Move crates under a sub folder to clean up the code

crates/dump/src/reader/v3/errors.rs

@@ -0,0 +1,52 @@
+use serde::{Deserialize, Serialize};
+
+#[allow(clippy::enum_variant_names)]
+#[derive(Serialize, Deserialize, Debug, Clone, Copy)]
+pub enum Code {
+    // index related error
+    CreateIndex,
+    IndexAlreadyExists,
+    IndexNotFound,
+    InvalidIndexUid,
+
+    // invalid state error
+    InvalidState,
+    MissingPrimaryKey,
+    PrimaryKeyAlreadyPresent,
+
+    MaxFieldsLimitExceeded,
+    MissingDocumentId,
+    InvalidDocumentId,
+
+    Filter,
+    Sort,
+
+    BadParameter,
+    BadRequest,
+    DatabaseSizeLimitReached,
+    DocumentNotFound,
+    Internal,
+    InvalidGeoField,
+    InvalidRankingRule,
+    InvalidStore,
+    InvalidToken,
+    MissingAuthorizationHeader,
+    NoSpaceLeftOnDevice,
+    DumpNotFound,
+    TaskNotFound,
+    PayloadTooLarge,
+    RetrieveDocument,
+    SearchDocuments,
+    UnsupportedMediaType,
+
+    DumpAlreadyInProgress,
+    DumpProcessFailed,
+
+    InvalidContentType,
+    MissingContentType,
+    MalformedPayload,
+    MissingPayload,
+
+    MalformedDump,
+    UnretrievableErrorCode,
+}

crates/dump/src/reader/v3/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/v3/mod.rs

@@ -0,0 +1,354 @@
+//! ```text
+//! .
+//! ├── indexes
+//! │   ├── 01d7dd17-8241-4f1f-a7d1-2d1cb255f5b0
+//! │   │   ├── documents.jsonl
+//! │   │   └── meta.json
+//! │   ├── 78be64a3-cae1-449e-b7ed-13e77c9a8a0c
+//! │   │   ├── documents.jsonl
+//! │   │   └── meta.json
+//! │   ├── ba553439-18fe-4733-ba53-44eed898280c
+//! │   │   ├── documents.jsonl
+//! │   │   └── meta.json
+//! │   └── c408bc22-5859-49d1-8e9f-c88e2fa95cb0
+//! │       ├── documents.jsonl
+//! │       └── meta.json
+//! ├── index_uuids
+//! │   └── data.jsonl
+//! ├── metadata.json
+//! └── updates
+//!     ├── data.jsonl
+//!     └── updates_files
+//!         └── 66d3f12d-fcf3-4b53-88cb-407017373de7
+//! ```
+
+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::v3_to_v4::CompatV3ToV4;
+use super::Document;
+use crate::{Error, IndexMetadata, Result, Version};
+
+pub type Settings<T> = settings::Settings<T>;
+pub type Checked = settings::Checked;
+pub type Unchecked = settings::Unchecked;
+
+pub type Task = updates::UpdateEntry;
+
+// ===== Other types to clarify the code of the compat module
+// everything related to the tasks
+pub type Status = updates::UpdateStatus;
+pub type Kind = updates::Update;
+
+// everything related to the settings
+pub type Setting<T> = settings::Setting<T>;
+
+// everything related to the errors
+pub type Code = errors::Code;
+
+#[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 V3Reader {
+    dump: TempDir,
+    metadata: Metadata,
+    tasks: BufReader<File>,
+    index_uuid: Vec<IndexUuid>,
+}
+
+impl V3Reader {
+    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(V3Reader {
+            metadata,
+            tasks: BufReader::new(File::open(dump.path().join("updates").join("data.jsonl"))?),
+            index_uuid,
+            dump,
+        })
+    }
+
+    pub fn index_uuid(&self) -> Vec<IndexUuid> {
+        self.index_uuid.clone()
+    }
+
+    pub fn to_v4(self) -> CompatV3ToV4 {
+        CompatV3ToV4::new(self)
+    }
+
+    pub fn version(&self) -> Version {
+        Version::V3
+    }
+
+    pub fn date(&self) -> Option<OffsetDateTime> {
+        Some(self.metadata.dump_date)
+    }
+
+    pub fn indexes(&self) -> Result<impl Iterator<Item = Result<V3IndexReader>> + '_> {
+        Ok(self.index_uuid.iter().map(|index| -> Result<_> {
+            V3IndexReader::new(
+                &self.dump.path().join("indexes").join(index.uuid.to_string()),
+                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<Box<super::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("updates_files")
+                        .join(uuid.to_string());
+                    Ok((
+                        task,
+                        Some(
+                            Box::new(UpdateFile::new(&update_file_path)?) as Box<super::UpdateFile>
+                        ),
+                    ))
+                } else {
+                    Ok((task, None))
+                }
+            } else {
+                Ok((task, None))
+            }
+        }))
+    }
+}
+
+pub struct V3IndexReader {
+    metadata: IndexMetadata,
+    settings: Settings<Checked>,
+
+    documents: BufReader<File>,
+}
+
+impl V3IndexReader {
+    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::DocumentAddition { .. } | 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 = V3IndexReader {
+            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 {
+    reader: BufReader<File>,
+}
+
+impl UpdateFile {
+    fn new(path: &Path) -> Result<Self> {
+        Ok(UpdateFile { reader: BufReader::new(File::open(path)?) })
+    }
+}
+
+impl Iterator for UpdateFile {
+    type Item = Result<Document>;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        (&mut self.reader)
+            .lines()
+            .map(|line| {
+                line.map_err(Error::from)
+                    .and_then(|line| serde_json::from_str(&line).map_err(Error::from))
+            })
+            .next()
+    }
+}
+
+#[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_v3() {
+        let dump = File::open("tests/assets/v3.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 = V3Reader::open(dir).unwrap();
+
+        // top level infos
+        insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +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), @"63086d59c3f2074e4ab3fff7e8cc36c1");
+        assert_eq!(update_files.len(), 10);
+        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": "2022-10-07T11:38:54.74389899Z",
+          "updatedAt": "2022-10-07T11:38:55.963185778Z"
+        }
+        "###);
+
+        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": "2022-10-07T11:38:54.026649575Z",
+          "updatedAt": "2022-10-07T11:39:04.188852537Z"
+        }
+        "###);
+
+        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": "2022-10-07T11:38:56.265951133Z",
+          "updatedAt": "2022-10-07T11:38:56.521004328Z"
+        }
+        "###);
+
+        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/v3/settings.rs

