Compare commits

..

8 Commits

Author SHA1 Message Date
Paul Masurel
073cc99254 Updated changelog 2019-12-12 10:17:22 +09:00
Paul Masurel
367c2102fc Fixing test 2019-12-12 10:13:56 +09:00
Paul Masurel
a57e3a8cc4 WIP. 2019-12-11 23:50:23 +09:00
Paul Masurel
be26d54719 Merge branch 'n662_footer_is_incompatible_impl' of https://github.com/petr-tik/tantivy into petr-tik-n662_footer_is_incompatible_impl 2019-12-11 09:38:57 +09:00
petr-tik
99d2b54273 Correct the compatibility check logic
Leave a defensive versioned footer check to make sure we add new logic handling
when we add possible footer versions

Restricted VersionedFooter::from_bytes to be used inside the crate only

remove a half-baked test
2019-11-11 23:41:42 +00:00
petr-tik
5804a2c7e5 Remove an unnecessary assert
it's follower by the same check that Errors instead of panicking
2019-11-11 21:46:18 +00:00
petr-tik
b34e660c84 Make error handling more ergonomic
Add an error subtype for OpenReadError and converters to TantivyError
2019-11-10 23:15:32 +00:00
petr-tik
660471a063 WIP implemented is_compatible
hide Footer::from_bytes from public consumption - only found Footer::extract
used outside the module

Add a new error type for IncompatibleIndex
add a prototypical call to footer.is_compatible() in ManagedDirectory::open_read
to make sure we error before reading it further
2019-11-10 18:15:36 +00:00
42 changed files with 369 additions and 1158 deletions

View File

@@ -1,17 +1,3 @@
Tantivy 0.11.3
=======================
- Fixed DateTime as a fast field (#735)
Tantivy 0.11.2
=======================
- The future returned by `IndexWriter::merge` does not borrow `self` mutably anymore (#732)
- Exposing a constructor for `WatchHandle` (#731)
Tantivy 0.11.1
=====================
- Bug fix #729
Tantivy 0.11.0
=====================
@@ -23,7 +9,6 @@ Tantivy 0.11.0
- API change around `Box<BoxableTokenizer>`. See detail in #629
- Avoid rebuilding Regex automaton whenever a regex query is reused. #639 (@brainlock)
- Add footer with some metadata to index files. #605 (@fdb-hiroshima)
- Add a method to check the compatibility of the footer in the index with the running version of tantivy (@petr-tik)
- TopDocs collector: ensure stable sorting on equal score. #671 (@brainlock)
- Added handling of pre-tokenized text fields (#642), which will enable users to
load tokens created outside tantivy. See usage in examples/pre_tokenized_text. (@kkoziara)

View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy"
version = "0.11.3"
version = "0.11.0"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
@@ -33,6 +33,7 @@ fs2={version="0.4", optional=true}
itertools = "0.8"
levenshtein_automata = {version="0.1", features=["fst_automaton"]}
notify = {version="4", optional=true}
bit-set = "0.5"
uuid = { version = "0.8", features = ["v4", "serde"] }
crossbeam = "0.7"
futures = {version = "0.3", features=["thread-pool"] }
@@ -40,7 +41,7 @@ owning_ref = "0.4"
stable_deref_trait = "1.0.0"
rust-stemmers = "1.2"
downcast-rs = { version="1.0" }
tantivy-query-grammar = { version="0.11", path="./query-grammar" }
tantivy-query-grammar = { path="./query-grammar" }
bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
census = "0.4"
fnv = "1.0.6"

View File

@@ -13,100 +13,63 @@
// ---
// Importing tantivy...
use tantivy::collector::FacetCollector;
use tantivy::query::{AllQuery, TermQuery};
use tantivy::query::AllQuery;
use tantivy::schema::*;
use tantivy::{doc, Index};
use tempfile::TempDir;
fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the sake of this example
// Let's create a temporary directory for the
// sake of this example
let index_path = TempDir::new()?;
let mut schema_builder = Schema::builder();
let name = schema_builder.add_text_field("felin_name", TEXT | STORED);
// this is our faceted field: its scientific classification
let classification = schema_builder.add_facet_field("classification");
schema_builder.add_text_field("name", TEXT | STORED);
// this is our faceted field
schema_builder.add_facet_field("tags");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer(30_000_000)?;
let index = Index::create_in_dir(&index_path, schema.clone())?;
let mut index_writer = index.writer(50_000_000)?;
let name = schema.get_field("name").unwrap();
let tags = schema.get_field("tags").unwrap();
// For convenience, tantivy also comes with a macro to
// reduce the boilerplate above.
index_writer.add_document(doc!(
name => "Cat",
classification => Facet::from("/Felidae/Felinae/Felis")
name => "the ditch",
tags => Facet::from("/pools/north")
));
index_writer.add_document(doc!(
name => "Canada lynx",
classification => Facet::from("/Felidae/Felinae/Lynx")
));
index_writer.add_document(doc!(
name => "Cheetah",
classification => Facet::from("/Felidae/Felinae/Acinonyx")
));
index_writer.add_document(doc!(
name => "Tiger",
classification => Facet::from("/Felidae/Pantherinae/Panthera")
));
index_writer.add_document(doc!(
name => "Lion",
classification => Facet::from("/Felidae/Pantherinae/Panthera")
));
index_writer.add_document(doc!(
name => "Jaguar",
classification => Facet::from("/Felidae/Pantherinae/Panthera")
));
index_writer.add_document(doc!(
name => "Sunda clouded leopard",
classification => Facet::from("/Felidae/Pantherinae/Neofelis")
));
index_writer.add_document(doc!(
name => "Fossa",
classification => Facet::from("/Eupleridae/Cryptoprocta")
name => "little stacey",
tags => Facet::from("/pools/south")
));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
{
let mut facet_collector = FacetCollector::for_field(classification);
facet_collector.add_facet("/Felidae");
let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
// This lists all of the facet counts, right below "/Felidae".
let facets: Vec<(&Facet, u64)> = facet_counts.get("/Felidae").collect();
assert_eq!(
facets,
vec![
(&Facet::from("/Felidae/Felinae"), 3),
(&Facet::from("/Felidae/Pantherinae"), 4),
]
);
}
// Facets are also searchable.
//
// For instance a common UI pattern is to allow the user someone to click on a facet link
// (e.g: `Pantherinae`) to drill down and filter the current result set with this subfacet.
//
// The search would then look as follows.
let mut facet_collector = FacetCollector::for_field(tags);
facet_collector.add_facet("/pools");
// Check the reference doc for different ways to create a `Facet` object.
{
let facet = Facet::from_text("/Felidae/Pantherinae");
let facet_term = Term::from_facet(classification, &facet);
let facet_term_query = TermQuery::new(facet_term, IndexRecordOption::Basic);
let mut facet_collector = FacetCollector::for_field(classification);
facet_collector.add_facet("/Felidae/Pantherinae");
let facet_counts = searcher.search(&facet_term_query, &facet_collector)?;
let facets: Vec<(&Facet, u64)> = facet_counts.get("/Felidae/Pantherinae").collect();
assert_eq!(
facets,
vec![
(&Facet::from("/Felidae/Pantherinae/Neofelis"), 1),
(&Facet::from("/Felidae/Pantherinae/Panthera"), 3),
]
);
}
let facet_counts = searcher.search(&AllQuery, &facet_collector).unwrap();
// This lists all of the facet counts
let facets: Vec<(&Facet, u64)> = facet_counts.get("/pools").collect();
assert_eq!(
facets,
vec![
(&Facet::from("/pools/north"), 1),
(&Facet::from("/pools/south"), 1),
]
);
Ok(())
}

View File

@@ -1,3 +0,0 @@
# Tantivy Query Grammar
This crate is used by tantivy to parse queries.

View File

@@ -452,11 +452,9 @@ impl FacetCounts {
#[cfg(test)]
mod tests {
use super::{FacetCollector, FacetCounts};
use crate::collector::Count;
use crate::core::Index;
use crate::query::{AllQuery, QueryParser, TermQuery};
use crate::schema::{Document, Facet, Field, IndexRecordOption, Schema};
use crate::Term;
use crate::query::AllQuery;
use crate::schema::{Document, Facet, Field, Schema};
use rand::distributions::Uniform;
use rand::prelude::SliceRandom;
use rand::{thread_rng, Rng};
@@ -546,56 +544,6 @@ mod tests {
assert_eq!(facets[0].1, 1);
}
#[test]
fn test_doc_search_by_facet() {
let mut schema_builder = Schema::builder();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/A"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/B"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/C/A"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/D/C/A"),
));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 4);
let count_facet = |facet_str: &str| {
let term = Term::from_facet(facet_field, &Facet::from_text(facet_str));
searcher
.search(&TermQuery::new(term, IndexRecordOption::Basic), &Count)
.unwrap()
};
assert_eq!(count_facet("/"), 4);
assert_eq!(count_facet("/A"), 3);
assert_eq!(count_facet("/A/B"), 1);
assert_eq!(count_facet("/A/C"), 1);
assert_eq!(count_facet("/A/C/A"), 1);
assert_eq!(count_facet("/C/A"), 0);
{
let query_parser = QueryParser::for_index(&index, vec![]);
{
let query = query_parser.parse_query("facet:/A/B").unwrap();
assert_eq!(1, searcher.search(&query, &Count).unwrap());
}
{
let query = query_parser.parse_query("facet:/A").unwrap();
assert_eq!(3, searcher.search(&query, &Count).unwrap());
}
}
}
#[test]
fn test_non_used_facet_collector() {
let mut facet_collector = FacetCollector::for_field(Field::from_field_id(0));

View File

@@ -186,7 +186,7 @@ mod test {
use super::{CompositeFile, CompositeWrite};
use crate::common::BinarySerializable;
use crate::common::VInt;
use crate::directory::{Directory, RAMDirectory, ReadOnlyDirectory};
use crate::directory::{Directory, RAMDirectory};
use crate::schema::Field;
use std::io::Write;
use std::path::Path;

View File

@@ -338,7 +338,7 @@ impl Index {
/// Creates a new segment.
pub fn new_segment(&self) -> Segment {
let mut segment_meta = self
let segment_meta = self
.inventory
.new_segment_meta(SegmentId::generate_random(), 0);
self.segment(segment_meta)

