refactor the Task a little bit

This commit is contained in:
Tamo 2022-10-12 03:21:25 +02:00 committed by Clément Renault
parent e6c033bd6b
commit e533e740d4
No known key found for this signature in database
GPG key ID: 92ADA4E935E71FA4
17 changed files with 1358 additions and 833 deletions

View file

@ -15,6 +15,7 @@ serde = { version = "1.0.145", features = ["derive"] }
serde_json = "1.0.85"
time = { version = "0.3.7", features = ["serde-well-known", "formatting", "parsing", "macros"] }
tokio = "1.0"
uuid = { version = "1.1.2", features = ["serde", "v4"] }
[dev-dependencies]
proptest = "1.0.0"

View file

@ -2,9 +2,11 @@ use milli::update::IndexDocumentsMethod;
use serde::{Deserialize, Serialize, Serializer};
use std::{
fmt::{Display, Write},
path::PathBuf,
str::FromStr,
};
use time::{Duration, OffsetDateTime};
use uuid::Uuid;
use crate::{
error::{Code, ResponseError},
@ -13,74 +15,192 @@ use crate::{
pub type TaskId = u32;
#[derive(Debug, Clone, PartialEq, Serialize)]
#[derive(Debug, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct TaskView {
pub struct Task {
pub uid: TaskId,
#[serde(default)]
pub index_uid: Option<String>,
pub status: Status,
// TODO use our own Kind for the user
#[serde(rename = "type")]
pub kind: Kind,
#[serde(skip_serializing_if = "Option::is_none")]
pub details: Option<DetailsView>,
#[serde(skip_serializing_if = "Option::is_none")]
pub error: Option<ResponseError>,
#[serde(
serialize_with = "serialize_duration",
skip_serializing_if = "Option::is_none",
default
)]
pub duration: Option<Duration>,
#[serde(with = "time::serde::rfc3339")]
pub enqueued_at: OffsetDateTime,
#[serde(
with = "time::serde::rfc3339::option",
skip_serializing_if = "Option::is_none",
default
)]
#[serde(with = "time::serde::rfc3339::option")]
pub started_at: Option<OffsetDateTime>,
#[serde(
with = "time::serde::rfc3339::option",
skip_serializing_if = "Option::is_none",
default
)]
#[serde(with = "time::serde::rfc3339::option")]
pub finished_at: Option<OffsetDateTime>,
pub error: Option<ResponseError>,
pub details: Option<Details>,
pub status: Status,
pub kind: KindWithContent,
}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
impl Task {
pub fn index_uid(&self) -> Option<&str> {
use KindWithContent::*;
match &self.kind {
DumpExport { .. }
| Snapshot
| CancelTask { .. }
| DeleteTasks { .. }
| IndexSwap { .. } => None,
DocumentImport { index_uid, .. }
| DocumentDeletion { index_uid, .. }
| DocumentClear { index_uid }
| Settings { index_uid, .. }
| IndexCreation { index_uid, .. }
| IndexUpdate { index_uid, .. }
| IndexDeletion { index_uid } => Some(index_uid),
}
}
/// Return the list of indexes updated by this tasks.
pub fn indexes(&self) -> Option<Vec<&str>> {
use KindWithContent::*;
match &self.kind {
DumpExport { .. } | Snapshot | CancelTask { .. } | DeleteTasks { .. } => None,
DocumentImport { index_uid, .. }
| DocumentDeletion { index_uid, .. }
| DocumentClear { index_uid }
| Settings { index_uid, .. }
| IndexCreation { index_uid, .. }
| IndexUpdate { index_uid, .. }
| IndexDeletion { index_uid } => Some(vec![index_uid]),
IndexSwap { lhs, rhs } => Some(vec![lhs, rhs]),
}
}
}
#[derive(Debug, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub struct TaskDump {
pub uid: TaskId,
#[serde(default)]
pub index_uid: Option<String>,
pub status: Status,
// TODO use our own Kind for the user
#[serde(rename = "type")]
pub kind: Kind,
pub enum KindWithContent {
DocumentImport {
index_uid: String,
primary_key: Option<String>,
method: IndexDocumentsMethod,
content_file: Uuid,
documents_count: u64,
allow_index_creation: bool,
},
DocumentDeletion {
index_uid: String,
documents_ids: Vec<String>,
},
DocumentClear {
index_uid: String,
},
Settings {
index_uid: String,
new_settings: Settings<Unchecked>,
is_deletion: bool,
allow_index_creation: bool,
},
IndexDeletion {
index_uid: String,
},
IndexCreation {
index_uid: String,
primary_key: Option<String>,
},
IndexUpdate {
index_uid: String,
primary_key: Option<String>,
},
IndexSwap {
lhs: String,
rhs: String,
},
CancelTask {
tasks: Vec<TaskId>,
},
DeleteTasks {
query: String,
tasks: Vec<TaskId>,
},
DumpExport {
output: PathBuf,
},
Snapshot,
}
#[serde(skip_serializing_if = "Option::is_none")]
pub details: Option<Details>,
