Move crates under a sub folder to clean up the code

crates/dump/src/reader/v2/errors.rs

@@ -0,0 +1,14 @@
+use http::StatusCode;
+use serde::Deserialize;
+
+#[derive(Debug, Deserialize, Clone)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(rename_all = "camelCase")]
+pub struct ResponseError {
+    #[serde(skip)]
+    pub code: StatusCode,
+    pub message: String,
+    pub error_code: String,
+    pub error_type: String,
+    pub error_link: String,
+}

crates/dump/src/reader/v2/meta.rs

@@ -0,0 +1,18 @@
+use serde::Deserialize;
+use uuid::Uuid;
+
+use super::Settings;
+
+#[derive(Deserialize, Debug, Clone)]
+#[cfg_attr(test, derive(serde::Serialize))]
+pub struct IndexUuid {
+    pub uid: String,
+    pub uuid: Uuid,
+}
+
+#[derive(Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+pub struct DumpMeta {
+    pub settings: Settings<super::Unchecked>,
+    pub primary_key: Option<String>,
+}

crates/dump/src/reader/v2/mod.rs

@@ -0,0 +1,416 @@
+//! ```text
+//! .
+//! ├── indexes
+//! │   ├── index-40d14c5f-37ae-4873-9d51-b69e014a0d30
+//! │   │   ├── documents.jsonl
+//! │   │   └── meta.json
+//! │   ├── index-88202369-4524-4410-9b3d-3e924c867fec
+//! │   │   ├── documents.jsonl
+//! │   │   └── meta.json
+//! │   ├── index-b7f2d03b-bf9b-40d9-a25b-94dc5ec60c32
+//! │   │   ├── documents.jsonl
+//! │   │   └── meta.json
+//! │   └── index-dc9070b3-572d-4f30-ab45-d4903ab71708
+//! │       ├── documents.jsonl
+//! │       └── meta.json
+//! ├── index_uuids
+//! │   └── data.jsonl
+//! ├── metadata.json
+//! └── updates
+//!     ├── data.jsonl
+//!     └── update_files
+//!         └── update_202573df-718b-4d80-9a65-2ee397c23dc3
+//! ```
+
+use std::fs::{self, File};
+use std::io::{BufRead, BufReader};
+use std::path::Path;
+
+use serde::{Deserialize, Serialize};
+use tempfile::TempDir;
+use time::OffsetDateTime;
+
+pub mod errors;
+pub mod meta;
+pub mod settings;
+pub mod updates;
+
+use self::meta::{DumpMeta, IndexUuid};
+use super::compat::v2_to_v3::CompatV2ToV3;
+use super::Document;
+use crate::{IndexMetadata, Result, Version};
+
+pub type Settings<T> = settings::Settings<T>;
+pub type Setting<T> = settings::Setting<T>;
+pub type Checked = settings::Checked;
+pub type Unchecked = settings::Unchecked;
+
+pub type Task = updates::UpdateEntry;
+pub type Kind = updates::UpdateMeta;
+
+// everything related to the errors
+pub type ResponseError = errors::ResponseError;
+
+#[derive(Serialize, Deserialize, Debug)]
+#[serde(rename_all = "camelCase")]
+pub struct Metadata {
+    db_version: String,
+    index_db_size: usize,
+    update_db_size: usize,
+    #[serde(with = "time::serde::rfc3339")]
+    dump_date: OffsetDateTime,
+}
+
+pub struct V2Reader {
+    dump: TempDir,
+    metadata: Metadata,
+    tasks: BufReader<File>,
+    pub index_uuid: Vec<IndexUuid>,
+}
+
+impl V2Reader {
+    pub fn open(dump: TempDir) -> Result<Self> {
+        let meta_file = fs::read(dump.path().join("metadata.json"))?;
+        let metadata = serde_json::from_reader(&*meta_file)?;
+        let index_uuid = File::open(dump.path().join("index_uuids/data.jsonl"))?;
+        let index_uuid = BufReader::new(index_uuid);
+        let index_uuid = index_uuid
+            .lines()
+            .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) })
+            .collect::<Result<Vec<_>>>()?;
+
+        Ok(V2Reader {
+            metadata,
+            tasks: BufReader::new(
+                File::open(dump.path().join("updates").join("data.jsonl")).unwrap(),
+            ),
+            index_uuid,
+            dump,
+        })
+    }
+
+    pub fn to_v3(self) -> CompatV2ToV3 {
+        CompatV2ToV3::new(self)
+    }
+
+    pub fn index_uuid(&self) -> Vec<IndexUuid> {
+        self.index_uuid.clone()
+    }
+
+    pub fn version(&self) -> Version {
+        Version::V2
+    }
+
+    pub fn date(&self) -> Option<OffsetDateTime> {
+        Some(self.metadata.dump_date)
+    }
+
+    pub fn indexes(&self) -> Result<impl Iterator<Item = Result<V2IndexReader>> + '_> {
+        Ok(self.index_uuid.iter().map(|index| -> Result<_> {
+            V2IndexReader::new(
+                &self.dump.path().join("indexes").join(format!("index-{}", index.uuid)),
+                index,
+                BufReader::new(
+                    File::open(self.dump.path().join("updates").join("data.jsonl")).unwrap(),
+                ),
+            )
+        }))
+    }
+
+    pub fn tasks(&mut self) -> Box<dyn Iterator<Item = Result<(Task, Option<UpdateFile>)>> + '_> {
+        Box::new((&mut self.tasks).lines().map(|line| -> Result<_> {
+            let task: Task = serde_json::from_str(&line?)?;
+            if !task.is_finished() {
+                if let Some(uuid) = task.get_content_uuid() {