View File

@@ -35,7 +35,6 @@ impl SegmentMetaInventory {
segment_id,
max_doc,
deletes: None,
bundled: false,
};
SegmentMeta::from(self.inventory.track(inner))
}
@@ -82,19 +81,6 @@ impl SegmentMeta {
self.tracked.segment_id
}
pub fn with_bundled(self) -> SegmentMeta {
SegmentMeta::from(self.tracked.map(|inner| InnerSegmentMeta {
segment_id: inner.segment_id,
max_doc: inner.max_doc,
deletes: inner.deletes.clone(),
bundled: true,
}))
}
pub fn is_bundled(&self) -> bool {
self.tracked.bundled
}
/// Returns the number of deleted documents.
pub fn num_deleted_docs(&self) -> u32 {
self.tracked
@@ -121,12 +107,8 @@ impl SegmentMeta {
/// It just joins the segment id with the extension
/// associated to a segment component.
pub fn relative_path(&self, component: SegmentComponent) -> PathBuf {
let suffix = self.suffix(component);
self.relative_path_from_suffix(&suffix)
}
fn suffix(&self, component: SegmentComponent) -> String {
match component {
let mut path = self.id().uuid_string();
path.push_str(&*match component {
SegmentComponent::POSTINGS => ".idx".to_string(),
SegmentComponent::POSITIONS => ".pos".to_string(),
SegmentComponent::POSITIONSSKIP => ".posidx".to_string(),
@@ -135,17 +117,7 @@ impl SegmentMeta {
SegmentComponent::FASTFIELDS => ".fast".to_string(),
SegmentComponent::FIELDNORMS => ".fieldnorm".to_string(),
SegmentComponent::DELETE => format!(".{}.del", self.delete_opstamp().unwrap_or(0)),
}
}
/// Returns the relative path of a component of our segment.
///
/// It just joins the segment id with the extension
/// associated to a segment component.
pub fn relative_path_from_suffix(&self, suffix: &str) -> PathBuf {
let mut path = self.id().uuid_string();
path.push_str(".");
path.push_str(&suffix);
});
PathBuf::from(path)
}
@@ -189,7 +161,6 @@ impl SegmentMeta {
segment_id: inner_meta.segment_id,
max_doc,
deletes: None,
bundled: inner_meta.bundled,
});
SegmentMeta { tracked }
}
@@ -204,7 +175,6 @@ impl SegmentMeta {
segment_id: inner_meta.segment_id,
max_doc: inner_meta.max_doc,
deletes: Some(delete_meta),
bundled: inner_meta.bundled,
});
SegmentMeta { tracked }
}
@@ -215,7 +185,6 @@ struct InnerSegmentMeta {
segment_id: SegmentId,
max_doc: u32,
deletes: Option<DeleteMeta>,
bundled: bool,
}
impl InnerSegmentMeta {

View File

@@ -4,12 +4,14 @@ use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::directory::error::{OpenReadError, OpenWriteError};
use crate::directory::Directory;
use crate::directory::{ReadOnlyDirectory, ReadOnlySource, WritePtr};
use crate::directory::{ReadOnlySource, WritePtr};
use crate::indexer::segment_serializer::SegmentSerializer;
use crate::schema::Schema;
use crate::Opstamp;
use crate::Result;
use std::fmt;
use std::path::PathBuf;
use std::result;
/// A segment is a piece of the index.
#[derive(Clone)]
@@ -81,30 +83,23 @@ impl Segment {
}
/// Open one of the component file for a *regular* read.
pub fn open_read(&self, component: SegmentComponent) -> Result<ReadOnlySource, OpenReadError> {
pub fn open_read(
&self,
component: SegmentComponent,
) -> result::Result<ReadOnlySource, OpenReadError> {
let path = self.relative_path(component);
let source = self.index.directory().open_read(&path)?;
Ok(source)
}
/// Open one of the component file for *regular* write.
pub fn open_write(&mut self, component: SegmentComponent) -> Result<WritePtr, OpenWriteError> {
let path = self.relative_path(component);
self.index.directory_mut().open_write(&path)
}
pub fn open_bundle_writer(&mut self) -> Result<WritePtr, OpenWriteError> {
let path = self.meta.relative_path_from_suffix("bundle");
self.index.directory_mut().open_write(&path)
}
pub(crate) fn open_write_in_directory(
pub fn open_write(
&mut self,
component: SegmentComponent,
directory: &mut dyn Directory,
) -> Result<WritePtr, OpenWriteError> {
) -> result::Result<WritePtr, OpenWriteError> {
let path = self.relative_path(component);
directory.open_write(&path)
let write = self.index.directory_mut().open_write(&path)?;
Ok(write)
}
}
@@ -114,5 +109,5 @@ pub trait SerializableSegment {
///
/// # Returns
/// The number of documents in the segment.
fn write(&self, serializer: SegmentSerializer) -> crate::Result<u32>;
fn write(&self, serializer: SegmentSerializer) -> Result<u32>;
}

View File

@@ -1,97 +0,0 @@
use crate::directory::directory::ReadOnlyDirectory;
use crate::directory::error::OpenReadError;
use crate::directory::ReadOnlySource;
use crate::error::DataCorruption;
use std::collections::HashMap;
use std::path::{Path, PathBuf};
use std::sync::Arc;
#[derive(Clone)]
struct BundleDirectory {
source_map: Arc<HashMap<PathBuf, ReadOnlySource>>,
}
impl BundleDirectory {
pub fn from_source(source: ReadOnlySource) -> Result<BundleDirectory, DataCorruption> {
let mut index_offset_buf = [0u8; 8];
let (body_idx, footer_offset) = source.split_from_end(8);
index_offset_buf.copy_from_slice(footer_offset.as_slice());
let offset = u64::from_le_bytes(index_offset_buf);
let (body_source, idx_source) = body_idx.split(offset as usize);
let idx: HashMap<PathBuf, (u64, u64)> = serde_json::from_slice(idx_source.as_slice())
.map_err(|err| {
let msg = format!("Failed to read index from bundle. {:?}", err);
DataCorruption::comment_only(msg)
})?;
let source_map: HashMap<PathBuf, ReadOnlySource> = idx
.into_iter()
.map(|(path, (start, stop))| {
let source = body_source.slice(start as usize, stop as usize);
(path, source)
})
.collect();
Ok(BundleDirectory {
source_map: Arc::new(source_map),
})
}
}
impl ReadOnlyDirectory for BundleDirectory {
fn open_read(&self, path: &Path) -> Result<ReadOnlySource, OpenReadError> {
self.source_map
.get(path)
.cloned()
.ok_or_else(|| OpenReadError::FileDoesNotExist(path.to_path_buf()))
}
fn exists(&self, path: &Path) -> bool {
self.source_map.contains_key(path)
}
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError> {
let source = self
.source_map
.get(path)
.ok_or_else(|| OpenReadError::FileDoesNotExist(path.to_path_buf()))?;
Ok(source.as_slice().to_vec())
}
}
#[cfg(test)]
mod tests {
use super::BundleDirectory;
use crate::directory::{RAMDirectory, ReadOnlyDirectory, TerminatingWrite};
use crate::Directory;
use std::io::Write;
use std::path::Path;
#[test]
fn test_bundle_directory() {
let mut ram_directory = RAMDirectory::default();
let test_path_atomic = Path::new("testpath_atomic");
let test_path_wrt = Path::new("testpath_wrt");
assert!(ram_directory
.atomic_write(test_path_atomic, b"titi")
.is_ok());
{
let mut test_wrt = ram_directory.open_write(test_path_wrt).unwrap();
assert!(test_wrt.write_all(b"toto").is_ok());
assert!(test_wrt.terminate().is_ok());
}
let mut dest_directory = RAMDirectory::default();
let bundle_path = Path::new("bundle");
let mut wrt = dest_directory.open_write(bundle_path).unwrap();
assert!(ram_directory.serialize_bundle(&mut wrt).is_ok());
assert!(wrt.terminate().is_ok());
let source = dest_directory.open_read(bundle_path).unwrap();
let bundle_directory = BundleDirectory::from_source(source).unwrap();
assert_eq!(
&bundle_directory.atomic_read(test_path_atomic).unwrap()[..],
b"titi"
);
assert_eq!(
&bundle_directory.open_read(test_path_wrt).unwrap()[..],
b"toto"
);
}
}

View File

@@ -100,30 +100,6 @@ fn retry_policy(is_blocking: bool) -> RetryPolicy {
}
}
pub trait ReadOnlyDirectory {
/// Opens a virtual file for read.
///
/// Once a virtual file is open, its data may not
/// change.
///
/// Specifically, subsequent writes or flushes should
/// have no effect on the returned `ReadOnlySource` object.
///
/// You should only use this to read files create with [Directory::open_write].
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError>;
/// Returns true iff the file exists
fn exists(&self, path: &Path) -> bool;
/// Reads the full content file that has been written using
/// atomic_write.
///
/// This should only be used for small files.
///
/// You should only use this to read files create with [Directory::atomic_write].
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError>;
}
/// Write-once read many (WORM) abstraction for where
/// tantivy's data should be stored.
///
@@ -134,9 +110,18 @@ pub trait ReadOnlyDirectory {
/// - The [`RAMDirectory`](struct.RAMDirectory.html), which
/// should be used mostly for tests.
///
pub trait Directory:
DirectoryClone + ReadOnlyDirectory + fmt::Debug + Send + Sync + 'static
{
pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// Opens a virtual file for read.
///
/// Once a virtual file is open, its data may not
/// change.
///
/// Specifically, subsequent writes or flushes should
/// have no effect on the returned `ReadOnlySource` object.
///
/// You should only use this to read files create with [`open_write`]
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError>;
/// Removes a file
///
/// Removing a file will not affect an eventual
@@ -146,6 +131,9 @@ pub trait Directory:
/// `DeleteError::DoesNotExist`.
fn delete(&self, path: &Path) -> result::Result<(), DeleteError>;
/// Returns true iff the file exists
fn exists(&self, path: &Path) -> bool;
/// Opens a writer for the *virtual file* associated with
/// a Path.
///
@@ -167,6 +155,14 @@ pub trait Directory:
/// The file may not previously exist.
fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError>;
/// Reads the full content file that has been written using
/// atomic_write.
///
/// This should only be used for small files.
///
/// You should only use this to read files create with [`atomic_write`]
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError>;
/// Atomically replace the content of a file with data.
///
/// This calls ensure that reads can never *observe*
@@ -201,7 +197,7 @@ pub trait Directory:
/// Registers a callback that will be called whenever a change on the `meta.json`
/// using the `atomic_write` API is detected.
///
/// The behavior when using `.watch()` on a file using [Directory::open_write] is, on the other
/// The behavior when using `.watch()` on a file using `.open_write(...)` is, on the other
/// hand, undefined.
///
/// The file will be watched for the lifetime of the returned `WatchHandle`. The caller is

