From ad03c86c4493cb1dec38897983bd0a4d6ec21631 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20Renault?= <clement@meilisearch.com>
Date: Mon, 30 Jun 2025 18:46:47 +0200
Subject: [PATCH] Display an accurate number of uploaded documents

---
 .../src/scheduler/process_batch.rs            | 10 +++++----
 .../src/scheduler/process_export.rs           | 21 +++++++++++++------
 crates/meilisearch-types/src/tasks.rs         |  8 +++----
 3 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/crates/index-scheduler/src/scheduler/process_batch.rs b/crates/index-scheduler/src/scheduler/process_batch.rs
index e56b8e13a..090ff844d 100644
--- a/crates/index-scheduler/src/scheduler/process_batch.rs
+++ b/crates/index-scheduler/src/scheduler/process_batch.rs
@@ -377,9 +377,8 @@ impl IndexScheduler {
                     )
                 }));
 
-                match ret {
-                    // TODO return the matched and exported documents
-                    Ok(Ok(())) => (),
+                let stats = match ret {
+                    Ok(Ok(stats)) => stats,
                     Ok(Err(Error::AbortedTask)) => return Err(Error::AbortedTask),
                     Ok(Err(e)) => return Err(Error::Export(Box::new(e))),
                     Err(e) => {
@@ -394,9 +393,12 @@ impl IndexScheduler {
                             msg.to_string(),
                         ))));
                     }
-                }
+                };
 
                 task.status = Status::Succeeded;
+                if let Some(Details::Export { indexes, .. }) = task.details.as_mut() {
+                    *indexes = stats;
+                }
                 Ok((vec![task], ProcessBatchInfo::default()))
             }
             Batch::UpgradeDatabase { mut tasks } => {
diff --git a/crates/index-scheduler/src/scheduler/process_export.rs b/crates/index-scheduler/src/scheduler/process_export.rs
index b81ff0b96..bf2917b73 100644
--- a/crates/index-scheduler/src/scheduler/process_export.rs
+++ b/crates/index-scheduler/src/scheduler/process_export.rs
@@ -14,7 +14,7 @@ use meilisearch_types::milli::update::{request_threads, Setting};
 use meilisearch_types::milli::vector::parsed_vectors::{ExplicitVectors, VectorOrArrayOfVectors};
 use meilisearch_types::milli::{self, obkv_to_json, Filter, InternalError};
 use meilisearch_types::settings::{self, SecretPolicy};
-use meilisearch_types::tasks::ExportIndexSettings;
+use meilisearch_types::tasks::{DetailsExportIndexSettings, ExportIndexSettings};
 use serde::Deserialize;
 use ureq::{json, Response};
 
@@ -30,7 +30,7 @@ impl IndexScheduler {
         payload_size: Option<&Byte>,
         indexes: &BTreeMap<IndexUidPattern, ExportIndexSettings>,
         progress: Progress,
-    ) -> Result<()> {
+    ) -> Result<BTreeMap<IndexUidPattern, DetailsExportIndexSettings>> {
         #[cfg(test)]
         self.maybe_fail(crate::test_utils::FailureLocation::ProcessExport)?;
 
@@ -41,13 +41,14 @@ impl IndexScheduler {
                 indexes
                     .iter()
                     .find(|(pattern, _)| pattern.matches_str(&uid))
-                    .map(|(_pattern, settings)| (uid, settings))
+                    .map(|(pattern, settings)| (pattern, uid, settings))
             })
             .collect();
 
+        let mut output = BTreeMap::new();
         let agent = ureq::AgentBuilder::new().timeout(Duration::from_secs(5)).build();
         let must_stop_processing = self.scheduler.must_stop_processing.clone();
-        for (i, (uid, settings)) in indexes.iter().enumerate() {
+        for (i, (pattern, uid, export_settings)) in indexes.iter().enumerate() {
             if must_stop_processing.get() {
                 return Err(Error::AbortedTask);
             }
@@ -58,7 +59,7 @@ impl IndexScheduler {
                 indexes.len() as u32,
             ));
 
-            let ExportIndexSettings { filter } = settings;
+            let ExportIndexSettings { filter } = export_settings;
             let index = self.index(uid)?;
             let index_rtxn = index.read_txn()?;
 
@@ -125,6 +126,14 @@ impl IndexScheduler {
             let (step, progress_step) = AtomicDocumentStep::new(total_documents);
             progress.update_progress(progress_step);
 
+            output.insert(
+                (*pattern).clone(),
+                DetailsExportIndexSettings {
+                    settings: (*export_settings).clone(),
+                    matched_documents: Some(total_documents as u64),
+                },
+            );
+
             let limit = payload_size.map(|ps| ps.as_u64() as usize).unwrap_or(50 * 1024 * 1024); // defaults to 50 MiB
             let documents_url = format!("{base_url}/indexes/{uid}/documents");
 
@@ -265,7 +274,7 @@ impl IndexScheduler {
             step.store(total_documents, atomic::Ordering::Relaxed);
         }
 
-        Ok(())
+        Ok(output)
     }
 }
 
diff --git a/crates/meilisearch-types/src/tasks.rs b/crates/meilisearch-types/src/tasks.rs
index a6ed593db..cdbf6d3aa 100644
--- a/crates/meilisearch-types/src/tasks.rs
+++ b/crates/meilisearch-types/src/tasks.rs
@@ -707,16 +707,14 @@ pub enum Details {
 #[schema(rename_all = "camelCase")]
 pub struct DetailsExportIndexSettings {
     #[serde(flatten)]
-    settings: ExportIndexSettings,
+    pub settings: ExportIndexSettings,
     #[serde(skip_serializing_if = "Option::is_none")]
-    matched_documents: Option<u64>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    exported_documents: Option<u64>,
+    pub matched_documents: Option<u64>,
 }
 
 impl From<ExportIndexSettings> for DetailsExportIndexSettings {
     fn from(settings: ExportIndexSettings) -> Self {
-        DetailsExportIndexSettings { settings, matched_documents: None, exported_documents: None }
+        DetailsExportIndexSettings { settings, matched_documents: None }
     }
 }