+                    let update_file_path = self
+                        .dump
+                        .path()
+                        .join("updates")
+                        .join("update_files")
+                        .join(format!("update_{}", uuid));
+                    Ok((task, Some(UpdateFile::new(&update_file_path)?)))
+                } else {
+                    Ok((task, None))
+                }
+            } else {
+                Ok((task, None))
+            }
+        }))
+    }
+}
+
+pub struct V2IndexReader {
+    metadata: IndexMetadata,
+    settings: Settings<Checked>,
+
+    documents: BufReader<File>,
+}
+
+impl V2IndexReader {
+    pub fn new(path: &Path, index_uuid: &IndexUuid, 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.uuid == index_uuid.uuid && task.is_finished()) {
+                continue;
+            }
+
+            let new_created_at = match task.update.meta() {
+                Kind::DocumentsAddition { .. } | Kind::Settings(_) => task.update.finished_at(),
+                _ => None,
+            };
+            let new_updated_at = task.update.finished_at();
+
+            if created_at.is_none() || created_at > new_created_at {
+                created_at = new_created_at;
+            }
+
+            if updated_at.is_none() || updated_at < new_updated_at {
+                updated_at = new_updated_at;
+            }
+        }
+
+        let current_time = OffsetDateTime::now_utc();
+
+        let metadata = IndexMetadata {
+            uid: index_uuid.uid.clone(),
+            primary_key: meta.primary_key,
+            created_at: created_at.unwrap_or(current_time),
+            updated_at: updated_at.unwrap_or(current_time),
+        };
+
+        let ret = V2IndexReader {
+            metadata,
+            settings: meta.settings.check(),
+            documents: BufReader::new(File::open(path.join("documents.jsonl"))?),
+        };
+
+        Ok(ret)
+    }
+
+    pub fn metadata(&self) -> &IndexMetadata {
+        &self.metadata
+    }
+
+    pub fn documents(&mut self) -> Result<impl Iterator<Item = Result<Document>> + '_> {
+        Ok((&mut self.documents)
+            .lines()
+            .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
+    }
+
+    pub fn settings(&mut self) -> Result<Settings<Checked>> {
+        Ok(self.settings.clone())
+    }
+}
+
+pub struct UpdateFile {
+    documents: Vec<Document>,
+    index: usize,
+}
+
+impl UpdateFile {
+    fn new(path: &Path) -> Result<Self> {
+        let reader = BufReader::new(File::open(path)?);
+        Ok(UpdateFile { documents: serde_json::from_reader(reader)?, index: 0 })
+    }
+}
+
+impl Iterator for UpdateFile {
+    type Item = Result<Document>;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        self.index += 1;
+        self.documents.get(self.index - 1).cloned().map(Ok)
+    }
+}
+
+#[cfg(test)]
+pub(crate) mod test {
+    use std::fs::File;
+    use std::io::BufReader;
+
+    use flate2::bufread::GzDecoder;
+    use meili_snap::insta;
+    use tempfile::TempDir;
+
+    use super::*;
+
+    #[test]
+    fn read_dump_v2() {
+        let dump = File::open("tests/assets/v2.dump").unwrap();
+        let dir = TempDir::new().unwrap();
+        let mut dump = BufReader::new(dump);
+        let gz = GzDecoder::new(&mut dump);
+        let mut archive = tar::Archive::new(gz);
+        archive.unpack(dir.path()).unwrap();
+
+        let mut dump = V2Reader::open(dir).unwrap();
+
+        // top level infos
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
+
+        // tasks
+        let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();
+        let (tasks, mut update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"ec5fc0a14bf735ad4e361d5aa8a89ac6");
+        assert_eq!(update_files.len(), 9);
+        assert!(update_files[0].is_some()); // the enqueued document addition
+        assert!(update_files[1..].iter().all(|u| u.is_none())); // everything already processed
+
+        let update_file = update_files.remove(0).unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot_hash!(meili_snap::json_string!(update_file), @"7b8889539b669c7b9ddba448bafa385d");
+
+        // indexes
+        let mut indexes = dump.indexes().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        // the index are not ordered in any way by default
+        indexes.sort_by_key(|index| index.metadata().uid.to_string());
+
+        let mut products = indexes.pop().unwrap();
+        let mut movies2 = indexes.pop().unwrap();
+        let mut movies = indexes.pop().unwrap();
+        let mut spells = indexes.pop().unwrap();
+        assert!(indexes.is_empty());
+
+        // products