View File

@@ -1,4 +1,4 @@
use crate::Version;
use crate::directory::footer::Footer;
use std::error::Error as StdError;
use std::fmt;
use std::io;
@@ -157,65 +157,6 @@ impl StdError for OpenWriteError {
}
}
/// Type of index incompatibility between the library and the index found on disk
/// Used to catch and provide a hint to solve this incompatibility issue
pub enum Incompatibility {
/// This library cannot decompress the index found on disk
CompressionMismatch {
/// Compression algorithm used by the current version of tantivy
library_compression_format: String,
/// Compression algorithm that was used to serialise the index
index_compression_format: String,
},
/// The index format found on disk isn't supported by this version of the library
IndexMismatch {
/// Version used by the library
library_version: Version,
/// Version the index was built with
index_version: Version,
},
}
impl fmt::Debug for Incompatibility {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
match self {
Incompatibility::CompressionMismatch {
library_compression_format,
index_compression_format,
} => {
let err = format!(
"Library was compiled with {:?} compression, index was compressed with {:?}",
library_compression_format, index_compression_format
);
let advice = format!(
"Change the feature flag to {:?} and rebuild the library",
index_compression_format
);
write!(f, "{}. {}", err, advice)?;
}
Incompatibility::IndexMismatch {
library_version,
index_version,
} => {
let err = format!(
"Library version: {}, index version: {}",
library_version.index_format_version, index_version.index_format_version
);
// TODO make a more useful error message
// include the version range that supports this index_format_version
let advice = format!(
"Change tantivy to a version compatible with index format {} (e.g. {}.{}.x) \
and rebuild your project.",
index_version.index_format_version, index_version.major, index_version.minor
);
write!(f, "{}. {}", err, advice)?;
}
}
Ok(())
}
}
/// Error that may occur when accessing a file read
#[derive(Debug)]
pub enum OpenReadError {
@@ -224,8 +165,8 @@ pub enum OpenReadError {
/// Any kind of IO error that happens when
/// interacting with the underlying IO device.
IOError(IOError),
/// This library doesn't support the index version found on disk
IncompatibleIndex(Incompatibility),
/// The version of tantivy trying to read the index doesn't support its format
IncompatibleIndex(Footer),
}
impl From<IOError> for OpenReadError {
@@ -252,6 +193,20 @@ impl fmt::Display for OpenReadError {
}
}
impl StdError for OpenReadError {
fn description(&self) -> &str {
"error occurred while opening a file for reading"
}
fn cause(&self) -> Option<&dyn StdError> {
match *self {
OpenReadError::FileDoesNotExist(_) => None,
OpenReadError::IOError(ref err) => Some(err),
OpenReadError::IncompatibleIndex(_) => None,
}
}
}
/// Error that may occur when trying to delete a file
#[derive(Debug)]
pub enum DeleteError {
@@ -268,12 +223,6 @@ impl From<IOError> for DeleteError {
}
}
impl From<Incompatibility> for OpenReadError {
fn from(incompatibility: Incompatibility) -> Self {
OpenReadError::IncompatibleIndex(incompatibility)
}
}
impl fmt::Display for DeleteError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match *self {

View File

@@ -1,5 +1,4 @@
use crate::common::{BinarySerializable, CountingWriter, FixedSize, VInt};
use crate::directory::error::Incompatibility;
use crate::directory::read_only_source::ReadOnlySource;
use crate::directory::{AntiCallToken, TerminatingWrite};
use crate::Version;
@@ -18,11 +17,11 @@ pub struct Footer {
}
/// Serialises the footer to a byte-array
/// - versioned_footer_len : 4 bytes
/// - versioned_footer_len : 4bytes
///- versioned_footer: variable bytes
/// - meta_len: 4 bytes
/// - meta: variable bytes
/// - version_len: 4 bytes
/// - version_len: 4bytes
/// - version json: variable bytes
impl BinarySerializable for Footer {
fn serialize<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
@@ -87,25 +86,16 @@ impl Footer {
/// Confirms that the index will be read correctly by this version of tantivy
/// Has to be called after `extract_footer` to make sure it's not accessing uninitialised memory
pub fn is_compatible(&self) -> Result<(), Incompatibility> {
let library_version = crate::version();
pub fn is_compatible(&self) -> bool {
let version = &*crate::VERSION;
match &self.versioned_footer {
VersionedFooter::V1 {
crc32: _crc,
store_compression: compression,
crc32: _,
compression,
} => {
if &library_version.store_compression != compression {
return Err(Incompatibility::CompressionMismatch {
library_compression_format: library_version.store_compression.to_string(),
index_compression_format: compression.to_string(),
});
}
Ok(())
return compression == &version.store_compression;
}
VersionedFooter::UnknownVersion => Err(Incompatibility::IndexMismatch {
library_version: library_version.clone(),
index_version: self.version.clone(),
}),
VersionedFooter::UnknownVersion { version: _ } => false,
}
}
}
@@ -113,32 +103,31 @@ impl Footer {
/// Footer that includes a crc32 hash that enables us to checksum files in the index
#[derive(Debug, Clone, PartialEq)]
pub enum VersionedFooter {
UnknownVersion,
UnknownVersion {
version: u32,
},
V1 {
crc32: CrcHashU32,
store_compression: String,
compression: String,
},
}
impl BinarySerializable for VersionedFooter {
fn serialize<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
let mut buf = Vec::new();
BinarySerializable::serialize(&self.version(), &mut buf)?;
match self {
VersionedFooter::V1 {
crc32,
store_compression: compression,
} => {
VersionedFooter::V1 { crc32, compression } => {
// Serializes a valid `VersionedFooter` or panics if the version is unknown
// [ version | crc_hash | compression_mode ]
// [ 0..4 | 4..8 | variable ]
BinarySerializable::serialize(&1u32, &mut buf)?;
// [ 0..4 | 4..8 | variable ]
BinarySerializable::serialize(crc32, &mut buf)?;
BinarySerializable::serialize(compression, &mut buf)?;
}
VersionedFooter::UnknownVersion => {
VersionedFooter::UnknownVersion { version: _ } => {
return Err(io::Error::new(
io::ErrorKind::InvalidInput,
"Cannot serialize an unknown versioned footer ",
"Cannot serialize an unknown versionned footer ",
));
}
}
@@ -156,20 +145,30 @@ impl BinarySerializable for VersionedFooter {
if version == 1 {
let crc32 = u32::deserialize(&mut cursor)?;
let compression = String::deserialize(&mut cursor)?;
Ok(VersionedFooter::V1 {
crc32,
store_compression: compression,
})
Ok(VersionedFooter::V1 { crc32, compression })
} else {
Ok(VersionedFooter::UnknownVersion)
Ok(VersionedFooter::UnknownVersion { version })
}
}
}
impl VersionedFooter {
pub fn version(&self) -> u32 {
match self {
VersionedFooter::V1 {
crc32: _,
compression: _,
} => 1u32,
VersionedFooter::UnknownVersion { version, .. } => *version,
}
}
pub fn crc(&self) -> Option<CrcHashU32> {
match self {
VersionedFooter::V1 { crc32, .. } => Some(*crc32),
VersionedFooter::V1 {
crc32,
compression: _,
} => Some(*crc32),
VersionedFooter::UnknownVersion { .. } => None,
}
}
@@ -208,7 +207,7 @@ impl<W: TerminatingWrite> TerminatingWrite for FooterProxy<W> {
let crc32 = self.hasher.take().unwrap().finalize();
let footer = Footer::new(VersionedFooter::V1 {
crc32,
store_compression: crate::store::COMPRESSION.to_string(),
compression: crate::store::COMPRESSION.to_string(),
});
let mut writer = self.writer.take().unwrap();
footer.append_footer(&mut writer)?;
@@ -228,21 +227,16 @@ mod tests {
use regex::Regex;
#[test]
fn test_versioned_footer() {
fn test_footer_version() {
let mut vec = Vec::new();
let footer_proxy = FooterProxy::new(&mut vec);
assert!(footer_proxy.terminate().is_ok());
assert_eq!(vec.len(), 167);
let footer = Footer::deserialize(&mut &vec[..]).unwrap();
if let VersionedFooter::V1 {
crc32: _,
store_compression,
} = footer.versioned_footer
{
assert_eq!(store_compression, crate::store::COMPRESSION);
} else {
panic!("Versioned footer should be V1.");
}
assert_eq!(
footer.versioned_footer.version(),
crate::INDEX_FORMAT_VERSION
);
assert_eq!(&footer.version, crate::version());
}
@@ -252,7 +246,7 @@ mod tests {
let crc32 = 123456u32;
let footer: Footer = Footer::new(VersionedFooter::V1 {
crc32,
store_compression: "lz4".to_string(),
compression: "lz4".to_string(),
});
footer.serialize(&mut buffer).unwrap();
let footer_deser = Footer::deserialize(&mut &buffer[..]).unwrap();
@@ -261,10 +255,11 @@ mod tests {
#[test]
fn footer_length() {
// test to make sure the ascii art in the doc-strings is correct
let crc32 = 1111111u32;
let versioned_footer = VersionedFooter::V1 {
crc32,
store_compression: "lz4".to_string(),
compression: "lz4".to_string(),
};
let mut buf = Vec::new();
versioned_footer.serialize(&mut buf).unwrap();
@@ -304,7 +299,7 @@ mod tests {
let expected_crc: u32 = LittleEndian::read_u32(&v_footer_bytes[5..9]) as CrcHashU32;
let expected_versioned_footer: VersionedFooter = VersionedFooter::V1 {
crc32: expected_crc,
store_compression: "lz4".to_string(),
compression: "lz4".to_string(),
};
assert_eq!(versioned_footer, expected_versioned_footer);
let mut buffer = Vec::new();
@@ -318,22 +313,11 @@ mod tests {
let mut b = &v_footer_bytes[..];
let versioned_footer = VersionedFooter::deserialize(&mut b).unwrap();
assert!(b.is_empty());
let expected_versioned_footer = VersionedFooter::UnknownVersion;
let expected_versioned_footer = VersionedFooter::UnknownVersion {
version: 16_777_219u32,
};
assert_eq!(versioned_footer, expected_versioned_footer);
let mut buf = Vec::new();
assert!(versioned_footer.serialize(&mut buf).is_err());
}
#[test]
#[cfg(not(feature = "lz4"))]
fn compression_mismatch() {
let crc32 = 1111111u32;
let versioned_footer = VersionedFooter::V1 {
crc32,
store_compression: "lz4".to_string(),
};
let footer = Footer::new(versioned_footer);
let res = footer.is_compatible();
assert!(res.is_err());
}
}

View File

@@ -9,8 +9,8 @@ use crate::directory::{ReadOnlySource, WritePtr};
use crate::directory::{WatchCallback, WatchHandle};
use crate::error::DataCorruption;
use crate::Directory;
use crate::Result;
use crate::directory::directory::ReadOnlyDirectory;
use crc32fast::Hasher;
use serde_json;
use std::collections::HashSet;
@@ -66,7 +66,7 @@ fn save_managed_paths(
impl ManagedDirectory {
/// Wraps a directory as managed directory.
pub fn wrap<Dir: Directory>(directory: Dir) -> crate::Result<ManagedDirectory> {
pub fn wrap<Dir: Directory>(directory: Dir) -> Result<ManagedDirectory> {
match directory.atomic_read(&MANAGED_FILEPATH) {
Ok(data) => {
let managed_files_json = String::from_utf8_lossy(&data);
@@ -89,10 +89,8 @@ impl ManagedDirectory {
meta_informations: Arc::default(),
}),
Err(OpenReadError::IOError(e)) => Err(From::from(e)),
Err(OpenReadError::IncompatibleIndex(incompatibility)) => {
// For the moment, this should never happen `meta.json`
// do not have any footer and cannot detect incompatibility.
Err(crate::TantivyError::IncompatibleIndex(incompatibility))
Err(OpenReadError::IncompatibleIndex(footer)) => {
Err(crate::Error::IncompatibleIndex(format!("{:?}", footer)))
}
}
}
@@ -265,6 +263,16 @@ impl ManagedDirectory {
}
impl Directory for ManagedDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
let read_only_source = self.directory.open_read(path)?;
let (footer, reader) = Footer::extract_footer(read_only_source)
.map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
if !footer.is_compatible() {
return Err(OpenReadError::IncompatibleIndex(footer));
}
Ok(reader)
}
fn open_write(&mut self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
self.register_file_as_managed(path)
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
@@ -282,10 +290,18 @@ impl Directory for ManagedDirectory {
self.directory.atomic_write(path, data)
}
fn atomic_read(&self, path: &Path) -> result::Result<Vec<u8>, OpenReadError> {
self.directory.atomic_read(path)
}
fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
self.directory.delete(path)
}
fn exists(&self, path: &Path) -> bool {
self.directory.exists(path)
}
fn acquire_lock(&self, lock: &Lock) -> result::Result<DirectoryLock, LockError> {
self.directory.acquire_lock(lock)
}
@@ -295,24 +311,6 @@ impl Directory for ManagedDirectory {
}
}
impl ReadOnlyDirectory for ManagedDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
let read_only_source = self.directory.open_read(path)?;
let (footer, reader) = Footer::extract_footer(read_only_source)
.map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
footer.is_compatible()?;
Ok(reader)
}
fn exists(&self, path: &Path) -> bool {
self.directory.exists(path)
}
fn atomic_read(&self, path: &Path) -> result::Result<Vec<u8>, OpenReadError> {
self.directory.atomic_read(path)
}
}
impl Clone for ManagedDirectory {
fn clone(&self) -> ManagedDirectory {
ManagedDirectory {
@@ -326,9 +324,7 @@ impl Clone for ManagedDirectory {
#[cfg(test)]
mod tests_mmap_specific {
use crate::directory::{
Directory, ManagedDirectory, MmapDirectory, ReadOnlyDirectory, TerminatingWrite,
};
use crate::directory::{Directory, ManagedDirectory, MmapDirectory, TerminatingWrite};
use std::collections::HashSet;
use std::fs::OpenOptions;
use std::io::Write;

