web search done right
rustup update and fix clippy
Mikkel Denkeree0fc39eaa18
diff --git a/crates/core/src/ampc/dht/mod.rs b/crates/core/src/ampc/dht/mod.rsindex 92036334..e3910068 100644--- a/crates/core/src/ampc/dht/mod.rs+++ b/crates/core/src/ampc/dht/mod.rs@@ -15,8 +15,10 @@// along with this program. If not, see <https://www.gnu.org/licenses/>.//! Simple in-memory key-value store with Raft consensus where keys-//! and values are arbitrary bytes. It is intended to be deployed-//! across multiple nodes with multiple shards. Each shard cluster+//! and values are arbitrary bytes.+//!+//! It is intended to be deployed across multiple nodes+//! with multiple shards. Each shard cluster//! is a Raft cluster, and each key is then routed to the correct//! cluster based on hash(key) % number_of_shards. The keys//! are currently *not* rebalanced if the number of shards change, sodiff --git a/crates/core/src/autosuggest.rs b/crates/core/src/autosuggest.rsindex 99b359a4..2640be66 100644--- a/crates/core/src/autosuggest.rs+++ b/crates/core/src/autosuggest.rs@@ -16,6 +16,7 @@//! Autosuggest provides the functionality for the little dropdown that appears//! when you type something into the search bar and queries are suggested.+//!//! It uses a finite state transducer (fst) to store popular queries//! and performs a prefix search on the fst to find suggestions.diff --git a/crates/core/src/inverted_index/mod.rs b/crates/core/src/inverted_index/mod.rsindex 621084ed..3db081b5 100644--- a/crates/core/src/inverted_index/mod.rs+++ b/crates/core/src/inverted_index/mod.rs@@ -15,6 +15,7 @@// along with this program. If not, see <https://www.gnu.org/licenses/>.//! The inverted index is the main data structure of the search engine.+//!//! It is a mapping from terms to a list of documents. Imagine a hash map//! { term -> \[doc1, doc2, doc3\] } etc. During search, we look up the terms//! from the query in the index and perform an intersection of the lists ofdiff --git a/crates/file-store/src/iterable.rs b/crates/file-store/src/iterable.rsindex 212848f7..54abca10 100644--- a/crates/file-store/src/iterable.rs+++ b/crates/file-store/src/iterable.rs@@ -15,6 +15,7 @@// along with this program. If not, see <https://www.gnu.org/licenses/>//! This module contains the implementation of the `IterableStoreWriter` and `IterableStoreReader`.+//!//! The iterable store is a simple format for storing a sequence of items in a file such that they//! can be read back in order. The format is as follows://!diff --git a/crates/file-store/src/peekable.rs b/crates/file-store/src/peekable.rsindex 1509ef65..5b76be57 100644--- a/crates/file-store/src/peekable.rs+++ b/crates/file-store/src/peekable.rs@@ -15,6 +15,7 @@// along with this program. If not, see <https://www.gnu.org/licenses//// An iterator that allows peeking at the next element.+////// Unlike the standard library's `Peekable`, this implementation/// *is not* lazy and will always consume the next element when peeking./// This is useful when you want to peek at the next element withoutdiff --git a/crates/tantivy/src/collector/filter_collector_wrapper.rs b/crates/tantivy/src/collector/filter_collector_wrapper.rsindex c7b78e4a..9979437f 100644--- a/crates/tantivy/src/collector/filter_collector_wrapper.rs+++ b/crates/tantivy/src/collector/filter_collector_wrapper.rs@@ -142,8 +142,9 @@ where}}-/// A variant of the [`FilterCollector`] specialized for bytes columnar fields, i.e.-/// it transparently wraps an inner [`Collector`] but filters documents+/// A variant of the [`FilterCollector`] specialized for bytes columnar fields.+///+/// It transparently wraps an inner [`Collector`] but filters documents/// based on the result of applying the predicate to the bytes columnar field.////// A document is accepted if and only if the predicate returns `true` for at least one value.diff --git a/crates/tantivy/src/directory/directory_lock.rs b/crates/tantivy/src/directory/directory_lock.rsindex 67a4cada..89c0a3f1 100644--- a/crates/tantivy/src/directory/directory_lock.rs+++ b/crates/tantivy/src/directory/directory_lock.rs@@ -48,6 +48,7 @@ pub static INDEX_WRITER_LOCK: LazyLock<Lock> = LazyLock::new(|| Lock {});/// The meta lock file is here to protect the segment files being opened by/// `IndexReader::reload()` from being garbage collected.