+        insta::assert_json_snapshot!(products.metadata(), @r###"
+        {
+          "uid": "products",
+          "primaryKey": "sku",
+          "createdAt": "2022-10-09T20:27:22.688964637Z",
+          "updatedAt": "2022-10-09T20:27:23.951017769Z"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(products.settings().unwrap());
+        let documents = products.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
+
+        // movies
+        insta::assert_json_snapshot!(movies.metadata(), @r###"
+        {
+          "uid": "movies",
+          "primaryKey": "id",
+          "createdAt": "2022-10-09T20:27:22.197788495Z",
+          "updatedAt": "2022-10-09T20:28:01.93111053Z"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(movies.settings().unwrap());
+        let documents = movies.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 110);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"d153b5a81d8b3cdcbe1dec270b574022");
+
+        // movies2
+        insta::assert_json_snapshot!(movies2.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
+        {
+          "uid": "movies_2",
+          "primaryKey": null,
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(movies2.settings().unwrap());
+        let documents = movies2.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 0);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"d751713988987e9331980363e24189ce");
+
+        // spells
+        insta::assert_json_snapshot!(spells.metadata(), @r###"
+        {
+          "uid": "dnd_spells",
+          "primaryKey": "index",
+          "createdAt": "2022-10-09T20:27:24.242683494Z",
+          "updatedAt": "2022-10-09T20:27:24.312809641Z"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(spells.settings().unwrap());
+        let documents = spells.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"235016433dd04262c7f2da01d1e808ce");
+    }
+
+    #[test]
+    fn read_dump_v2_from_meilisearch_v0_22_0_issue_3435() {
+        let dump = File::open("tests/assets/v2-v0.22.0.dump").unwrap();
+        let dir = TempDir::new().unwrap();
+        let mut dump = BufReader::new(dump);
+        let gz = GzDecoder::new(&mut dump);
+        let mut archive = tar::Archive::new(gz);
+        archive.unpack(dir.path()).unwrap();
+
+        let mut dump = V2Reader::open(dir).unwrap();
+
+        // top level infos
+        insta::assert_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
+
+        // tasks
+        let tasks = dump.tasks().collect::<Result<Vec<_>>>().unwrap();
+        let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"aca8ba13046272664eb3ea2da3031633");
+        assert_eq!(update_files.len(), 8);
+        assert!(update_files[0..].iter().all(|u| u.is_none())); // everything has already been processed
+
+        // indexes
+        let mut indexes = dump.indexes().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        // the index are not ordered in any way by default
+        indexes.sort_by_key(|index| index.metadata().uid.to_string());
+
+        let mut products = indexes.pop().unwrap();
+        let mut movies = indexes.pop().unwrap();
+        let mut spells = indexes.pop().unwrap();
+        assert!(indexes.is_empty());
+
+        // products
+        insta::assert_json_snapshot!(products.metadata(), @r###"
+        {
+          "uid": "products",
+          "primaryKey": "sku",
+          "createdAt": "2023-01-30T16:25:56.595257Z",
+          "updatedAt": "2023-01-30T16:25:58.70348Z"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(products.settings().unwrap());
+        let documents = products.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
+
+        // movies
+        insta::assert_json_snapshot!(movies.metadata(), @r###"
+        {
+          "uid": "movies",
+          "primaryKey": "id",
+          "createdAt": "2023-01-30T16:25:56.192178Z",
+          "updatedAt": "2023-01-30T16:25:56.455714Z"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(movies.settings().unwrap());
+        let documents = movies.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"0227598af846e574139ee0b80e03a720");
+
+        // spells
+        insta::assert_json_snapshot!(spells.metadata(), @r###"
+        {
+          "uid": "dnd_spells",
+          "primaryKey": "index",
+          "createdAt": "2023-01-30T16:25:58.876405Z",
+          "updatedAt": "2023-01-30T16:25:59.079906Z"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(spells.settings().unwrap());
+        let documents = spells.documents().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(documents.len(), 10);
+        meili_snap::snapshot_hash!(format!("{:#?}", documents), @"235016433dd04262c7f2da01d1e808ce");
+    }
+}