@@ -0,0 +1,234 @@
+use std::collections::{BTreeMap, BTreeSet};
+use std::marker::PhantomData;
+use std::num::NonZeroUsize;
+
+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;
+
+/// Holds all the settings for an index. `T` can either be `Checked` if they represents settings
+/// whose validity is guaranteed, or `Unchecked` if they need to be validated. In the later case, a
+/// call to `check` will return a `Settings<Checked>` from a `Settings<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<Checked> {
+    pub fn cleared() -> Settings<Checked> {
+        Settings {
+            displayed_attributes: Setting::Reset,
+            searchable_attributes: Setting::Reset,
+            filterable_attributes: Setting::Reset,
+            sortable_attributes: Setting::Reset,
+            ranking_rules: Setting::Reset,
+            stop_words: Setting::Reset,
+            synonyms: Setting::Reset,
+            distinct_attribute: Setting::Reset,
+            _kind: PhantomData,
+        }
+    }
+
+    pub fn into_unchecked(self) -> Settings<Unchecked> {
+        let Self {
+            displayed_attributes,
+            searchable_attributes,
+            filterable_attributes,
+            sortable_attributes,
+            ranking_rules,
+            stop_words,
+            synonyms,
+            distinct_attribute,
+            ..
+        } = self;
+
+        Settings {
+            displayed_attributes,
+            searchable_attributes,
+            filterable_attributes,
+            sortable_attributes,
+            ranking_rules,
+            stop_words,
+            synonyms,
+            distinct_attribute,
+            _kind: PhantomData,
+        }
+    }
+}
+
+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, Deserialize)]
+#[allow(dead_code)] // otherwise rustc complains that the fields go unused
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(deny_unknown_fields)]
+#[serde(rename_all = "camelCase")]
+pub struct Facets {
+    pub level_group_size: Option<NonZeroUsize>,
+    pub min_level_size: Option<NonZeroUsize>,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum Setting<T> {
+    Set(T),
+    Reset,
+    NotSet,
+}
+
+impl<T> Default for Setting<T> {
+    fn default() -> Self {
+        Self::NotSet
+    }
+}
+
+impl<T> Setting<T> {
+    pub fn map<U, F>(self, f: F) -> Setting<U>
+    where
+        F: FnOnce(T) -> U,
+    {
+        match self {
+            Setting::Set(t) => Setting::Set(f(t)),
+            Setting::Reset => Setting::Reset,
+            Setting::NotSet => Setting::NotSet,
+        }
+    }
+
+    pub fn set(self) -> Option<T> {
+        match self {
+            Self::Set(value) => Some(value),
+            _ => None,
+        }
+    }
+
+    pub const fn as_ref(&self) -> Setting<&T> {
+        match *self {
+            Self::Set(ref value) => Setting::Set(value),
+            Self::Reset => Setting::Reset,
+            Self::NotSet => Setting::NotSet,
+        }
+    }
+
+    pub const fn is_not_set(&self) -> bool {
+        matches!(self, Self::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
+        })
+    }
+}

