MeiliSearch/meilidb-data/src/database.rs

225 lines
6.1 KiB
Rust
Raw Normal View History

2019-04-08 15:19:57 +02:00
use std::path::Path;
use std::sync::Arc;
2019-04-08 15:19:57 +02:00
use arc_swap::{ArcSwap, Lease};
use hashbrown::HashMap;
use meilidb_core::shared_data_cursor::{FromSharedDataCursor, SharedDataCursor};
use meilidb_core::write_to_bytes::WriteToBytes;
use meilidb_core::{DocumentId, Index as WordIndex};
use sled::IVec;
use crate::{Schema, SchemaAttr, RankedMap};
2019-04-08 15:19:57 +02:00
#[derive(Debug)]
pub enum Error {
SchemaDiffer,
SchemaMissing,
WordIndexMissing,
2019-04-08 15:19:57 +02:00
SledError(sled::Error),
BincodeError(bincode::Error),
}
impl From<sled::Error> for Error {
fn from(error: sled::Error) -> Error {
Error::SledError(error)
}
}
impl From<bincode::Error> for Error {
fn from(error: bincode::Error) -> Error {
Error::BincodeError(error)
}
}
fn index_name(name: &str) -> Vec<u8> {
format!("index-{}", name).into_bytes()
}
fn document_key(id: DocumentId, attr: SchemaAttr) -> Vec<u8> {
let DocumentId(document_id) = id;
let SchemaAttr(schema_attr) = attr;
let mut bytes = Vec::new();
bytes.extend_from_slice(b"document-");
bytes.extend_from_slice(&document_id.to_be_bytes()[..]);
bytes.extend_from_slice(&schema_attr.to_be_bytes()[..]);
bytes
}
fn ivec_into_arc(ivec: IVec) -> Arc<[u8]> {
match ivec {
IVec::Inline(len, bytes) => Arc::from(&bytes[..len as usize]),
IVec::Remote { buf } => buf,
}
}
#[derive(Clone)]
pub struct Database {
opened: Arc<ArcSwap<HashMap<String, Index>>>,
inner: sled::Db,
}
impl Database {
2019-04-08 15:19:57 +02:00
pub fn start_default<P: AsRef<Path>>(path: P) -> Result<Database, Error> {
let inner = sled::Db::start_default(path)?;
let opened = Arc::new(ArcSwap::new(Arc::new(HashMap::new())));
Ok(Database { opened, inner })
}
2019-04-08 15:19:57 +02:00
pub fn open_index(&self, name: &str) -> Result<Option<Index>, Error> {
// check if the index was already opened
if let Some(index) = self.opened.lease().get(name) {
return Ok(Some(index.clone()))
}
let raw_name = index_name(name);
if self.inner.tree_names().into_iter().any(|tn| tn == raw_name) {
let tree = self.inner.open_tree(raw_name)?;
2019-04-08 15:19:57 +02:00
let index = Index::from_raw(tree)?;
self.opened.rcu(|opened| {
let mut opened = HashMap::clone(opened);
opened.insert(name.to_string(), index.clone());
opened
});
2019-04-08 15:19:57 +02:00
return Ok(Some(index))
}
Ok(None)
}
pub fn create_index(&self, name: String, schema: Schema) -> Result<Index, Error> {
match self.open_index(&name)? {
2019-04-08 15:19:57 +02:00
Some(index) => {
if index.schema != schema {
return Err(Error::SchemaDiffer);
}
2019-04-08 15:19:57 +02:00
Ok(index)
},
None => {
let raw_name = index_name(&name);
let tree = self.inner.open_tree(raw_name)?;
2019-04-08 15:19:57 +02:00
let index = Index::new_from_raw(tree, schema)?;
self.opened.rcu(|opened| {
let mut opened = HashMap::clone(opened);
opened.insert(name.clone(), index.clone());
opened
});
2019-04-08 15:19:57 +02:00
Ok(index)
},
}
}
}
#[derive(Clone)]
2019-04-08 15:19:57 +02:00
pub struct Index {
schema: Schema,
word_index: Arc<ArcSwap<WordIndex>>,
ranked_map: Arc<ArcSwap<RankedMap>>,
2019-04-08 15:19:57 +02:00
inner: Arc<sled::Tree>,
}
impl Index {
fn from_raw(inner: Arc<sled::Tree>) -> Result<Index, Error> {
let schema = {
let bytes = inner.get("schema")?;
let bytes = bytes.ok_or(Error::SchemaMissing)?;
Schema::read_from_bin(bytes.as_ref())?
};
let bytes = inner.get("word-index")?;
let bytes = bytes.ok_or(Error::WordIndexMissing)?;
let word_index = {
let len = bytes.len();
let bytes = ivec_into_arc(bytes);
let mut cursor = SharedDataCursor::from_shared_bytes(bytes, 0, len);
// TODO must handle this error
let word_index = WordIndex::from_shared_data_cursor(&mut cursor).unwrap();
Arc::new(ArcSwap::new(Arc::new(word_index)))
};
let ranked_map = {
let map = match inner.get("ranked-map")? {
Some(bytes) => bincode::deserialize(bytes.as_ref())?,
None => RankedMap::default(),
};
Arc::new(ArcSwap::new(Arc::new(map)))
};
Ok(Index { schema, word_index, ranked_map, inner })
2019-04-08 15:19:57 +02:00
}
fn new_from_raw(inner: Arc<sled::Tree>, schema: Schema) -> Result<Index, Error> {
let mut schema_bytes = Vec::new();
schema.write_to_bin(&mut schema_bytes)?;
2019-04-08 15:19:57 +02:00
inner.set("schema", schema_bytes)?;
let word_index = WordIndex::default();
inner.set("word-index", word_index.into_bytes())?;
let word_index = Arc::new(ArcSwap::new(Arc::new(word_index)));
let ranked_map = Arc::new(ArcSwap::new(Arc::new(RankedMap::default())));
Ok(Index { schema, word_index, ranked_map, inner })
2019-04-08 15:19:57 +02:00
}
pub fn schema(&self) -> &Schema {
&self.schema
}
pub fn word_index(&self) -> Lease<Arc<WordIndex>> {
self.word_index.lease()
}
pub fn ranked_map(&self) -> Lease<Arc<RankedMap>> {
self.ranked_map.lease()
}
fn update_word_index(&self, word_index: Arc<WordIndex>) {
self.word_index.store(word_index)
}
fn update_ranked_map(&self, ranked_map: Arc<RankedMap>) {
self.ranked_map.store(ranked_map)
}
pub fn set_document_attribute<V>(
&self,
id: DocumentId,
attr: SchemaAttr,
value: V,
) -> Result<Option<IVec>, Error>
where IVec: From<V>,
{
let key = document_key(id, attr);
Ok(self.inner.set(key, value)?)
}
pub fn get_document_attribute(
&self,
id: DocumentId,
attr: SchemaAttr
) -> Result<Option<IVec>, Error>
{
let key = document_key(id, attr);
Ok(self.inner.get(key)?)
}
pub fn del_document_attribute(
&self,
id: DocumentId,
attr: SchemaAttr
) -> Result<Option<IVec>, Error>
{
let key = document_key(id, attr);
Ok(self.inner.del(key)?)
}
2019-04-08 15:19:57 +02:00
}