crates/dump/src/reader/v2/settings.rs

@@ -0,0 +1,269 @@
+use std::collections::{BTreeMap, BTreeSet};
+use std::fmt;
+use std::marker::PhantomData;
+use std::str::FromStr;
+
+use serde::{Deserialize, Deserializer};
+
+#[cfg(test)]
+fn serialize_with_wildcard<S>(
+    field: &Setting<Vec<String>>,
+    s: S,
+) -> std::result::Result<S::Ok, S::Error>
+where
+    S: serde::Serializer,
+{
+    use serde::Serialize;
+
+    let wildcard = vec!["*".to_string()];
+    match field {
+        Setting::Set(value) => Some(value),
+        Setting::Reset => Some(&wildcard),
+        Setting::NotSet => None,
+    }
+    .serialize(s)
+}
+
+#[derive(Clone, Default, Debug)]
+#[cfg_attr(test, derive(serde::Serialize))]
+pub struct Checked;
+
+#[derive(Clone, Default, Debug, Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+pub struct Unchecked;
+
+#[derive(Debug, Clone, Default, Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(deny_unknown_fields)]
+#[serde(rename_all = "camelCase")]
+#[serde(bound(serialize = "T: serde::Serialize", deserialize = "T: Deserialize<'static>"))]
+pub struct Settings<T> {
+    #[serde(
+        default,
+        serialize_with = "serialize_with_wildcard",
+        skip_serializing_if = "Setting::is_not_set"
+    )]
+    pub displayed_attributes: Setting<Vec<String>>,
+
+    #[serde(
+        default,
+        serialize_with = "serialize_with_wildcard",
+        skip_serializing_if = "Setting::is_not_set"
+    )]
+    pub searchable_attributes: Setting<Vec<String>>,
+
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub filterable_attributes: Setting<BTreeSet<String>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub sortable_attributes: Setting<BTreeSet<String>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub ranking_rules: Setting<Vec<String>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub stop_words: Setting<BTreeSet<String>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub synonyms: Setting<BTreeMap<String, Vec<String>>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    pub distinct_attribute: Setting<String>,
+
+    #[serde(skip)]
+    pub _kind: PhantomData<T>,
+}
+
+impl Settings<Unchecked> {
+    pub fn check(self) -> Settings<Checked> {
+        let displayed_attributes = match self.displayed_attributes {
+            Setting::Set(fields) => {
+                if fields.iter().any(|f| f == "*") {
+                    Setting::Reset
+                } else {
+                    Setting::Set(fields)
+                }
+            }
+            otherwise => otherwise,
+        };
+
+        let searchable_attributes = match self.searchable_attributes {
+            Setting::Set(fields) => {
+                if fields.iter().any(|f| f == "*") {
+                    Setting::Reset
+                } else {
+                    Setting::Set(fields)
+                }
+            }
+            otherwise => otherwise,
+        };
+
+        Settings {
+            displayed_attributes,
+            searchable_attributes,
+            filterable_attributes: self.filterable_attributes,
+            sortable_attributes: self.sortable_attributes,
+            ranking_rules: self.ranking_rules,
+            stop_words: self.stop_words,
+            synonyms: self.synonyms,
+            distinct_attribute: self.distinct_attribute,
+            _kind: PhantomData,
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq)]
+pub enum Setting<T> {
+    Set(T),
+    Reset,
+    NotSet,
+}
+
+impl<T> Default for Setting<T> {
+    fn default() -> Self {
+        Self::NotSet
+    }
+}
+
+impl<T> Setting<T> {
+    pub const fn is_not_set(&self) -> bool {
+        matches!(self, Self::NotSet)
+    }
+
+    pub fn map<A>(self, f: fn(T) -> A) -> Setting<A> {
+        match self {
+            Setting::Set(a) => Setting::Set(f(a)),
+            Setting::Reset => Setting::Reset,
+            Setting::NotSet => Setting::NotSet,
+        }
+    }
+}
+
+#[cfg(test)]
+impl<T: serde::Serialize> serde::Serialize for Setting<T> {
+    fn serialize<S>(&self, serializer: S) -> std::result::Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        match self {
+            Self::Set(value) => Some(value),
+            // Usually not_set isn't serialized by setting skip_serializing_if field attribute
+            Self::NotSet | Self::Reset => None,