View File

@@ -6,7 +6,6 @@ use self::notify::RawEvent;
use self::notify::RecursiveMode;
use self::notify::Watcher;
use crate::core::META_FILEPATH;
use crate::directory::directory::ReadOnlyDirectory;
use crate::directory::error::LockError;
use crate::directory::error::{
DeleteError, IOError, OpenDirectoryError, OpenReadError, OpenWriteError,
@@ -132,13 +131,14 @@ impl MmapCache {
}
self.cache.remove(full_path);
self.counters.miss += 1;
let mmap_opt = open_mmap(full_path)?;
Ok(mmap_opt.map(|mmap| {
Ok(if let Some(mmap) = open_mmap(full_path)? {
let mmap_arc: Arc<BoxedData> = Arc::new(Box::new(mmap));
let mmap_weak = Arc::downgrade(&mmap_arc);
self.cache.insert(full_path.to_owned(), mmap_weak);
mmap_arc
}))
Some(mmap_arc)
} else {
None
})
}
}
@@ -408,6 +408,24 @@ impl TerminatingWrite for SafeFileWriter {
}
impl Directory for MmapDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
debug!("Open Read {:?}", path);
let full_path = self.resolve_path(path);
let mut mmap_cache = self.inner.mmap_cache.write().map_err(|_| {
let msg = format!(
"Failed to acquired write lock \
on mmap cache while reading {:?}",
path
);
IOError::with_path(path.to_owned(), make_io_err(msg))
})?;
Ok(mmap_cache
.get_mmap(&full_path)?
.map(ReadOnlySource::from)
.unwrap_or_else(ReadOnlySource::empty))
}
/// Any entry associated to the path in the mmap will be
/// removed before the file is deleted.
fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
@@ -426,6 +444,11 @@ impl Directory for MmapDirectory {
}
}
fn exists(&self, path: &Path) -> bool {
let full_path = self.resolve_path(path);
full_path.exists()
}
fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError> {
debug!("Open Write {:?}", path);
let full_path = self.resolve_path(path);
@@ -456,6 +479,25 @@ impl Directory for MmapDirectory {
Ok(BufWriter::new(Box::new(writer)))
}
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError> {
let full_path = self.resolve_path(path);
let mut buffer = Vec::new();
match File::open(&full_path) {
Ok(mut file) => {
file.read_to_end(&mut buffer)
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
Ok(buffer)
}
Err(e) => {
if e.kind() == io::ErrorKind::NotFound {
Err(OpenReadError::FileDoesNotExist(path.to_owned()))
} else {
Err(IOError::with_path(path.to_owned(), e).into())
}
}
}
}
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
debug!("Atomic Write {:?}", path);
let full_path = self.resolve_path(path);
@@ -489,50 +531,6 @@ impl Directory for MmapDirectory {
}
}
impl ReadOnlyDirectory for MmapDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
debug!("Open Read {:?}", path);
let full_path = self.resolve_path(path);
let mut mmap_cache = self.inner.mmap_cache.write().map_err(|_| {
let msg = format!(
"Failed to acquired write lock \
on mmap cache while reading {:?}",
path
);
IOError::with_path(path.to_owned(), make_io_err(msg))
})?;
Ok(mmap_cache
.get_mmap(&full_path)?
.map(ReadOnlySource::from)
.unwrap_or_else(ReadOnlySource::empty))
}
fn exists(&self, path: &Path) -> bool {
let full_path = self.resolve_path(path);
full_path.exists()
}
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError> {
let full_path = self.resolve_path(path);
let mut buffer = Vec::new();
match File::open(&full_path) {
Ok(mut file) => {
file.read_to_end(&mut buffer)
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
Ok(buffer)
}
Err(e) => {
if e.kind() == io::ErrorKind::NotFound {
Err(OpenReadError::FileDoesNotExist(path.to_owned()))
} else {
Err(IOError::with_path(path.to_owned(), e).into())
}
}
}
}
}
#[cfg(test)]
mod tests {

View File

@@ -7,7 +7,6 @@ WORM directory abstraction.
#[cfg(feature = "mmap")]
mod mmap_directory;
mod bundle_directory;
mod directory;
mod directory_lock;
mod footer;
@@ -20,13 +19,15 @@ mod watch_event_router;
pub mod error;
pub use self::directory::DirectoryLock;
pub use self::directory::{Directory, DirectoryClone, ReadOnlyDirectory};
pub use self::directory::{Directory, DirectoryClone};
pub use self::directory_lock::{Lock, INDEX_WRITER_LOCK, META_LOCK};
pub use self::ram_directory::RAMDirectory;
pub use self::read_only_source::ReadOnlySource;
pub use self::watch_event_router::{WatchCallback, WatchCallbackList, WatchHandle};
pub(crate) use self::watch_event_router::WatchCallbackList;
pub use self::watch_event_router::{WatchCallback, WatchHandle};
use std::io::{self, BufWriter, Write};
use std::path::PathBuf;
/// Outcome of the Garbage collection
pub struct GarbageCollectionResult {
/// List of files that were deleted in this cycle
@@ -47,9 +48,6 @@ pub use self::mmap_directory::MmapDirectory;
pub use self::managed_directory::ManagedDirectory;
/// Struct used to prevent from calling [`terminate_ref`](trait.TerminatingWrite#method.terminate_ref) directly
///
/// The point is that while the type is public, it cannot be built by anyone
/// outside of this module.
pub struct AntiCallToken(());
/// Trait used to indicate when no more write need to be done on a writer

View File

@@ -1,6 +1,4 @@
use crate::common::CountingWriter;
use crate::core::META_FILEPATH;
use crate::directory::directory::ReadOnlyDirectory;
use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError};
use crate::directory::AntiCallToken;
use crate::directory::WatchCallbackList;
@@ -117,22 +115,6 @@ impl InnerDirectory {
fn total_mem_usage(&self) -> usize {
self.fs.values().map(|f| f.len()).sum()
}
fn serialize_bundle(&self, wrt: &mut WritePtr) -> io::Result<()> {
let mut counting_writer = CountingWriter::wrap(wrt);
let mut file_index: HashMap<PathBuf, (u64, u64)> = HashMap::default();
for (path, source) in &self.fs {
let start = counting_writer.written_bytes();
counting_writer.write_all(source.as_slice())?;
let stop = counting_writer.written_bytes();
file_index.insert(path.to_path_buf(), (start, stop));
}
let index_offset = counting_writer.written_bytes();
serde_json::to_writer(&mut counting_writer, &file_index)?;
let index_offset_buffer = index_offset.to_le_bytes();
counting_writer.write_all(&index_offset_buffer[..])?;
Ok(())
}
}
impl fmt::Debug for RAMDirectory {
@@ -162,18 +144,13 @@ impl RAMDirectory {
pub fn total_mem_usage(&self) -> usize {
self.fs.read().unwrap().total_mem_usage()
}
/// Serialize the RAMDirectory into a bundle.
///
/// This method will fail, write nothing, and return an error if a
/// clone of this repository exists.
pub fn serialize_bundle(self, wrt: &mut WritePtr) -> io::Result<()> {
let inner_directory_rlock = self.fs.read().unwrap();
inner_directory_rlock.serialize_bundle(wrt)
}
}
impl Directory for RAMDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
self.fs.read().unwrap().open_read(path)
}
fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
fail_point!("RAMDirectory::delete", |_| {
use crate::directory::error::IOError;
@@ -183,6 +160,10 @@ impl Directory for RAMDirectory {
self.fs.write().unwrap().delete(path)
}
fn exists(&self, path: &Path) -> bool {
self.fs.read().unwrap().exists(path)
}
fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError> {
let mut fs = self.fs.write().unwrap();
let path_buf = PathBuf::from(path);
@@ -196,6 +177,10 @@ impl Directory for RAMDirectory {
}
}
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError> {
Ok(self.open_read(path)?.as_slice().to_owned())
}
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
fail_point!("RAMDirectory::atomic_write", |msg| Err(io::Error::new(
io::ErrorKind::Other,
@@ -219,17 +204,3 @@ impl Directory for RAMDirectory {
Ok(self.fs.write().unwrap().watch(watch_callback))
}
}
impl ReadOnlyDirectory for RAMDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
self.fs.read().unwrap().open_read(path)
}
fn exists(&self, path: &Path) -> bool {
self.fs.read().unwrap().exists(path)
}
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError> {
Ok(self.open_read(path)?.as_slice().to_owned())
}
}

View File

@@ -24,20 +24,13 @@ pub struct WatchCallbackList {
#[derive(Clone)]
pub struct WatchHandle(Arc<WatchCallback>);
impl WatchHandle {
/// Create a WatchHandle handle.
pub fn new(watch_callback: Arc<WatchCallback>) -> WatchHandle {
WatchHandle(watch_callback)
}
}
impl WatchCallbackList {
/// Suscribes a new callback and returns a handle that controls the lifetime of the callback.
pub fn subscribe(&self, watch_callback: WatchCallback) -> WatchHandle {
let watch_callback_arc = Arc::new(watch_callback);
let watch_callback_weak = Arc::downgrade(&watch_callback_arc);
self.router.write().unwrap().push(watch_callback_weak);
WatchHandle::new(watch_callback_arc)
WatchHandle(watch_callback_arc)
}
fn list_callback(&self) -> Vec<Arc<WatchCallback>> {