#[serde(skip_serializing_if = "Option::is_none")]
pub error: Option<ResponseError>,
impl KindWithContent {
pub fn as_kind(&self) -> Kind {
match self {
KindWithContent::DocumentImport { .. } => Kind::DocumentImport,
KindWithContent::DocumentDeletion { .. } => Kind::DocumentDeletion,
KindWithContent::DocumentClear { .. } => Kind::DocumentClear,
KindWithContent::Settings { .. } => Kind::Settings,
KindWithContent::IndexCreation { .. } => Kind::IndexCreation,
KindWithContent::IndexDeletion { .. } => Kind::IndexDeletion,
KindWithContent::IndexUpdate { .. } => Kind::IndexUpdate,
KindWithContent::IndexSwap { .. } => Kind::IndexSwap,
KindWithContent::CancelTask { .. } => Kind::CancelTask,
KindWithContent::DeleteTasks { .. } => Kind::DeleteTasks,
KindWithContent::DumpExport { .. } => Kind::DumpExport,
KindWithContent::Snapshot => Kind::Snapshot,
}
}
#[serde(with = "time::serde::rfc3339")]
pub enqueued_at: OffsetDateTime,
#[serde(
with = "time::serde::rfc3339::option",
skip_serializing_if = "Option::is_none",
default
)]
pub started_at: Option<OffsetDateTime>,
#[serde(
with = "time::serde::rfc3339::option",
skip_serializing_if = "Option::is_none",
default
)]
pub finished_at: Option<OffsetDateTime>,
pub fn indexes(&self) -> Option<Vec<&str>> {
use KindWithContent::*;
match self {
DumpExport { .. } | Snapshot | CancelTask { .. } | DeleteTasks { .. } => None,
DocumentImport { index_uid, .. }
| DocumentDeletion { index_uid, .. }
| DocumentClear { index_uid }
| Settings { index_uid, .. }
| IndexCreation { index_uid, .. }
| IndexUpdate { index_uid, .. }
| IndexDeletion { index_uid } => Some(vec![index_uid]),
IndexSwap { lhs, rhs } => Some(vec![lhs, rhs]),
}
}
/// Returns the default `Details` that correspond to this `KindWithContent`,
/// `None` if it cannot be generated.
pub fn default_details(&self) -> Option<Details> {
match self {
KindWithContent::DocumentImport {
documents_count, ..
} => Some(Details::DocumentAddition {
received_documents: *documents_count,
indexed_documents: 0,
}),
KindWithContent::DocumentDeletion {
index_uid: _,
documents_ids,
} => Some(Details::DocumentDeletion {
received_document_ids: documents_ids.len(),
deleted_documents: None,
}),
KindWithContent::DocumentClear { .. } => Some(Details::ClearAll {
deleted_documents: None,
}),
KindWithContent::Settings { new_settings, .. } => Some(Details::Settings {
settings: new_settings.clone(),
}),
KindWithContent::IndexDeletion { .. } => None,
KindWithContent::IndexCreation { primary_key, .. }
| KindWithContent::IndexUpdate { primary_key, .. } => Some(Details::IndexInfo {
primary_key: primary_key.clone(),
}),
KindWithContent::IndexSwap { .. } => {
todo!()
}
KindWithContent::CancelTask { .. } => {
None // TODO: check correctness of this return value
}
KindWithContent::DeleteTasks { query, tasks } => Some(Details::DeleteTasks {
matched_tasks: tasks.len(),
deleted_tasks: None,
original_query: query.clone(),
}),
KindWithContent::DumpExport { .. } => None,
KindWithContent::Snapshot => None,
}
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
@ -123,15 +243,10 @@ impl FromStr for Status {
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub enum Kind {
DocumentImport {
method: IndexDocumentsMethod,
allow_index_creation: bool,
},
DocumentImport,
DocumentDeletion,
DocumentClear,
Settings {
allow_index_creation: bool,
},
Settings,
IndexCreation,
IndexDeletion,
IndexUpdate,
@ -147,22 +262,11 @@ impl FromStr for Kind {
fn from_str(s: &str) -> Result<Self, Self::Err> {
match s {
"document_addition" => Ok(Kind::DocumentImport {
method: IndexDocumentsMethod::ReplaceDocuments,
// TODO this doesn't make sense
allow_index_creation: false,
}),
"document_update" => Ok(Kind::DocumentImport {
method: IndexDocumentsMethod::UpdateDocuments,
// TODO this doesn't make sense
allow_index_creation: false,
}),
"document_addition" => Ok(Kind::DocumentImport),
"document_update" => Ok(Kind::DocumentImport),
"document_deletion" => Ok(Kind::DocumentDeletion),
"document_clear" => Ok(Kind::DocumentClear),
"settings" => Ok(Kind::Settings {
// TODO this doesn't make sense
allow_index_creation: false,
}),
"settings" => Ok(Kind::Settings),
"index_creation" => Ok(Kind::IndexCreation),
"index_deletion" => Ok(Kind::IndexDeletion),
"index_update" => Ok(Kind::IndexUpdate),
