Skip to content

fix: MongoDB ifNoneExist search correctness #917

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bomanaps wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: MongoDB ifNoneExist search correctness #917

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3ea30f3
fix: MongoDB ifNoneExist search correctness
bomanaps Sep 2, 2026
bc07bdf
fix mongodb ifNoneExist search
bomanaps Sep 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions crates/persistence/src/backends/mongodb/search_impl.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -807,7 +807,7 @@ impl MongoBackend {
Ok(Some(ids))
}

fn build_search_index_filter(
pub(super) fn build_search_index_filter(
&self,
tenant_id: &str,
resource_type: &str,
Expand Down Expand Up @@ -1171,7 +1171,7 @@ impl MongoBackend {
}
}

fn build_resource_filter(
pub(super) fn build_resource_filter(
&self,
tenant_id: &str,
resource_type: &str,
Expand Down Expand Up @@ -1423,7 +1423,7 @@ impl MongoBackend {
Ok(result.resources.items)
}

fn build_search_parameters(
pub(super) fn build_search_parameters(
&self,
tenant: &TenantContext,
resource_type: &str,
Expand Down
271 changes: 155 additions & 116 deletions crates/persistence/src/backends/mongodb/storage.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
//! ResourceStorage implementation for MongoDB.

use std::collections::HashMap;
use std::collections::{HashMap, HashSet};

use async_trait::async_trait;
use chrono::{DateTime, Utc};
Expand Down Expand Up @@ -28,7 +28,7 @@ use crate::search::converters::IndexValue;
use crate::search::extractor::ExtractedValue;
use crate::search::reindex::{ReindexSource, ReindexTarget, ResourcePage};
use crate::tenant::{Operation, TenantContext};
use crate::types::{CursorValue, Page, PageCursor, PageInfo, StoredResource};
use crate::types::{CursorValue, Page, PageCursor, PageInfo, SearchQuery, StoredResource};

use super::MongoBackend;

Expand Down Expand Up @@ -3328,47 +3328,173 @@ impl MongoBackend {
return Ok(Vec::new());
}

let resources = db.collection::<Document>(MongoBackend::RESOURCES_COLLECTION);
if self.is_search_offloaded() {
return self
.if_none_exist_offloaded_scan(db, session, tenant, resource_type, &parsed_params)
.await;
}

let typed_params = self.build_search_parameters(tenant, resource_type, &parsed_params);
let query = SearchQuery {
resource_type: resource_type.to_string(),
parameters: typed_params,
count: Some(2),
..Default::default()
};

let tenant_id = tenant.tenant_id().as_str();
let search_index = db.collection::<Document>(MongoBackend::SEARCH_INDEX_COLLECTION);
let mut matched_ids: Option<HashSet<String>> = None;

for param in &query.parameters {
if matches!(param.name.as_str(), "_id" | "_lastUpdated") {
continue;
}

let filter = self.build_search_index_filter(tenant_id, resource_type, param)?;
let pipeline = vec![
doc! { "$match": filter },
doc! { "$group": { "_id": "$resource_id" } },
doc! { "$limit": 1001_i32 },
];
let cursor = search_index
.aggregate(pipeline)
.session(&mut *session)
.await
.map_err(|e| {
internal_error(format!(
"Failed to query search_index in transaction: {}",
e
))
})?;
let docs = collect_session_documents(cursor, session).await?;

if docs.len() > 1000 {
tracing::warn!(
resource_type,
param_name = %param.name,
"ifNoneExist criteria match more than 1000 search_index entries; \
intersection may be incomplete for this parameter"
);
}

let ids: HashSet<String> = docs
.into_iter()
.filter_map(|d| d.get_str("_id").ok().map(str::to_string))
.collect();

if ids.is_empty() {
return Ok(Vec::new());
}

matched_ids = Some(match matched_ids {
Some(current) => current.intersection(&ids).cloned().collect(),
None => ids,
});

if matched_ids.as_ref().is_some_and(|s| s.is_empty()) {
return Ok(Vec::new());
}
}

let candidate_ids: Option<HashSet<String>> =
matched_ids.map(|ids| ids.into_iter().take(2).collect());

let filter = self.build_resource_filter(
tenant_id,
resource_type,
&query,
candidate_ids.as_ref(),
None,
)?;

let resources = db.collection::<Document>(MongoBackend::RESOURCES_COLLECTION);
let cursor = resources
.find(doc! {
"tenant_id": tenant_id,
"resource_type": resource_type,
"is_deleted": false,
})
.find(filter)
.limit(2)
.session(&mut *session)
.await
.map_err(|e| {
internal_error(format!(
"Failed to query conditional matches in transaction: {}",
e
))
internal_error(format!("Failed to query resources in transaction: {}", e))
})?;

