nidx-binding 6.3.1.post46__tar.gz → 6.3.1.post48__tar.gz

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/Cargo.lock

@@ -1,6 +1,6 @@
 # This file is automatically @generated by Cargo.
 # It is not intended for manual editing.
-version = 3
+version = 4
 
 [[package]]
 name = "addr2line"
@@ -2838,9 +2838,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3"
-version = "0.22.6"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f402062616ab18202ae8319da13fa4279883a2b8a9d9f83f20dbade813ce1884"
+checksum = "7778bffd85cf38175ac1f545509665d0b9b92a198ca7941f131f85f7a4f9a872"
 dependencies = [
  "cfg-if",
  "indoc",
@@ -2856,9 +2856,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-build-config"
-version = "0.22.6"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b14b5775b5ff446dd1056212d778012cbe8a0fbffd368029fd9e25b514479c38"
+checksum = "94f6cbe86ef3bf18998d9df6e0f3fc1050a8c5efa409bf712e661a4366e010fb"
 dependencies = [
  "once_cell",
  "target-lexicon",
@@ -2866,9 +2866,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-ffi"
-version = "0.22.6"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9ab5bcf04a2cdcbb50c7d6105de943f543f9ed92af55818fd17b660390fc8636"
+checksum = "e9f1b4c431c0bb1c8fb0a338709859eed0d030ff6daa34368d3b152a63dfdd8d"
 dependencies = [
  "libc",
  "pyo3-build-config",
@@ -2876,9 +2876,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros"
-version = "0.22.6"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0fd24d897903a9e6d80b968368a34e1525aeb719d568dba8b3d4bfa5dc67d453"
+checksum = "fbc2201328f63c4710f68abdf653c89d8dbc2858b88c5d88b0ff38a75288a9da"
 dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
@@ -2888,9 +2888,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros-backend"
-version = "0.22.6"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "36c011a03ba1e50152b4b394b479826cad97e7a21eb52df179cd91ac411cbfbe"
+checksum = "fca6726ad0f3da9c9de093d6f116a93c1a38e417ed73bf138472cf4064f72028"
 dependencies = [
  "heck",
  "proc-macro2",

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "nidx"
 version = "0.1.0"
-edition = "2021"
+edition = "2024"
 license = "AGPL-3.0"
 
 [[bin]]

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nidx_binding
-Version: 6.3.1.post46
+Version: 6.3.1.post48
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/nidx_binding/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "nidx_binding"
 version = "0.1.0"
-edition = "2021"
+edition = "2024"
 license = "AGPL-3.0"
 
 [lib]
@@ -12,7 +12,7 @@ crate-type = ["cdylib"]
 anyhow = "1.0.93"
 nidx = { version = "0.1.0", path = "..", default-features = false }
 nidx_protos = { version = "0.1.0", path = "../nidx_protos" }
-pyo3 = "0.22.0"
+pyo3 = "0.23"
 tempfile = "3.14.0"
 tokio = "1.41.1"
 tokio-util = { version = "0.7.12", features = ["io", "io-util", "compat"] }

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/nidx_binding/src/lib.rs

@@ -23,21 +23,21 @@ use nidx::worker;
 use pyo3::exceptions::PyException;
 use pyo3::prelude::*;
 
+use nidx::Settings;
 use nidx::api::grpc::ApiServer;
 use nidx::grpc_server::GrpcServer;
 use nidx::indexer::process_index_message;
 use nidx::searcher::grpc::SearchServer;
 use nidx::searcher::{SyncStatus, SyncedSearcher};
 use nidx::settings::EnvSettings;
-use nidx::Settings;
-use nidx_protos::prost::*;
 use nidx_protos::IndexMessage;
+use nidx_protos::prost::*;
 use std::collections::HashMap;
-use std::sync::atomic::AtomicI64;
 use std::sync::Arc;
-use tempfile::{tempdir, TempDir};
+use std::sync::atomic::AtomicI64;
+use tempfile::{TempDir, tempdir};
 use tokio::runtime::Runtime;
-use tokio::sync::mpsc::{channel, Sender};
+use tokio::sync::mpsc::{Sender, channel};
 use tokio::sync::watch;
 use tokio_util::sync::CancellationToken;
 