+////// It makes it possible for another process to safely consume/// our index in-writing. Ideally, we may have preferred `RWLock` semantics/// here, but it is difficult to achieve on Windows.diff --git a/crates/tantivy/src/index/segment_component.rs b/crates/tantivy/src/index/segment_component.rsindex e39e48af..4378de56 100644--- a/crates/tantivy/src/index/segment_component.rs+++ b/crates/tantivy/src/index/segment_component.rs@@ -1,6 +1,7 @@use std::slice;/// Enum describing each component of a tantivy segment.+////// Each component is stored in its own file,/// using the pattern `segment_uuid`.`component_extension`,/// except the delete component that takes an `segment_uuid`.`delete_opstamp`.`component_extension`diff --git a/crates/tantivy/src/positions/mod.rs b/crates/tantivy/src/positions/mod.rsindex cd98eb69..2f2ff318 100644--- a/crates/tantivy/src/positions/mod.rs+++ b/crates/tantivy/src/positions/mod.rs@@ -1,4 +1,5 @@//! Tantivy can (if instructed to do so in the schema) store the term positions in a given field.+//!//! This position is expressed as token ordinal. For instance,//! In "The beauty and the beast", the term "the" appears in position 0 and position 3.//! This information is useful to run phrase queries.diff --git a/crates/tantivy/src/query/grammar/infallible.rs b/crates/tantivy/src/query/grammar/infallible.rsindex 0bc0fb8b..043b42e1 100644--- a/crates/tantivy/src/query/grammar/infallible.rs+++ b/crates/tantivy/src/query/grammar/infallible.rs@@ -113,7 +113,6 @@ wheremove |input: I| match f.parse(input) {Ok((input, (output, _err))) => Ok((input, output)),Err(Err::Incomplete(needed)) => Err(Err::Incomplete(needed)),- Err(Err::Error(val)) | Err(Err::Failure(val)) => match val {},}}diff --git a/crates/tantivy/src/query/phrase_prefix_query/phrase_prefix_scorer.rs b/crates/tantivy/src/query/phrase_prefix_query/phrase_prefix_scorer.rsindex 4e76d492..ccb0e080 100644--- a/crates/tantivy/src/query/phrase_prefix_query/phrase_prefix_scorer.rs+++ b/crates/tantivy/src/query/phrase_prefix_query/phrase_prefix_scorer.rs@@ -12,7 +12,7 @@ enum PhraseKind<TPostings: Postings> {postings: TPostings,positions: Vec<u32>,},- MultiPrefix(PhraseScorer<TPostings>),+ MultiPrefix(Box<PhraseScorer<TPostings>>),}impl<TPostings: Postings> PhraseKind<TPostings> {@@ -117,13 +117,13 @@ impl<TPostings: Postings> PhrasePrefixScorer<TPostings> {.unwrap();let phrase_scorer = if term_postings.len() > 1 {- PhraseKind::MultiPrefix(PhraseScorer::new_with_offset(+ PhraseKind::MultiPrefix(Box::new(PhraseScorer::new_with_offset(term_postings,similarity_weight_opt,fieldnorm_reader,0,1,- ))+ )))} else {let (pos, postings) = term_postings.pop()diff --git a/crates/tantivy/src/schema/term.rs b/crates/tantivy/src/schema/term.rsindex 07a89600..ceecd51d 100644--- a/crates/tantivy/src/schema/term.rs+++ b/crates/tantivy/src/schema/term.rs@@ -302,6 +302,7 @@ where}/// ValueBytes represents a serialized value.+////// The value can be of any type of [`Type`] (e.g. string, u64, f64, bool, date, JSON)./// The serialized representation matches the lexographical order of the type.///diff --git a/crates/tantivy/src/snippet/mod.rs b/crates/tantivy/src/snippet/mod.rsindex 38059a1a..20c0e395 100644--- a/crates/tantivy/src/snippet/mod.rs+++ b/crates/tantivy/src/snippet/mod.rs@@ -1,5 +1,6 @@//! [`SnippetGenerator`]//! Generates a text snippet for a given document, and some highlighted parts inside it.+//!//! Imagine you doing a text search in a document//! and want to show a preview of where in the document the search terms occur,//! along with some surrounding text to give context, and the search terms highlighted.diff --git a/crates/tantivy/src/tokenizer/regex_tokenizer.rs b/crates/tantivy/src/tokenizer/regex_tokenizer.rsindex f4a608b3..a771e42d 100644--- a/crates/tantivy/src/tokenizer/regex_tokenizer.rs+++ b/crates/tantivy/src/tokenizer/regex_tokenizer.rs@@ -4,6 +4,7 @@ use super::{Token, TokenStream, Tokenizer};use crate::TantivyError;/// Tokenize the text by using a regex pattern to split.+////// Each match of the regex emits a distinct token, empty tokens will not be emitted. Anchors such/// as `\A` will match the text from the part where the last token was emitted or the beginning of/// the complete text if no token was emitted yet.