View File

@@ -2,8 +2,8 @@
use std::io;
use crate::directory::error::LockError;
use crate::directory::error::{IOError, OpenDirectoryError, OpenReadError, OpenWriteError};
use crate::directory::error::{Incompatibility, LockError};
use crate::fastfield::FastFieldNotAvailableError;
use crate::query;
use crate::schema;
@@ -25,10 +25,10 @@ impl DataCorruption {
}
}
pub fn comment_only<TS: ToString>(comment: TS) -> DataCorruption {
pub fn comment_only(comment: String) -> DataCorruption {
DataCorruption {
filepath: None,
comment: comment.to_string(),
comment,
}
}
}
@@ -81,8 +81,11 @@ pub enum TantivyError {
#[fail(display = "System error.'{}'", _0)]
SystemError(String),
/// Index incompatible with current version of tantivy
#[fail(display = "{:?}", _0)]
IncompatibleIndex(Incompatibility),
#[fail(
display = "Current version of tantivy is incompatible with index version: '{}'",
_0
)]
IncompatibleIndex(String),
}
impl From<DataCorruption> for TantivyError {
@@ -132,8 +135,8 @@ impl From<OpenReadError> for TantivyError {
match error {
OpenReadError::FileDoesNotExist(filepath) => TantivyError::PathDoesNotExist(filepath),
OpenReadError::IOError(io_error) => TantivyError::IOError(io_error),
OpenReadError::IncompatibleIndex(incompatibility) => {
TantivyError::IncompatibleIndex(incompatibility)
OpenReadError::IncompatibleIndex(tantivy_err) => {
TantivyError::IncompatibleIndex(format!("{:?}", tantivy_err))
}
}
}

View File

@@ -1,8 +1,9 @@
use crate::common::{BitSet, HasLen};
use crate::common::HasLen;
use crate::directory::ReadOnlySource;
use crate::directory::WritePtr;
use crate::space_usage::ByteCount;
use crate::DocId;
use bit_set::BitSet;
use std::io;
use std::io::Write;
@@ -16,7 +17,7 @@ pub fn write_delete_bitset(
) -> io::Result<()> {
let mut byte = 0u8;
let mut shift = 0u8;
for doc in 0..max_doc {
for doc in 0..(max_doc as usize) {
if delete_bitset.contains(doc) {
byte |= 1 << shift;
}
@@ -31,7 +32,7 @@ pub fn write_delete_bitset(
if max_doc % 8 > 0 {
writer.write_all(&[byte])?;
}
Ok(())
writer.flush()
}
/// Set of deleted `DocId`s.
@@ -85,6 +86,7 @@ impl HasLen for DeleteBitSet {
mod tests {
use super::*;
use crate::directory::*;
use bit_set::BitSet;
use std::path::PathBuf;
fn test_delete_bitset_helper(bitset: &BitSet, max_doc: u32) {
@@ -93,26 +95,27 @@ mod tests {
{
let mut writer = directory.open_write(&*test_path).unwrap();
write_delete_bitset(bitset, max_doc, &mut writer).unwrap();
writer.terminate().unwrap();
}
let source = directory.open_read(&test_path).unwrap();
let delete_bitset = DeleteBitSet::open(source);
for doc in 0..max_doc {
assert_eq!(bitset.contains(doc), delete_bitset.is_deleted(doc as DocId));
{
let source = directory.open_read(&test_path).unwrap();
let delete_bitset = DeleteBitSet::open(source);
for doc in 0..max_doc as usize {
assert_eq!(bitset.contains(doc), delete_bitset.is_deleted(doc as DocId));
}
assert_eq!(delete_bitset.len(), bitset.len());
}
assert_eq!(delete_bitset.len(), bitset.len());
}
#[test]
fn test_delete_bitset() {
{
let mut bitset = BitSet::with_max_value(10);
let mut bitset = BitSet::with_capacity(10);
bitset.insert(1);
bitset.insert(9);
test_delete_bitset_helper(&bitset, 10);
}
{
let mut bitset = BitSet::with_max_value(8);
let mut bitset = BitSet::with_capacity(8);
bitset.insert(1);
bitset.insert(2);
bitset.insert(3);

View File

@@ -33,7 +33,6 @@ pub use self::reader::FastFieldReader;
pub use self::readers::FastFieldReaders;
pub use self::serializer::FastFieldSerializer;
pub use self::writer::{FastFieldsWriter, IntFastFieldWriter};
use crate::chrono::{NaiveDateTime, Utc};
use crate::common;
use crate::schema::Cardinality;
use crate::schema::FieldType;
@@ -50,7 +49,7 @@ mod serializer;
mod writer;
/// Trait for types that are allowed for fast fields: (u64, i64 and f64).
pub trait FastValue: Clone + Copy + Send + Sync + PartialOrd {
pub trait FastValue: Default + Clone + Copy + Send + Sync + PartialOrd {
/// Converts a value from u64
///
/// Internally all fast field values are encoded as u64.
@@ -70,12 +69,6 @@ pub trait FastValue: Clone + Copy + Send + Sync + PartialOrd {
/// Cast value to `u64`.
/// The value is just reinterpreted in memory.
fn as_u64(&self) -> u64;
/// Build a default value. This default value is never used, so the value does not
/// really matter.
fn make_zero() -> Self {
Self::from_u64(0i64.to_u64())
}
}
impl FastValue for u64 {
@@ -142,34 +135,11 @@ impl FastValue for f64 {
}
}
impl FastValue for crate::DateTime {
fn from_u64(timestamp_u64: u64) -> Self {
let timestamp_i64 = i64::from_u64(timestamp_u64);
crate::DateTime::from_utc(NaiveDateTime::from_timestamp(timestamp_i64, 0), Utc)
}
fn to_u64(&self) -> u64 {
self.timestamp().to_u64()
}
fn fast_field_cardinality(field_type: &FieldType) -> Option<Cardinality> {
match *field_type {
FieldType::Date(ref integer_options) => integer_options.get_fastfield_cardinality(),
_ => None,
}
}
fn as_u64(&self) -> u64 {
self.timestamp().as_u64()
}
}
fn value_to_u64(value: &Value) -> u64 {
match *value {
Value::U64(ref val) => *val,
Value::I64(ref val) => common::i64_to_u64(*val),
Value::F64(ref val) => common::f64_to_u64(*val),
Value::Date(ref datetime) => common::i64_to_u64(datetime.timestamp()),
_ => panic!("Expected a u64/i64/f64 field, got {:?} ", value),
}
}
@@ -179,14 +149,12 @@ mod tests {
use super::*;
use crate::common::CompositeFile;
use crate::directory::{Directory, RAMDirectory, ReadOnlyDirectory, WritePtr};
use crate::directory::{Directory, RAMDirectory, WritePtr};
use crate::fastfield::FastFieldReader;
use crate::merge_policy::NoMergePolicy;
use crate::schema::Document;
use crate::schema::Field;
use crate::schema::Schema;
use crate::schema::FAST;
use crate::schema::{Document, IntOptions};
use crate::{Index, SegmentId, SegmentReader};
use once_cell::sync::Lazy;
use rand::prelude::SliceRandom;
use rand::rngs::StdRng;
@@ -210,12 +178,6 @@ mod tests {
assert_eq!(test_fastfield.get(2), 300);
}
#[test]
pub fn test_fastfield_i64_u64() {
let datetime = crate::DateTime::from_utc(NaiveDateTime::from_timestamp(0i64, 0), Utc);
assert_eq!(i64::from_u64(datetime.to_u64()), 0i64);
}
#[test]
fn test_intfastfield_small() {
let path = Path::new("test");
@@ -467,93 +429,6 @@ mod tests {
}
}
}
#[test]
fn test_merge_missing_date_fast_field() {
let mut schema_builder = Schema::builder();
let date_field = schema_builder.add_date_field("date", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.set_merge_policy(Box::new(NoMergePolicy));
index_writer.add_document(doc!(date_field =>crate::chrono::prelude::Utc::now()));
index_writer.commit().unwrap();
index_writer.add_document(doc!());
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let segment_ids: Vec<SegmentId> = reader
.searcher()
.segment_readers()
.iter()
.map(SegmentReader::segment_id)
.collect();
assert_eq!(segment_ids.len(), 2);
let merge_future = index_writer.merge(&segment_ids[..]);
let merge_res = futures::executor::block_on(merge_future);
assert!(merge_res.is_ok());
assert!(reader.reload().is_ok());
assert_eq!(reader.searcher().segment_readers().len(), 1);
}
#[test]
fn test_default_datetime() {
assert_eq!(crate::DateTime::make_zero().timestamp(), 0i64);
}
#[test]
fn test_datefastfield() {
use crate::fastfield::FastValue;
let mut schema_builder = Schema::builder();
let date_field = schema_builder.add_date_field("date", FAST);
let multi_date_field = schema_builder.add_date_field(
"multi_date",
IntOptions::default().set_fast(Cardinality::MultiValues),
);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.set_merge_policy(Box::new(NoMergePolicy));
index_writer.add_document(doc!(
date_field => crate::DateTime::from_u64(1i64.to_u64()),
multi_date_field => crate::DateTime::from_u64(2i64.to_u64()),
multi_date_field => crate::DateTime::from_u64(3i64.to_u64())
));
index_writer.add_document(doc!(
date_field => crate::DateTime::from_u64(4i64.to_u64())
));
index_writer.add_document(doc!(
multi_date_field => crate::DateTime::from_u64(5i64.to_u64()),
multi_date_field => crate::DateTime::from_u64(6i64.to_u64())
));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
let segment_reader = searcher.segment_reader(0);
let fast_fields = segment_reader.fast_fields();
let date_fast_field = fast_fields.date(date_field).unwrap();
let dates_fast_field = fast_fields.dates(multi_date_field).unwrap();
let mut dates = vec![];
{
assert_eq!(date_fast_field.get(0u32).timestamp(), 1i64);
dates_fast_field.get_vals(0u32, &mut dates);
assert_eq!(dates.len(), 2);
assert_eq!(dates[0].timestamp(), 2i64);
assert_eq!(dates[1].timestamp(), 3i64);
}
{
assert_eq!(date_fast_field.get(1u32).timestamp(), 4i64);
dates_fast_field.get_vals(1u32, &mut dates);
assert!(dates.is_empty());
}
{
assert_eq!(date_fast_field.get(2u32).timestamp(), 0i64);
dates_fast_field.get_vals(2u32, &mut dates);
assert_eq!(dates.len(), 2);
assert_eq!(dates[0].timestamp(), 5i64);
assert_eq!(dates[1].timestamp(), 6i64);
}
}
}
#[cfg(all(test, feature = "unstable"))]

View File

@@ -45,7 +45,7 @@ impl<Item: FastValue> MultiValueIntFastFieldReader<Item> {
pub fn get_vals(&self, doc: DocId, vals: &mut Vec<Item>) {
let (start, stop) = self.range(doc);
let len = (stop - start) as usize;
vals.resize(len, Item::make_zero());
vals.resize(len, Item::default());
self.vals_reader.get_range_u64(start, &mut vals[..]);
}

View File

@@ -4,7 +4,7 @@ use crate::common::compute_num_bits;
use crate::common::BinarySerializable;
use crate::common::CompositeFile;
use crate::directory::ReadOnlySource;
use crate::directory::{Directory, RAMDirectory, ReadOnlyDirectory, WritePtr};
use crate::directory::{Directory, RAMDirectory, WritePtr};
use crate::fastfield::{FastFieldSerializer, FastFieldsWriter};
use crate::schema::Schema;
use crate::schema::FAST;

