Merge #3012

3012: Extract the dates out of the dumpv4. r=irevoire a=funilrys

Hi there, 

please review this PR that tries to fix #2987. I'm still learning Rust and I found that #2987 is an excellent way for me to read and learn what others do with Rust. So please excuse my semantics ...

Stay safe and healthy.

---

# Pull Request

This patch possibly fixes #2987.

This patch introduces a way to fill the IndexMetadata.created_at and IndexMetadata.updated_at keys from the tasks events. This is done by reading the creation date of the first event (created_at) and the creation date of the last event (updated_at).


## Related issue
Fixes #2987

## What does this PR do?
- Extract the dates out of the dumpv4.

## PR checklist
Please check if your PR fulfills the following requirements:
- [x] Does this PR fix an existing issue, or have you listed the changes applied in the PR description (and why they are needed)?
- [x] Have you read the contributing guidelines?
- [x] Have you made sure that the title is accurate and descriptive of the changes?

Thank you so much for contributing to Meilisearch!


Co-authored-by: funilrys <contact@funilrys.com>

dump/src/reader/v4/mod.rs

@@ -13,7 +13,7 @@ pub mod meta;
 pub mod settings;
 pub mod tasks;
 
-use self::meta::{DumpMeta, IndexUuid};
+use self::meta::{DumpMeta, IndexMeta, IndexUuid};
 use super::compat::v4_to_v5::CompatV4ToV5;
 use crate::{Error, IndexMetadata, Result, Version};
 
@@ -100,6 +100,10 @@ impl V4Reader {
             V4IndexReader::new(
                 index.uid.clone(),
                 &self.dump.path().join("indexes").join(index.index_meta.uuid.to_string()),
+                &index.index_meta,
+                BufReader::new(
+                    File::open(&self.dump.path().join("updates").join("data.jsonl")).unwrap(),
+                ),
             )
         }))
     }
@@ -147,16 +151,43 @@ pub struct V4IndexReader {
 }
 
 impl V4IndexReader {
-    pub fn new(name: String, path: &Path) -> Result<Self> {
+    pub fn new(
+        name: String,
+        path: &Path,
+        index_metadata: &IndexMeta,
+        tasks: BufReader<File>,
+    ) -> Result<Self> {
         let meta = File::open(path.join("meta.json"))?;
         let meta: DumpMeta = serde_json::from_reader(meta)?;
 
+        let mut created_at = None;
+        let mut updated_at = None;
+
+        for line in tasks.lines() {
+            let task: Task = serde_json::from_str(&line?)?;
+
+            if task.index_uid.to_string() == name {
+                if updated_at.is_none() {
+                    updated_at = task.updated_at()
+                }
+
+                if created_at.is_none() {
+                    created_at = task.created_at()
+                }
+
+                if task.id as usize == index_metadata.creation_task_id {
+                    created_at = task.processed_at();
+
+                    break;
+                }
+            }
+        }
+
         let metadata = IndexMetadata {
             uid: name,
             primary_key: meta.primary_key,
-            // FIXME: Iterate over the whole task queue to find the creation and last update date.
-            created_at: OffsetDateTime::now_utc(),
-            updated_at: OffsetDateTime::now_utc(),
+            created_at: created_at.unwrap_or_else(OffsetDateTime::now_utc),
+            updated_at: updated_at.unwrap_or_else(OffsetDateTime::now_utc),
         };
 
         let ret = V4IndexReader {

dump/src/reader/v4/tasks.rs

@@ -104,6 +104,48 @@ impl Task {
         })
     }
 
+    pub fn processed_at(&self) -> Option<OffsetDateTime> {
+        match self.events.last() {
+            Some(TaskEvent::Succeded { result: _, timestamp }) => Some(*timestamp),
+            _ => None,
+        }
+    }
+
+    pub fn updated_at(&self) -> Option<OffsetDateTime> {
+        match self.events.last() {
+            Some(TaskEvent::Created(ts)) => Some(*ts),
+            _ => None,
+        }
+    }
+
+    pub fn created_at(&self) -> Option<OffsetDateTime> {
+        match &self.content {
+            TaskContent::IndexCreation { primary_key: _ } => match self.events.first() {
+                Some(TaskEvent::Created(ts)) => Some(*ts),
+                _ => None,
+            },
+            TaskContent::DocumentAddition {
+                content_uuid: _,
+                merge_strategy: _,
+                primary_key: _,
+                documents_count: _,
+                allow_index_creation: _,
+            } => match self.events.first() {
+                Some(TaskEvent::Created(ts)) => Some(*ts),
+                _ => None,
+            },
+            TaskContent::SettingsUpdate {
+                settings: _,
+                is_deletion: _,
+                allow_index_creation: _,
+            } => match self.events.first() {
+                Some(TaskEvent::Created(ts)) => Some(*ts),
+                _ => None,
+            },
+            _ => None,
+        }
+    }
+
     /// Return the content_uuid of the `Task` if there is one.
     pub fn get_content_uuid(&self) -> Option<Uuid> {
         match self {