
||||
&FacetGroupKey {
|
||||
field_id,
|
||||
level: 0,
|
||||
left_bound: &val.value().to_lowercase(),
|
||||
left_bound: &crate::normalize_facet(val.value()),
|
||||
},
|
||||
)?
|
||||
.map(|v| v.bitmap)
|
||||
|
||||
@@ -4,7 +4,6 @@ use std::fs::File;
|
||||
use std::io;
|
||||
use std::mem::size_of;
|
||||
|
||||
use charabia::normalizer::{CharNormalizer, CompatibilityDecompositionNormalizer};
|
||||
use heed::zerocopy::AsBytes;
|
||||
use heed::BytesEncode;
|
||||
use roaring::RoaringBitmap;
|
||||
@@ -136,9 +135,7 @@ fn extract_facet_values(value: &Value) -> (Vec<f64>, Vec<(String, String)>) {
|
||||
}
|
||||
}
|
||||
Value::String(original) => {
|
||||
let normalized = CompatibilityDecompositionNormalizer
|
||||
.normalize_str(original.trim())
|
||||
.to_lowercase();
|
||||
let normalized = crate::normalize_facet(original);
|
||||
output_strings.push((normalized, original.clone()));
|
||||
}
|
||||
Value::Array(values) => {
|
||||
|
||||
Reference in New Issue
Block a user