View File

@@ -15,11 +15,9 @@ pub struct FastFieldReaders {
fast_field_i64: HashMap<Field, FastFieldReader<i64>>,
fast_field_u64: HashMap<Field, FastFieldReader<u64>>,
fast_field_f64: HashMap<Field, FastFieldReader<f64>>,
fast_field_date: HashMap<Field, FastFieldReader<crate::DateTime>>,
fast_field_i64s: HashMap<Field, MultiValueIntFastFieldReader<i64>>,
fast_field_u64s: HashMap<Field, MultiValueIntFastFieldReader<u64>>,
fast_field_f64s: HashMap<Field, MultiValueIntFastFieldReader<f64>>,
fast_field_dates: HashMap<Field, MultiValueIntFastFieldReader<crate::DateTime>>,
fast_bytes: HashMap<Field, BytesFastFieldReader>,
fast_fields_composite: CompositeFile,
}
@@ -28,7 +26,6 @@ enum FastType {
I64,
U64,
F64,
Date,
}
fn type_and_cardinality(field_type: &FieldType) -> Option<(FastType, Cardinality)> {
@@ -42,9 +39,6 @@ fn type_and_cardinality(field_type: &FieldType) -> Option<(FastType, Cardinality
FieldType::F64(options) => options
.get_fastfield_cardinality()
.map(|cardinality| (FastType::F64, cardinality)),
FieldType::Date(options) => options
.get_fastfield_cardinality()
.map(|cardinality| (FastType::Date, cardinality)),
FieldType::HierarchicalFacet => Some((FastType::U64, Cardinality::MultiValues)),
_ => None,
}
@@ -59,11 +53,9 @@ impl FastFieldReaders {
fast_field_i64: Default::default(),
fast_field_u64: Default::default(),
fast_field_f64: Default::default(),
fast_field_date: Default::default(),
fast_field_i64s: Default::default(),
fast_field_u64s: Default::default(),
fast_field_f64s: Default::default(),
fast_field_dates: Default::default(),
fast_bytes: Default::default(),
fast_fields_composite: fast_fields_composite.clone(),
};
@@ -103,12 +95,6 @@ impl FastFieldReaders {
FastFieldReader::open(fast_field_data.clone()),
);
}
FastType::Date => {
fast_field_readers.fast_field_date.insert(
field,
FastFieldReader::open(fast_field_data.clone()),
);
}
}
} else {
return Err(From::from(FastFieldNotAvailableError::new(field_entry)));
@@ -144,14 +130,6 @@ impl FastFieldReaders {
.fast_field_f64s
.insert(field, multivalued_int_fast_field);
}
FastType::Date => {
let vals_reader = FastFieldReader::open(fast_field_data);
let multivalued_int_fast_field =
MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
fast_field_readers
.fast_field_dates
.insert(field, multivalued_int_fast_field);
}
}
} else {
return Err(From::from(FastFieldNotAvailableError::new(field_entry)));
@@ -178,6 +156,8 @@ impl FastFieldReaders {
/// If the field is a i64-fast field, return the associated u64 reader. Values are
/// mapped from i64 to u64 using a (well the, it is unique) monotonic mapping. ///
///
///TODO should it also be lenient with f64?
///
/// This method is useful when merging segment reader.
pub(crate) fn u64_lenient(&self, field: Field) -> Option<FastFieldReader<u64>> {
if let Some(u64_ff_reader) = self.u64(field) {
@@ -186,12 +166,6 @@ impl FastFieldReaders {
if let Some(i64_ff_reader) = self.i64(field) {
return Some(i64_ff_reader.into_u64_reader());
}
if let Some(f64_ff_reader) = self.f64(field) {
return Some(f64_ff_reader.into_u64_reader());
}
if let Some(date_ff_reader) = self.date(field) {
return Some(date_ff_reader.into_u64_reader());
}
None
}
@@ -202,13 +176,6 @@ impl FastFieldReaders {
self.fast_field_i64.get(&field).cloned()
}
/// Returns the `i64` fast field reader reader associated to `field`.
///
/// If `field` is not a i64 fast field, this method returns `None`.
pub fn date(&self, field: Field) -> Option<FastFieldReader<crate::DateTime>> {
self.fast_field_date.get(&field).cloned()
}
/// Returns the `f64` fast field reader reader associated to `field`.
///
/// If `field` is not a f64 fast field, this method returns `None`.
@@ -235,9 +202,6 @@ impl FastFieldReaders {
if let Some(i64s_ff_reader) = self.i64s(field) {
return Some(i64s_ff_reader.into_u64s_reader());
}
if let Some(f64s_ff_reader) = self.f64s(field) {
return Some(f64s_ff_reader.into_u64s_reader());
}
None
}
@@ -255,13 +219,6 @@ impl FastFieldReaders {
self.fast_field_f64s.get(&field).cloned()
}
/// Returns a `crate::DateTime` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a `crate::DateTime` multi-valued fast field, this method returns `None`.
pub fn dates(&self, field: Field) -> Option<MultiValueIntFastFieldReader<crate::DateTime>> {
self.fast_field_dates.get(&field).cloned()
}
/// Returns the `bytes` fast field reader associated to `field`.
///
/// If `field` is not a bytes fast field, returns `None`.

View File

@@ -4,7 +4,7 @@ use crate::common::BinarySerializable;
use crate::common::VInt;
use crate::fastfield::{BytesFastFieldWriter, FastFieldSerializer};
use crate::postings::UnorderedTermId;
use crate::schema::{Cardinality, Document, Field, FieldEntry, FieldType, Schema};
use crate::schema::{Cardinality, Document, Field, FieldType, Schema};
use crate::termdict::TermOrdinal;
use fnv::FnvHashMap;
use std::collections::HashMap;
@@ -17,14 +17,6 @@ pub struct FastFieldsWriter {
bytes_value_writers: Vec<BytesFastFieldWriter>,
}
fn fast_field_default_value(field_entry: &FieldEntry) -> u64 {
match *field_entry.field_type() {
FieldType::I64(_) | FieldType::Date(_) => common::i64_to_u64(0i64),
FieldType::F64(_) => common::f64_to_u64(0.0f64),
_ => 0u64,
}
}
impl FastFieldsWriter {
/// Create all `FastFieldWriter` required by the schema.
pub fn from_schema(schema: &Schema) -> FastFieldsWriter {
@@ -33,15 +25,18 @@ impl FastFieldsWriter {
let mut bytes_value_writers = Vec::new();
for (field, field_entry) in schema.fields() {
let default_value = match *field_entry.field_type() {
FieldType::I64(_) => common::i64_to_u64(0i64),
FieldType::F64(_) => common::f64_to_u64(0.0f64),
_ => 0u64,
};
match *field_entry.field_type() {
FieldType::I64(ref int_options)
| FieldType::U64(ref int_options)
| FieldType::F64(ref int_options)
| FieldType::Date(ref int_options) => {
| FieldType::F64(ref int_options) => {
match int_options.get_fastfield_cardinality() {
Some(Cardinality::SingleValue) => {
let mut fast_field_writer = IntFastFieldWriter::new(field);
let default_value = fast_field_default_value(field_entry);
fast_field_writer.set_val_if_missing(default_value);
single_value_writers.push(fast_field_writer);
}

View File

@@ -1,7 +1,6 @@
use super::operation::{AddOperation, UserOperation};
use super::segment_updater::SegmentUpdater;
use super::PreparedCommit;
use crate::common::BitSet;
use crate::core::Index;
use crate::core::Segment;
use crate::core::SegmentComponent;
@@ -24,6 +23,7 @@ use crate::schema::Document;
use crate::schema::IndexRecordOption;
use crate::schema::Term;
use crate::Opstamp;
use bit_set::BitSet;
use crossbeam::channel;
use futures::executor::block_on;
use futures::future::Future;
@@ -115,7 +115,7 @@ fn compute_deleted_bitset(
while docset.advance() {
let deleted_doc = docset.doc();
if deleted_doc < limit_doc {
delete_bitset.insert(deleted_doc);
delete_bitset.insert(deleted_doc as usize);
might_have_changed = true;
}
}
@@ -126,60 +126,51 @@ fn compute_deleted_bitset(
Ok(might_have_changed)
}
/// Advance delete for the given segment up to the target opstamp.
///
/// Note that there are no guarantee that the resulting `segment_entry` delete_opstamp
/// is `==` target_opstamp.
/// For instance, there was no delete operation between the state of the `segment_entry` and
/// the `target_opstamp`, `segment_entry` is not updated.
/// Advance delete for the given segment up
/// to the target opstamp.
pub(crate) fn advance_deletes(
mut segment: Segment,
segment_entry: &mut SegmentEntry,
target_opstamp: Opstamp,
) -> crate::Result<()> {
if segment_entry.meta().delete_opstamp() == Some(target_opstamp) {
// We are already up-to-date here.
return Ok(());
}
{
if segment_entry.meta().delete_opstamp() == Some(target_opstamp) {
// We are already up-to-date here.
return Ok(());
}
if segment_entry.delete_bitset().is_none() && segment_entry.delete_cursor().get().is_none() {
// There has been no `DeleteOperation` between the segment status and `target_opstamp`.
return Ok(());
}
let segment_reader = SegmentReader::open(&segment)?;
let segment_reader = SegmentReader::open(&segment)?;
let max_doc = segment_reader.max_doc();
let mut delete_bitset: BitSet = match segment_entry.delete_bitset() {
Some(previous_delete_bitset) => (*previous_delete_bitset).clone(),
None => BitSet::with_capacity(max_doc as usize),
};
let max_doc = segment_reader.max_doc();
let mut delete_bitset: BitSet = match segment_entry.delete_bitset() {
Some(previous_delete_bitset) => (*previous_delete_bitset).clone(),
None => BitSet::with_max_value(max_doc),
};
let delete_cursor = segment_entry.delete_cursor();
compute_deleted_bitset(
&mut delete_bitset,
&segment_reader,
delete_cursor,
&DocToOpstampMapping::None,
target_opstamp,
)?;
compute_deleted_bitset(
&mut delete_bitset,
&segment_reader,
segment_entry.delete_cursor(),
&DocToOpstampMapping::None,
target_opstamp,
)?;
// TODO optimize
if let Some(seg_delete_bitset) = segment_reader.delete_bitset() {
// TODO optimize
for doc in 0u32..max_doc {
if seg_delete_bitset.is_deleted(doc) {
delete_bitset.insert(doc);
if segment_reader.is_deleted(doc) {
delete_bitset.insert(doc as usize);
}
}
}
let num_deleted_docs = delete_bitset.len();
if num_deleted_docs > 0 {
segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp);
let mut delete_file = segment.open_write(SegmentComponent::DELETE)?;
write_delete_bitset(&delete_bitset, max_doc, &mut delete_file)?;
delete_file.terminate()?;
let num_deleted_docs = delete_bitset.len();
if num_deleted_docs > 0 {
segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp);
let mut delete_file = segment.open_write(SegmentComponent::DELETE)?;
write_delete_bitset(&delete_bitset, max_doc, &mut delete_file)?;
delete_file.terminate()?;
}
}
segment_entry.set_meta(segment.meta().clone());
Ok(())
}
@@ -245,7 +236,7 @@ fn apply_deletes(
mut delete_cursor: &mut DeleteCursor,
doc_opstamps: &[Opstamp],
last_docstamp: Opstamp,
) -> crate::Result<Option<BitSet>> {
) -> crate::Result<Option<BitSet<u32>>> {
if delete_cursor.get().is_none() {
// if there are no delete operation in the queue, no need
// to even open the segment.
@@ -255,7 +246,7 @@ fn apply_deletes(
let doc_to_opstamps = DocToOpstampMapping::from(doc_opstamps);
let max_doc = segment.meta().max_doc();
let mut deleted_bitset = BitSet::with_max_value(max_doc);
let mut deleted_bitset = BitSet::with_capacity(max_doc as usize);
let may_have_deletes = compute_deleted_bitset(
&mut deleted_bitset,
&segment_reader,
@@ -514,13 +505,9 @@ impl IndexWriter {
/// Merges a given list of segments
///
/// `segment_ids` is required to be non-empty.
pub fn merge(
&mut self,
segment_ids: &[SegmentId],
) -> impl Future<Output = crate::Result<SegmentMeta>> {
pub async fn merge(&mut self, segment_ids: &[SegmentId]) -> crate::Result<SegmentMeta> {
let merge_operation = self.segment_updater.make_merge_operation(segment_ids);
let segment_updater = self.segment_updater.clone();
async move { segment_updater.start_merge(merge_operation)?.await }
self.segment_updater.start_merge(merge_operation)?.await
}
/// Closes the current document channel send.