+        }
+        .serialize(serializer)
+    }
+}
+
+impl<'de, T: Deserialize<'de>> Deserialize<'de> for Setting<T> {
+    fn deserialize<D>(deserializer: D) -> std::result::Result<Self, D::Error>
+    where
+        D: Deserializer<'de>,
+    {
+        Deserialize::deserialize(deserializer).map(|x| match x {
+            Some(x) => Self::Set(x),
+            None => Self::Reset, // Reset is forced by sending null value
+        })
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum Criterion {
+    /// Sorted by decreasing number of matched query terms.
+    /// Query words at the front of an attribute is considered better than if it was at the back.
+    Words,
+    /// Sorted by increasing number of typos.
+    Typo,
+    /// Sorted by increasing distance between matched query terms.
+    Proximity,
+    /// Documents with quey words contained in more important
+    /// attributes are considered better.
+    Attribute,
+    /// Dynamically sort at query time the documents. None, one or multiple Asc/Desc sortable
+    /// attributes can be used in place of this criterion at query time.
+    Sort,
+    /// Sorted by the similarity of the matched words with the query words.
+    Exactness,
+    /// Sorted by the increasing value of the field specified.
+    Asc(String),
+    /// Sorted by the decreasing value of the field specified.
+    Desc(String),
+}
+
+impl Criterion {
+    /// Returns the field name parameter of this criterion.
+    pub fn field_name(&self) -> Option<&str> {
+        match self {
+            Criterion::Asc(name) | Criterion::Desc(name) => Some(name),
+            _otherwise => None,
+        }
+    }
+}
+
+impl FromStr for Criterion {
+    // since we're not going to show the custom error message we can override the
+    // error type.
+    type Err = ();
+
+    fn from_str(text: &str) -> Result<Criterion, Self::Err> {
+        match text {
+            "words" => Ok(Criterion::Words),
+            "typo" => Ok(Criterion::Typo),
+            "proximity" => Ok(Criterion::Proximity),
+            "attribute" => Ok(Criterion::Attribute),
+            "sort" => Ok(Criterion::Sort),
+            "exactness" => Ok(Criterion::Exactness),
+            text => match AscDesc::from_str(text) {
+                Ok(AscDesc::Asc(field)) => Ok(Criterion::Asc(field)),
+                Ok(AscDesc::Desc(field)) => Ok(Criterion::Desc(field)),
+                Err(_) => Err(()),
+            },
+        }
+    }
+}
+
+#[derive(Debug, Deserialize, Clone, PartialEq, Eq)]
+pub enum AscDesc {
+    Asc(String),
+    Desc(String),
+}
+
+impl FromStr for AscDesc {
+    type Err = ();
+
+    // since we don't know if this comes from the old or new syntax we need to check
+    // for both syntax.
+    // WARN: this code doesn't come from the original meilisearch v0.22.0 but was
+    // written specifically to be able to import the dump of meilisearch v0.21.0 AND
+    // meilisearch v0.22.0.
+    fn from_str(text: &str) -> Result<AscDesc, Self::Err> {
+        if let Some((field_name, asc_desc)) = text.rsplit_once(':') {
+            match asc_desc {
+                "asc" => Ok(AscDesc::Asc(field_name.to_string())),
+                "desc" => Ok(AscDesc::Desc(field_name.to_string())),
+                _ => Err(()),
+            }
+        } else if text.starts_with("asc(") && text.ends_with(')') {
+            Ok(AscDesc::Asc(
+                text.strip_prefix("asc(").unwrap().strip_suffix(')').unwrap().to_string(),
+            ))
+        } else if text.starts_with("desc(") && text.ends_with(')') {
+            Ok(AscDesc::Desc(
+                text.strip_prefix("desc(").unwrap().strip_suffix(')').unwrap().to_string(),
+            ))
+        } else {
+            Err(())
+        }
+    }
+}
+
+impl fmt::Display for Criterion {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        use Criterion::*;
+
+        match self {
+            Words => f.write_str("words"),
+            Typo => f.write_str("typo"),
+            Proximity => f.write_str("proximity"),
+            Attribute => f.write_str("attribute"),
+            Sort => f.write_str("sort"),
+            Exactness => f.write_str("exactness"),
+            Asc(attr) => write!(f, "{}:asc", attr),
+            Desc(attr) => write!(f, "{}:desc", attr),
+        }
+    }
+}