let docs = collect_session_documents(cursor, session).await?;
let mut matches = Vec::new();

for doc in docs {
let payload = doc.get_document("data").map_err(|e| {
docs.into_iter()
.map(|doc| document_to_stored_resource(&doc, tenant, resource_type))
.collect()
}

async fn if_none_exist_offloaded_scan(
&self,
db: &mongodb::Database,
session: &mut ClientSession,
tenant: &TenantContext,
resource_type: &str,
parsed_params: &[(String, String)],
) -> StorageResult<Vec<StoredResource>> {
let tenant_id = tenant.tenant_id().as_str();
let mut conditions = vec![doc! {
"tenant_id": tenant_id,
"resource_type": resource_type,
"is_deleted": false,
}];

for (name, value) in parsed_params {
match name.as_str() {
"_id" => {
conditions.push(doc! { "id": value.as_str() });
}
"identifier" => {
let mut elem_match = Document::new();
if let Some((system, val)) = value.split_once('|') {
if !system.is_empty() {
elem_match.insert("system", system);
}
if !val.is_empty() {
elem_match.insert("value", val);
}
} else if !value.is_empty() {
elem_match.insert("value", value.as_str());
}
if !elem_match.is_empty() {
conditions.push(doc! { "data.identifier": { "$elemMatch": elem_match } });
}
}
_ => {
tracing::warn!(
resource_type,
param_name = %name,
"ifNoneExist with offloaded search: param cannot be evaluated \
against the resource collection directly; matches may include \
false positives"
);
}
}
}

let filter = if conditions.len() == 1 {
conditions.remove(0)
} else {
doc! { "$and": Bson::Array(conditions.into_iter().map(Bson::Document).collect()) }
};

let resources = db.collection::<Document>(MongoBackend::RESOURCES_COLLECTION);
let cursor = resources
.find(filter)
.limit(2)
.session(&mut *session)
.await
.map_err(|e| {
internal_error(format!(
"Missing payload while matching conditionals: {}",
"Failed to scan resources for offloaded ifNoneExist: {}",
e
))
})?;
let resource = document_to_value(payload)?;

if resource_matches_bundle_search_params(&resource, &parsed_params)
&& doc
.get_str("resource_type")
.map(|rt| rt == resource_type)
.unwrap_or(true)
{
matches.push(document_to_stored_resource(&doc, tenant, resource_type)?);
}
}
let docs = collect_session_documents(cursor, session).await?;

Ok(matches)
docs.into_iter()
.map(|doc| document_to_stored_resource(&doc, tenant, resource_type))
.collect()
}

async fn index_resource_in_bundle_transaction(
Expand Down Expand Up @@ -3494,93 +3620,6 @@ impl MongoBackend {
}
}

fn resource_matches_bundle_search_params(resource: &Value, params: &[(String, String)]) -> bool {
params.iter().all(|(name, expected)| match name.as_str() {
"_id" => resource
.get("id")
.and_then(Value::as_str)
.is_some_and(|id| id == expected),
"identifier" => resource_identifier_matches(resource, expected),
_ => resource_field_matches(resource.get(name), expected),
})
}

fn resource_identifier_matches(resource: &Value, expected: &str) -> bool {
let Some(identifier_value) = resource.get("identifier") else {
return false;
};

let (system, value, has_separator) = if let Some((system, value)) = expected.split_once('|') {
(system, value, true)
} else {
("", expected, false)
};

match identifier_value {
Value::Array(items) => items
.iter()
.any(|item| match_identifier_item(item, system, value, has_separator)),
Value::Object(_) => match_identifier_item(identifier_value, system, value, has_separator),
_ => false,
}
}

fn match_identifier_item(item: &Value, system: &str, value: &str, has_separator: bool) -> bool {
let item_system = item.get("system").and_then(Value::as_str);
let item_value = item.get("value").and_then(Value::as_str);

if has_separator {
let system_matches = if system.is_empty() {
true
} else {
item_system == Some(system)
};
let value_matches = if value.is_empty() {
true
} else {
item_value == Some(value)
};

system_matches && value_matches
} else {
item_value == Some(value)
}
}

fn resource_field_matches(value: Option<&Value>, expected: &str) -> bool {
let Some(value) = value else {
return false;
};

match value {
Value::String(s) => s == expected,
Value::Array(items) => items
.iter()
.any(|item| resource_field_matches(Some(item), expected)),
Value::Object(map) => {
if map
.get("reference")
.and_then(Value::as_str)
.is_some_and(|reference| reference == expected)
{
return true;
}

if map
.get("value")
.and_then(Value::as_str)
.is_some_and(|value| value == expected)
{
return true;
}

map.values()
.any(|nested| resource_field_matches(Some(nested), expected))
}
_ => false,
}
}

// ============================================================================
// PurgableStorage
//
Expand Down
Loading