View File

@@ -1492,46 +1492,4 @@ mod tests {
assert_eq!(&vals, &[20]);
}
}
#[test]
fn merges_f64_fast_fields_correctly() -> crate::Result<()> {
let mut builder = schema::SchemaBuilder::new();
let fast_multi = IntOptions::default().set_fast(Cardinality::MultiValues);
let field = builder.add_f64_field("f64", schema::FAST);
let multi_field = builder.add_f64_field("f64s", fast_multi);
let index = Index::create_in_ram(builder.build());
let mut writer = index.writer_with_num_threads(1, 3_000_000)?;
// Make sure we'll attempt to merge every created segment
let mut policy = crate::indexer::LogMergePolicy::default();
policy.set_min_merge_size(2);
writer.set_merge_policy(Box::new(policy));
for i in 0..100 {
let mut doc = Document::new();
doc.add_f64(field, 42.0);
doc.add_f64(multi_field, 0.24);
doc.add_f64(multi_field, 0.27);
writer.add_document(doc);
if i % 5 == 0 {
writer.commit()?;
}
}
writer.commit()?;
writer.wait_merging_threads()?;
// If a merging thread fails, we should end up with more
// than one segment here
assert_eq!(1, index.searchable_segments()?.len());
Ok(())
}
}

View File

@@ -33,7 +33,6 @@ pub type DefaultMergePolicy = LogMergePolicy;
mod tests {
use crate::schema::{self, Schema};
use crate::{Index, Term};
#[test]
fn test_advance_delete_bug() {
let mut schema_builder = Schema::builder();

View File

@@ -1,7 +1,7 @@
use crate::common::BitSet;
use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::indexer::delete_queue::DeleteCursor;
use bit_set::BitSet;
use std::fmt;
/// A segment entry describes the state of

View File

@@ -1,13 +1,10 @@
use crate::Directory;
use crate::Result;
use crate::core::Segment;
use crate::core::SegmentComponent;
use crate::directory::error::OpenWriteError;
use crate::directory::{DirectoryClone, RAMDirectory, TerminatingWrite, WritePtr};
use crate::fastfield::FastFieldSerializer;
use crate::fieldnorm::FieldNormsSerializer;
use crate::postings::InvertedIndexSerializer;
use crate::schema::Schema;
use crate::store::StoreWriter;
/// Segment serializer is in charge of laying out on disk
@@ -17,50 +14,25 @@ pub struct SegmentSerializer {
fast_field_serializer: FastFieldSerializer,
fieldnorms_serializer: FieldNormsSerializer,
postings_serializer: InvertedIndexSerializer,
bundle_writer: Option<(RAMDirectory, WritePtr)>,
}
pub(crate) struct SegmentSerializerWriters {
postings_wrt: WritePtr,
positions_skip_wrt: WritePtr,
positions_wrt: WritePtr,
terms_wrt: WritePtr,
fast_field_wrt: WritePtr,
fieldnorms_wrt: WritePtr,
store_wrt: WritePtr,
}
impl SegmentSerializerWriters {
pub(crate) fn for_segment(segment: &mut Segment) -> Result<Self, OpenWriteError> {
Ok(SegmentSerializerWriters {
postings_wrt: segment.open_write(SegmentComponent::POSTINGS)?,
positions_skip_wrt: segment.open_write(SegmentComponent::POSITIONS)?,
positions_wrt: segment.open_write(SegmentComponent::POSITIONSSKIP)?,
terms_wrt: segment.open_write(SegmentComponent::TERMS)?,
fast_field_wrt: segment.open_write(SegmentComponent::FASTFIELDS)?,
fieldnorms_wrt: segment.open_write(SegmentComponent::FIELDNORMS)?,
store_wrt: segment.open_write(SegmentComponent::STORE)?,
})
}
}
impl SegmentSerializer {
pub(crate) fn new(schema: Schema, writers: SegmentSerializerWriters) -> crate::Result<Self> {
let fast_field_serializer = FastFieldSerializer::from_write(writers.fast_field_wrt)?;
let fieldnorms_serializer = FieldNormsSerializer::from_write(writers.fieldnorms_wrt)?;
let postings_serializer = InvertedIndexSerializer::open(
schema,
writers.terms_wrt,
writers.postings_wrt,
writers.positions_wrt,
writers.positions_skip_wrt,
);
/// Creates a new `SegmentSerializer`.
pub fn for_segment(segment: &mut Segment) -> Result<SegmentSerializer> {
let store_write = segment.open_write(SegmentComponent::STORE)?;
let fast_field_write = segment.open_write(SegmentComponent::FASTFIELDS)?;
let fast_field_serializer = FastFieldSerializer::from_write(fast_field_write)?;
let fieldnorms_write = segment.open_write(SegmentComponent::FIELDNORMS)?;
let fieldnorms_serializer = FieldNormsSerializer::from_write(fieldnorms_write)?;
let postings_serializer = InvertedIndexSerializer::open(segment)?;
Ok(SegmentSerializer {
store_writer: StoreWriter::new(writers.store_wrt),
store_writer: StoreWriter::new(store_write),
fast_field_serializer,
fieldnorms_serializer,
postings_serializer,
bundle_writer: None,
})
}
@@ -85,15 +57,11 @@ impl SegmentSerializer {
}
/// Finalize the segment serialization.
pub fn close(mut self) -> crate::Result<()> {
pub fn close(self) -> Result<()> {
self.fast_field_serializer.close()?;
self.postings_serializer.close()?;
self.store_writer.close()?;
self.fieldnorms_serializer.close()?;
if let Some((ram_directory, mut bundle_wrt)) = self.bundle_writer.take() {
ram_directory.serialize_bundle(&mut bundle_wrt)?;
bundle_wrt.terminate()?;
}
Ok(())
}
}

View File

@@ -12,7 +12,6 @@ use crate::indexer::index_writer::advance_deletes;
use crate::indexer::merge_operation::MergeOperationInventory;
use crate::indexer::merger::IndexMerger;
use crate::indexer::segment_manager::SegmentsStatus;
use crate::indexer::segment_serializer::SegmentSerializerWriters;
use crate::indexer::stamper::Stamper;
use crate::indexer::SegmentEntry;
use crate::indexer::SegmentSerializer;
@@ -133,9 +132,7 @@ fn merge(
let merger: IndexMerger = IndexMerger::open(index.schema(), &segments[..])?;
// ... we just serialize this index merger in our new segment to merge the two segments.
let segment_serializer_wrts = SegmentSerializerWriters::for_segment(&mut merged_segment)?;
let segment_serializer =
SegmentSerializer::new(merged_segment.schema(), segment_serializer_wrts)?;
let segment_serializer = SegmentSerializer::for_segment(&mut merged_segment)?;
let num_docs = merger.write(segment_serializer)?;
@@ -217,10 +214,6 @@ impl SegmentUpdater {
self.pool.spawn_ok(async move {
let _ = sender.send(f.await);
});
} else {
let _ = sender.send(Err(crate::TantivyError::SystemError(
"Segment updater killed".to_string(),
)));
}
receiver.unwrap_or_else(|_| {
let err_msg =
@@ -333,11 +326,13 @@ impl SegmentUpdater {
) -> impl Future<Output = crate::Result<()>> {
let segment_updater: SegmentUpdater = self.clone();
self.schedule_future(async move {
let segment_entries = segment_updater.purge_deletes(opstamp)?;
segment_updater.segment_manager.commit(segment_entries);
segment_updater.save_metas(opstamp, payload)?;
let _ = garbage_collect_files(segment_updater.clone()).await;
segment_updater.consider_merge_options().await;
if segment_updater.is_alive() {
let segment_entries = segment_updater.purge_deletes(opstamp)?;
segment_updater.segment_manager.commit(segment_entries);
segment_updater.save_metas(opstamp, payload)?;
let _ = garbage_collect_files(segment_updater.clone()).await;
segment_updater.consider_merge_options().await;
}
Ok(())
})
}

View File

@@ -3,7 +3,7 @@ use crate::core::Segment;
use crate::core::SerializableSegment;
use crate::fastfield::FastFieldsWriter;
use crate::fieldnorm::FieldNormsWriter;
use crate::indexer::segment_serializer::{SegmentSerializer, SegmentSerializerWriters};
use crate::indexer::segment_serializer::SegmentSerializer;
use crate::postings::compute_table_size;
use crate::postings::MultiFieldPostingsWriter;
use crate::schema::FieldType;
@@ -69,8 +69,7 @@ impl SegmentWriter {
schema: &Schema,
) -> Result<SegmentWriter> {
let table_num_bits = initial_table_size(memory_budget)?;
let segment_serializer_wrts = SegmentSerializerWriters::for_segment(&mut segment)?;
let segment_serializer = SegmentSerializer::new(segment.schema(), segment_serializer_wrts)?;
let segment_serializer = SegmentSerializer::for_segment(&mut segment)?;
let multifield_postings = MultiFieldPostingsWriter::new(schema, table_num_bits);
let tokenizers = schema
.fields()