crates/dump/src/reader/v2/snapshots/dump__reader__v2__test__read_dump_v2-11.snap

@@ -0,0 +1,23 @@
+---
+source: dump/src/reader/v2/mod.rs
+expression: movies2.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

crates/dump/src/reader/v2/snapshots/dump__reader__v2__test__read_dump_v2-14.snap

@@ -0,0 +1,23 @@
+---
+source: dump/src/reader/v2/mod.rs
+expression: spells.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

crates/dump/src/reader/v2/snapshots/dump__reader__v2__test__read_dump_v2-5.snap

@@ -0,0 +1,37 @@
+---
+source: dump/src/reader/v2/mod.rs
+expression: products.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {
+    "android": [
+      "phone",
+      "smartphone"
+    ],
+    "iphone": [
+      "phone",
+      "smartphone"
+    ],
+    "phone": [
+      "android",
+      "iphone",
+      "smartphone"
+    ]
+  },
+  "distinctAttribute": null
+}

crates/dump/src/reader/v2/snapshots/dump__reader__v2__test__read_dump_v2-8.snap

@@ -0,0 +1,24 @@
+---
+source: dump/src/reader/v2/mod.rs
+expression: movies.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "exactness",
+    "asc(release_date)"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

crates/dump/src/reader/v2/snapshots/dump__reader__v2__test__read_dump_v2_from_meilisearch_v0_22_0_issue_3435-10.snap