@ -179,73 +283,6 @@ impl FromStr for Kind {
}
}
#[derive(Default, Debug, PartialEq, Clone, Serialize)]
#[serde(rename_all = "camelCase")]
pub struct DetailsView {
#[serde(skip_serializing_if = "Option::is_none")]
pub received_documents: Option<u64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub indexed_documents: Option<u64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub primary_key: Option<Option<String>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub received_document_ids: Option<usize>,
#[serde(skip_serializing_if = "Option::is_none")]
pub deleted_documents: Option<Option<u64>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub matched_tasks: Option<usize>,
#[serde(skip_serializing_if = "Option::is_none")]
pub deleted_tasks: Option<Option<usize>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub original_query: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub dump_uid: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(flatten)]
pub settings: Option<Settings<Unchecked>>,
}
// A `Kind` specific version made for the dump. If modified you may break the dump.
#[derive(Debug, PartialEq, Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
pub enum KindDump {
DocumentImport {
primary_key: Option<String>,
method: IndexDocumentsMethod,
documents_count: u64,
allow_index_creation: bool,
},
DocumentDeletion {
documents_ids: Vec<String>,
},
DocumentClear,
Settings {
new_settings: Settings<Unchecked>,
is_deletion: bool,
allow_index_creation: bool,
},
IndexDeletion,
IndexCreation {
primary_key: Option<String>,
},
IndexUpdate {
primary_key: Option<String>,
},
IndexSwap {
lhs: String,
rhs: String,
},
CancelTask {
tasks: Vec<TaskId>,
},
DeleteTasks {
query: String,
tasks: Vec<TaskId>,
},
DumpExport,
Snapshot,
}
#[derive(Debug, PartialEq, Clone, Serialize, Deserialize)]
#[allow(clippy::large_enum_variant)]
pub enum Details {
@ -277,59 +314,10 @@ pub enum Details {
},
}
impl Details {
pub fn as_details_view(&self) -> DetailsView {
match self.clone() {
Details::DocumentAddition {
received_documents,
indexed_documents,
} => DetailsView {
received_documents: Some(received_documents),
indexed_documents: Some(indexed_documents),
..DetailsView::default()
},
Details::Settings { settings } => DetailsView {
settings: Some(settings),
..DetailsView::default()
},
Details::IndexInfo { primary_key } => DetailsView {
primary_key: Some(primary_key),
..DetailsView::default()
},
Details::DocumentDeletion {
received_document_ids,
deleted_documents,
} => DetailsView {
received_document_ids: Some(received_document_ids),
deleted_documents: Some(deleted_documents),
..DetailsView::default()
},
Details::ClearAll { deleted_documents } => DetailsView {
deleted_documents: Some(deleted_documents),
..DetailsView::default()
},
Details::DeleteTasks {
matched_tasks,
deleted_tasks,
original_query,
} => DetailsView {
matched_tasks: Some(matched_tasks),
deleted_tasks: Some(deleted_tasks),
original_query: Some(original_query),
..DetailsView::default()
},
Details::Dump { dump_uid } => DetailsView {
dump_uid: Some(dump_uid),
..DetailsView::default()
},
}
}
}
/// Serialize a `time::Duration` as a best effort ISO 8601 while waiting for
/// https://github.com/time-rs/time/issues/378.
/// This code is a port of the old code of time that was removed in 0.2.
fn serialize_duration<S: Serializer>(
pub fn serialize_duration<S: Serializer>(
duration: &Option<Duration>,
serializer: S,
) -> Result<S::Ok, S::Error> {
@ -376,3 +364,26 @@ fn serialize_duration<S: Serializer>(
None => serializer.serialize_none(),
}
}
/*
#[cfg(test)]
mod tests {
use crate::assert_smol_debug_snapshot;
use crate::heed::{types::SerdeJson, BytesDecode, BytesEncode};
use super::Details;
#[test]
fn bad_deser() {
let details = Details::DeleteTasks {
matched_tasks: 1,
deleted_tasks: None,
original_query: "hello".to_owned(),
};
let serialised = SerdeJson::<Details>::bytes_encode(&details).unwrap();
let deserialised = SerdeJson::<Details>::bytes_decode(&serialised).unwrap();
assert_smol_debug_snapshot!(details, @r###"DeleteTasks { matched_tasks: 1, deleted_tasks: None, original_query: "hello" }"###);
assert_smol_debug_snapshot!(deserialised, @r###"DeleteTasks { matched_tasks: 1, deleted_tasks: None, original_query: "hello" }"###);
}
}
*/