crates/dump/src/reader/v3/snapshots/dump__reader__v3__test__read_dump_v3-11.snap

@@ -0,0 +1,25 @@
+---
+source: dump/src/reader/v3/mod.rs
+expression: movies2.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "sort",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

crates/dump/src/reader/v3/snapshots/dump__reader__v3__test__read_dump_v3-14.snap

@@ -0,0 +1,25 @@
+---
+source: dump/src/reader/v3/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/v3/snapshots/dump__reader__v3__test__read_dump_v3-5.snap

@@ -0,0 +1,39 @@
+---
+source: dump/src/reader/v3/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/v3/snapshots/dump__reader__v3__test__read_dump_v3-8.snap

@@ -0,0 +1,31 @@
+---
+source: dump/src/reader/v3/mod.rs
+expression: movies.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [
+    "genres",
+    "id"
+  ],
+  "sortableAttributes": [
+    "release_date"
+  ],
+  "rankingRules": [
+    "words",
+    "typo",
+    "proximity",
+    "attribute",
+    "sort",
+    "exactness",
+    "release_date:asc"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

crates/dump/src/reader/v3/updates.rs

@@ -0,0 +1,247 @@
+use std::fmt::Display;
+
+use serde::Deserialize;
+use time::OffsetDateTime;
+use uuid::Uuid;
+
+use super::{Code, 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::Processed(_) | UpdateStatus::Aborted(_) | UpdateStatus::Failed(_) => true,
+            UpdateStatus::Processing(_) | UpdateStatus::Enqueued(_) => false,
+        }
+    }
+
+    pub fn get_content_uuid(&self) -> Option<&Uuid> {
+        match self.update.meta() {
+            Update::DocumentAddition { content_uuid, .. } => Some(content_uuid),
+            Update::DeleteDocuments(_) | Update::Settings(_) | Update::ClearDocuments => None,
+        }
+    }
+}
+
+#[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) -> &Update {
+        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 is_finished(&self) -> bool {
+        match self {
+            UpdateStatus::Processing(_) | UpdateStatus::Enqueued(_) => false,
+            UpdateStatus::Aborted(_) | UpdateStatus::Failed(_) | UpdateStatus::Processed(_) => true,
+        }
+    }
+
+    pub fn processed(&self) -> Option<&Processed> {
+        match self {
+            UpdateStatus::Processed(p) => Some(p),
+            _ => None,
+        }
+    }
+
+    pub fn enqueued_at(&self) -> Option<OffsetDateTime> {
+        match self {
+            UpdateStatus::Processing(u) => Some(u.from.enqueued_at),
+            UpdateStatus::Enqueued(u) => Some(u.enqueued_at),
+            UpdateStatus::Processed(u) => Some(u.from.from.enqueued_at),
+            UpdateStatus::Aborted(u) => Some(u.from.enqueued_at),
+            UpdateStatus::Failed(u) => Some(u.from.from.enqueued_at),
+        }
+    }
+
+    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),
+        }
+    }
+}
+
+#[derive(Debug, Deserialize, Clone)]
+#[cfg_attr(test, derive(serde::Serialize))]
+#[serde(rename_all = "camelCase")]
+pub struct Enqueued {
+    pub update_id: u64,
+    pub meta: Update,
+    #[serde(with = "time::serde::rfc3339")]
+    pub enqueued_at: OffsetDateTime,
+}
+
+impl Enqueued {
+    pub fn meta(&self) -> &Update {
+        &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) -> &Update {
+        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) -> &Update {
+        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) -> &Update {
+        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 msg: String,
+    pub code: Code,
+    #[serde(with = "time::serde::rfc3339")]
+    pub failed_at: OffsetDateTime,
+}
+
+impl Display for Failed {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        self.msg.fmt(f)
+    }
+}
+
+impl Failed {
+    pub fn id(&self) -> u64 {
+        self.from.id()
+    }
+
+    pub fn meta(&self) -> &Update {
+        self.from.meta()
+    }
+}
+
+#[allow(clippy::large_enum_variant)]
+#[derive(Debug, Clone, Deserialize)]
+#[cfg_attr(test, derive(serde::Serialize))]
+pub enum Update {
+    DeleteDocuments(Vec<String>),
+    DocumentAddition {
+        primary_key: Option<String>,
+        method: IndexDocumentsMethod,
+        content_uuid: Uuid,
+    },
+    Settings(Settings<Unchecked>),
+    ClearDocuments,
+}
+
+#[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, 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,
+}