@@ -0,0 +1,25 @@
+---
+source: dump/src/reader/v2/mod.rs
+expression: spells.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "sort",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

crates/dump/src/reader/v2/snapshots/dump__reader__v2__test__read_dump_v2_from_meilisearch_v0_22_0_issue_3435-4.snap

@@ -0,0 +1,39 @@
+---
+source: dump/src/reader/v2/mod.rs
+expression: products.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "sort",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {
+    "android": [
+      "phone",
+      "smartphone"
+    ],
+    "iphone": [
+      "phone",
+      "smartphone"
+    ],
+    "phone": [
+      "android",
+      "iphone",
+      "smartphone"
+    ]
+  },
+  "distinctAttribute": null
+}

crates/dump/src/reader/v2/snapshots/dump__reader__v2__test__read_dump_v2_from_meilisearch_v0_22_0_issue_3435-7.snap

@@ -0,0 +1,30 @@
+---
+source: dump/src/reader/v2/mod.rs
+expression: movies.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [
+    "genres",
+    "id"
+  ],
+  "sortableAttributes": [
+    "release_date"
+  ],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "exactness",
+    "release_date:asc"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

crates/dump/src/reader/v2/updates.rs

@@ -0,0 +1,240 @@
+use serde::Deserialize;
+use time::OffsetDateTime;
+use uuid::Uuid;
+
+use super::{ResponseError, Settings, Unchecked};
+
+#[derive(Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+pub struct UpdateEntry {
+    pub uuid: Uuid,
+    pub update: UpdateStatus,
+}
+
+impl UpdateEntry {
+    pub fn is_finished(&self) -> bool {
+        match self.update {
+            UpdateStatus::Processing(_) | UpdateStatus::Enqueued(_) => false,
+            UpdateStatus::Processed(_) | UpdateStatus::Aborted(_) | UpdateStatus::Failed(_) => true,
+        }
+    }
+
+    pub fn get_content_uuid(&self) -> Option<&Uuid> {
+        match &self.update {
+            UpdateStatus::Enqueued(enqueued) => enqueued.content.as_ref(),
+            UpdateStatus::Processing(processing) => processing.from.content.as_ref(),
+            UpdateStatus::Processed(processed) => processed.from.from.content.as_ref(),
+            UpdateStatus::Aborted(aborted) => aborted.from.content.as_ref(),
+            UpdateStatus::Failed(failed) => failed.from.from.content.as_ref(),
+        }
+    }
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+pub enum UpdateResult {
+    DocumentsAddition(DocumentAdditionResult),
+    DocumentDeletion { deleted: u64 },
+    Other,
+}
+
+#[derive(Debug, Deserialize, Clone)]
+#[cfg_attr(test, derive(serde::Serialize))]
+pub struct DocumentAdditionResult {
+    pub nb_documents: usize,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[non_exhaustive]
+pub enum IndexDocumentsMethod {
+    /// Replace the previous document with the new one,
+    /// removing all the already known attributes.
+    ReplaceDocuments,
+
+    /// Merge the previous version of the document with the new version,
+    /// replacing old attributes values with the new ones and add the new attributes.
+    UpdateDocuments,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[non_exhaustive]
+pub enum UpdateFormat {
+    /// The given update is a real **comma separated** CSV with headers on the first line.
+    Csv,
+    /// The given update is a JSON array with documents inside.
+    Json,
+    /// The given update is a JSON stream with a document on each line.
+    JsonStream,
+}
+
+#[allow(clippy::large_enum_variant)]
+#[derive(Debug, Clone, Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(tag = "type")]
+pub enum UpdateMeta {
+    DocumentsAddition {
+        method: IndexDocumentsMethod,
+        format: UpdateFormat,
+        primary_key: Option<String>,
+    },
+    ClearDocuments,
+    DeleteDocuments {
+        ids: Vec<String>,