View File

@@ -173,7 +173,6 @@ use std::fmt;
use once_cell::sync::Lazy;
/// Index format version.
const INDEX_FORMAT_VERSION: u32 = 1;
/// Structure version for the index.
@@ -940,73 +939,4 @@ mod tests {
assert_eq!(fast_field_reader.get(0), 4f64)
}
}
// motivated by #729
#[test]
fn test_update_via_delete_insert() {
use crate::collector::Count;
use crate::indexer::NoMergePolicy;
use crate::query::AllQuery;
use crate::SegmentId;
use futures::executor::block_on;
const DOC_COUNT: u64 = 2u64;
let mut schema_builder = SchemaBuilder::default();
let id = schema_builder.add_u64_field("id", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema.clone());
let index_reader = index.reader().unwrap();
let mut index_writer = index.writer(3_000_000).unwrap();
index_writer.set_merge_policy(Box::new(NoMergePolicy));
for doc_id in 0u64..DOC_COUNT {
index_writer.add_document(doc!(id => doc_id));
}
index_writer.commit().unwrap();
index_reader.reload().unwrap();
let searcher = index_reader.searcher();
assert_eq!(
searcher.search(&AllQuery, &Count).unwrap(),
DOC_COUNT as usize
);
// update the 10 elements by deleting and re-adding
for doc_id in 0u64..DOC_COUNT {
index_writer.delete_term(Term::from_field_u64(id, doc_id));
index_writer.commit().unwrap();
index_reader.reload().unwrap();
let doc = doc!(id => doc_id);
index_writer.add_document(doc);
index_writer.commit().unwrap();
index_reader.reload().unwrap();
let searcher = index_reader.searcher();
// The number of document should be stable.
assert_eq!(
searcher.search(&AllQuery, &Count).unwrap(),
DOC_COUNT as usize
);
}
index_reader.reload().unwrap();
let searcher = index_reader.searcher();
let segment_ids: Vec<SegmentId> = searcher
.segment_readers()
.into_iter()
.map(|reader| reader.segment_id())
.collect();
block_on(index_writer.merge(&segment_ids)).unwrap();
index_reader.reload().unwrap();
let searcher = index_reader.searcher();
assert_eq!(
searcher.search(&AllQuery, &Count).unwrap(),
DOC_COUNT as usize
);
}
}

View File

@@ -75,7 +75,7 @@ pub mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut segment = index.new_segment();
let mut posting_serializer = InvertedIndexSerializer::for_segment(&mut segment).unwrap();
let mut posting_serializer = InvertedIndexSerializer::open(&mut segment).unwrap();
{
let mut field_serializer = posting_serializer.new_field(text_field, 120 * 4).unwrap();
field_serializer.new_term("abc".as_bytes()).unwrap();

View File

@@ -10,8 +10,8 @@ use crate::postings::USE_SKIP_INFO_LIMIT;
use crate::schema::Schema;
use crate::schema::{Field, FieldEntry, FieldType};
use crate::termdict::{TermDictionaryBuilder, TermOrdinal};
use crate::DocId;
use crate::Result;
use crate::{Directory, DocId};
use std::io::{self, Write};
/// `InvertedIndexSerializer` is in charge of serializing
@@ -54,36 +54,33 @@ pub struct InvertedIndexSerializer {
}
impl InvertedIndexSerializer {
pub(crate) fn for_segment(segment: &mut Segment) -> crate::Result<Self> {
let schema = segment.schema();
use crate::core::SegmentComponent;
let terms_wrt = segment.open_write(SegmentComponent::TERMS)?;
let postings_wrt = segment.open_write(SegmentComponent::POSTINGS)?;
let positions_wrt = segment.open_write(SegmentComponent::POSITIONS)?;
let positions_idx_wrt = segment.open_write(SegmentComponent::POSITIONSSKIP)?;
Ok(Self::open(
schema,
terms_wrt,
postings_wrt,
positions_wrt,
positions_idx_wrt,
))
}
/// Open a new `PostingsSerializer` for the given segment
pub(crate) fn open(
/// Open a new `InvertedIndexSerializer` for the given segment
fn create(
terms_write: CompositeWrite<WritePtr>,
postings_write: CompositeWrite<WritePtr>,
positions_write: CompositeWrite<WritePtr>,
positionsidx_write: CompositeWrite<WritePtr>,
schema: Schema,
terms_wrt: WritePtr,
postings_wrt: WritePtr,
positions_wrt: WritePtr,
positions_idx_wrt: WritePtr,
) -> InvertedIndexSerializer {
InvertedIndexSerializer {
terms_write: CompositeWrite::wrap(terms_wrt),
postings_write: CompositeWrite::wrap(postings_wrt),
positions_write: CompositeWrite::wrap(positions_wrt),
positionsidx_write: CompositeWrite::wrap(positions_idx_wrt),
) -> Result<InvertedIndexSerializer> {
Ok(InvertedIndexSerializer {
terms_write,
postings_write,
positions_write,
positionsidx_write,
schema,
}
})
}
/// Open a new `PostingsSerializer` for the given segment
pub fn open(segment: &mut Segment) -> Result<InvertedIndexSerializer> {
use crate::SegmentComponent::{POSITIONS, POSITIONSSKIP, POSTINGS, TERMS};
InvertedIndexSerializer::create(
CompositeWrite::wrap(segment.open_write(TERMS)?),
CompositeWrite::wrap(segment.open_write(POSTINGS)?),
CompositeWrite::wrap(segment.open_write(POSITIONS)?),
CompositeWrite::wrap(segment.open_write(POSITIONSSKIP)?),
segment.schema(),
)
}
/// Must be called before starting pushing terms of

View File

@@ -8,7 +8,7 @@ use crate::query::PhraseQuery;
use crate::query::Query;
use crate::query::RangeQuery;
use crate::query::TermQuery;
use crate::schema::{Facet, IndexRecordOption};
use crate::schema::IndexRecordOption;
use crate::schema::{Field, Schema};
use crate::schema::{FieldType, Term};
use crate::tokenizer::TokenizerManager;
@@ -319,10 +319,7 @@ impl QueryParser {
))
}
}
FieldType::HierarchicalFacet => {
let facet = Facet::from_text(phrase);
Ok(vec![(0, Term::from_field_text(field, facet.encoded_str()))])
}
FieldType::HierarchicalFacet => Ok(vec![(0, Term::from_field_text(field, phrase))]),
FieldType::Bytes => {
let field_name = self.schema.get_field_name(field).to_string();
Err(QueryParserError::FieldNotIndexed(field_name))
@@ -557,7 +554,6 @@ mod test {
schema_builder.add_text_field("with_stop_words", text_options);
schema_builder.add_date_field("date", INDEXED);
schema_builder.add_f64_field("float", INDEXED);
schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let default_fields = vec![title, text];
let tokenizer_manager = TokenizerManager::default();
@@ -592,13 +588,9 @@ mod test {
}
#[test]
pub fn test_parse_query_facet() {
pub fn test_parse_query_simple() {
let query_parser = make_query_parser();
let query = query_parser.parse_query("facet:/root/branch/leaf").unwrap();
assert_eq!(
format!("{:?}", query),
"TermQuery(Term(field=11,bytes=[114, 111, 111, 116, 0, 98, 114, 97, 110, 99, 104, 0, 108, 101, 97, 102]))"
);
assert!(query_parser.parse_query("toto").is_ok());
}
#[test]

View File

@@ -166,7 +166,7 @@ impl SchemaBuilder {
}
/// Adds a field entry to the schema in build.
pub fn add_field(&mut self, field_entry: FieldEntry) -> Field {
fn add_field(&mut self, field_entry: FieldEntry) -> Field {
let field = Field::from_field_id(self.fields.len() as u32);
let field_name = field_entry.name().to_string();
self.fields.push(field_entry);
@@ -401,7 +401,6 @@ pub enum DocParsingError {
mod tests {
use crate::schema::field_type::ValueParsingError;
use crate::schema::int_options::Cardinality::SingleValue;
use crate::schema::schema::DocParsingError::NotJSON;
use crate::schema::*;
use matches::{assert_matches, matches};
@@ -716,94 +715,4 @@ mod tests {
assert_matches!(json_err, Err(NotJSON(_)));
}
}
#[test]
pub fn test_schema_add_field() {
let mut schema_builder = SchemaBuilder::default();
let id_options = TextOptions::default().set_stored().set_indexing_options(
TextFieldIndexing::default()
.set_tokenizer("raw")
.set_index_option(IndexRecordOption::Basic),
);
let timestamp_options = IntOptions::default()
.set_stored()
.set_indexed()
.set_fast(SingleValue);
schema_builder.add_text_field("_id", id_options);
schema_builder.add_date_field("_timestamp", timestamp_options);
let schema_content = r#"[
{
"name": "text",
"type": "text",
"options": {
"indexing": {
"record": "position",
"tokenizer": "default"
},
"stored": false
}
},
{
"name": "popularity",
"type": "i64",
"options": {
"indexed": false,
"fast": "single",
"stored": true
}
}
]"#;
let tmp_schema: Schema =
serde_json::from_str(&schema_content).expect("error while reading json");
for (_field, field_entry) in tmp_schema.fields() {
schema_builder.add_field(field_entry.clone());
}
let schema = schema_builder.build();
let schema_json = serde_json::to_string_pretty(&schema).unwrap();
let expected = r#"[
{
"name": "_id",
"type": "text",
"options": {
"indexing": {
"record": "basic",
"tokenizer": "raw"
},
"stored": true
}
},
{
"name": "_timestamp",
"type": "date",
"options": {
"indexed": true,
"fast": "single",
"stored": true
}
},
{
"name": "text",
"type": "text",
"options": {
"indexing": {
"record": "position",
"tokenizer": "default"
},
"stored": false
}
},
{
"name": "popularity",
"type": "i64",
"options": {
"indexed": false,
"fast": "single",
"stored": true
}
}
]"#;
assert_eq!(schema_json, expected);
}
}

View File

@@ -209,8 +209,8 @@ impl From<f64> for Value {
}
}
impl From<crate::DateTime> for Value {
fn from(date_time: crate::DateTime) -> Value {
impl From<DateTime> for Value {
fn from(date_time: DateTime) -> Value {
Value::Date(date_time)
}
}

View File

@@ -5,7 +5,7 @@ use std::io::{self, Read, Write};
/// Name of the compression scheme used in the doc store.
///
/// This name is appended to the version string of tantivy.
pub const COMPRESSION: &str = "snappy";
pub const COMPRESSION: &'static str = "snappy";
pub fn compress(uncompressed: &[u8], compressed: &mut Vec<u8>) -> io::Result<()> {
compressed.clear();

View File

@@ -57,7 +57,7 @@ use self::compression_snap::{compress, decompress};
pub mod tests {
use super::*;
use crate::directory::{Directory, RAMDirectory, ReadOnlyDirectory, WritePtr};
use crate::directory::{Directory, RAMDirectory, WritePtr};
use crate::schema::Document;
use crate::schema::FieldValue;
use crate::schema::Schema;

View File

@@ -36,7 +36,7 @@ pub use self::termdict::{TermDictionary, TermDictionaryBuilder};
mod tests {
use super::{TermDictionary, TermDictionaryBuilder, TermStreamer};
use crate::core::Index;
use crate::directory::{Directory, RAMDirectory, ReadOnlyDirectory, ReadOnlySource};
use crate::directory::{Directory, RAMDirectory, ReadOnlySource};
use crate::postings::TermInfo;
use crate::schema::{Document, FieldType, Schema, TEXT};
use std::path::PathBuf;

View File

@@ -1,8 +1,6 @@
use fail;
use std::path::Path;
use tantivy::directory::{
Directory, ManagedDirectory, RAMDirectory, ReadOnlyDirectory, TerminatingWrite,
};
use tantivy::directory::{Directory, ManagedDirectory, RAMDirectory, TerminatingWrite};
use tantivy::doc;
use tantivy::schema::{Schema, TEXT};
use tantivy::{Index, Term};