+    },
+    Settings(Settings<Unchecked>),
+}
+
+#[derive(Debug, Deserialize, Clone)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(rename_all = "camelCase")]
+pub struct Enqueued {
+    pub update_id: u64,
+    pub meta: UpdateMeta,
+    #[serde(with = "time::serde::rfc3339")]
+    pub enqueued_at: OffsetDateTime,
+    pub content: Option<Uuid>,
+}
+
+impl Enqueued {
+    pub fn meta(&self) -> &UpdateMeta {
+        &self.meta
+    }
+
+    pub fn id(&self) -> u64 {
+        self.update_id
+    }
+}
+
+#[derive(Debug, Deserialize, Clone)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(rename_all = "camelCase")]
+pub struct Processed {
+    pub success: UpdateResult,
+    #[serde(with = "time::serde::rfc3339")]
+    pub processed_at: OffsetDateTime,
+    #[serde(flatten)]
+    pub from: Processing,
+}
+
+impl Processed {
+    pub fn id(&self) -> u64 {
+        self.from.id()
+    }
+
+    pub fn meta(&self) -> &UpdateMeta {
+        self.from.meta()
+    }
+}
+
+#[derive(Debug, Deserialize, Clone)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(rename_all = "camelCase")]
+pub struct Processing {
+    #[serde(flatten)]
+    pub from: Enqueued,
+    #[serde(with = "time::serde::rfc3339")]
+    pub started_processing_at: OffsetDateTime,
+}
+
+impl Processing {
+    pub fn id(&self) -> u64 {
+        self.from.id()
+    }
+
+    pub fn meta(&self) -> &UpdateMeta {
+        self.from.meta()
+    }
+}
+
+#[derive(Debug, Deserialize, Clone)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(rename_all = "camelCase")]
+pub struct Aborted {
+    #[serde(flatten)]
+    pub from: Enqueued,
+    #[serde(with = "time::serde::rfc3339")]
+    pub aborted_at: OffsetDateTime,
+}
+
+impl Aborted {
+    pub fn id(&self) -> u64 {
+        self.from.id()
+    }
+
+    pub fn meta(&self) -> &UpdateMeta {
+        self.from.meta()
+    }
+}
+
+#[derive(Debug, Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(rename_all = "camelCase")]
+pub struct Failed {
+    #[serde(flatten)]
+    pub from: Processing,
+    pub error: ResponseError,
+    #[serde(with = "time::serde::rfc3339")]
+    pub failed_at: OffsetDateTime,
+}
+
+impl Failed {
+    pub fn id(&self) -> u64 {
+        self.from.id()
+    }
+
+    pub fn meta(&self) -> &UpdateMeta {
+        self.from.meta()
+    }
+}
+
+#[derive(Debug, Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(tag = "status", rename_all = "camelCase")]
+pub enum UpdateStatus {
+    Processing(Processing),
+    Enqueued(Enqueued),
+    Processed(Processed),
+    Aborted(Aborted),
+    Failed(Failed),
+}
+
+impl UpdateStatus {
+    pub fn id(&self) -> u64 {
+        match self {
+            UpdateStatus::Processing(u) => u.id(),
+            UpdateStatus::Enqueued(u) => u.id(),
+            UpdateStatus::Processed(u) => u.id(),
+            UpdateStatus::Aborted(u) => u.id(),
+            UpdateStatus::Failed(u) => u.id(),
+        }
+    }
+
+    pub fn meta(&self) -> &UpdateMeta {
+        match self {
+            UpdateStatus::Processing(u) => u.meta(),
+            UpdateStatus::Enqueued(u) => u.meta(),
+            UpdateStatus::Processed(u) => u.meta(),
+            UpdateStatus::Aborted(u) => u.meta(),
+            UpdateStatus::Failed(u) => u.meta(),
+        }
+    }
+
+    pub fn processed(&self) -> Option<&Processed> {
+        match self {
+            UpdateStatus::Processed(p) => Some(p),
+            _ => None,
+        }
+    }
+
+    pub fn finished_at(&self) -> Option<OffsetDateTime> {
+        match self {
+            UpdateStatus::Processing(_) => None,
+            UpdateStatus::Enqueued(_) => None,
+            UpdateStatus::Processed(u) => Some(u.processed_at),
+            UpdateStatus::Aborted(_) => None,
+            UpdateStatus::Failed(u) => Some(u.failed_at),
+        }
+    }
+}