@@ -112,9 +112,15 @@ impl NidxBinding {
     pub fn wait_for_sync(&mut self) {
         self.runtime.as_ref().unwrap().block_on(async {
             // Wait for a new sync to start
-            self.sync_watcher.wait_for(|s| matches!(s, SyncStatus::Syncing)).await.unwrap();
+            self.sync_watcher
+                .wait_for(|s| matches!(s, SyncStatus::Syncing))
+                .await
+                .unwrap();
             // Wait for it to finish
-            self.sync_watcher.wait_for(|s| matches!(s, SyncStatus::Synced)).await.unwrap();
+            self.sync_watcher
+                .wait_for(|s| matches!(s, SyncStatus::Synced))
+                .await
+                .unwrap();
         });
     }
 }

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/nidx_paragraph/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "nidx_paragraph"
 version = "0.1.0"
-edition = "2021"
+edition = "2024"
 license = "AGPL-3.0"
 
 [dependencies]

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/nidx_paragraph/src/fuzzy_query.rs

@@ -44,12 +44,12 @@ use std::io;
 use std::ops::Range;
 use std::sync::Arc;
 
-use levenshtein_automata::{Distance, LevenshteinAutomatonBuilder, DFA};
+use levenshtein_automata::{DFA, Distance, LevenshteinAutomatonBuilder};
 use once_cell::sync::Lazy;
+use tantivy::TantivyError::InvalidArgument;
 use tantivy::query::{BitSetDocSet, ConstScorer, EnableScoring, Explanation, Query, Scorer, Weight};
 use tantivy::schema::{Field, IndexRecordOption, Term};
 use tantivy::termdict::{TermDictionary, TermStreamer};
-use tantivy::TantivyError::InvalidArgument;
 use tantivy::{DocId, DocSet, Score, SegmentReader, TantivyError};
 use tantivy_common::BitSet;
 use tantivy_fst::Automaton;
@@ -224,7 +224,11 @@ impl FuzzyTermQuery {
                 } else {
                     automaton_builder.build_dfa(term_text)
                 };
-                Ok(AutomatonWeight::new(self.term.field(), DfaWrapper(automaton), self.termc.clone()))
+                Ok(AutomatonWeight::new(
+                    self.term.field(),
+                    DfaWrapper(automaton),
+                    self.termc.clone(),
+                ))
             }
             None => Err(InvalidArgument(format!(
                 "Levenshtein distance of {} is not allowed. Choose a value in the {:?} range",

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/nidx_paragraph/src/lib.rs

@@ -31,20 +31,20 @@ mod stop_words;
 
 use nidx_protos::{ParagraphItem, ParagraphSearchResponse, StreamRequest};
 use nidx_tantivy::{
-    index_reader::{open_index_with_deletions, DeletionQueryBuilder},
     TantivyIndexer, TantivyMeta, TantivySegmentMetadata,
+    index_reader::{DeletionQueryBuilder, open_index_with_deletions},
 };
-use nidx_types::{prefilter::PrefilterResult, OpenIndexMetadata};
+use nidx_types::{OpenIndexMetadata, prefilter::PrefilterResult};
 use reader::ParagraphReaderService;
 use resource_indexer::index_paragraphs;
 use schema::ParagraphSchema;
 use std::path::Path;
 use tantivy::{
+    Term,
     directory::MmapDirectory,
     indexer::merge_indices,
     query::{Query, TermSetQuery},
     schema::{Field, Schema},
-    Term,
 };
 use tracing::instrument;
 
@@ -61,11 +61,7 @@ impl DeletionQueryBuilder for ParagraphDeletionQueryBuilder {
         Box::new(TermSetQuery::new(keys.map(|k| {
             // Our keys can be resource or field ids, match the corresponding tantivy field
             let is_field = k.len() > 32;
-            let tantivy_field = if is_field {
-                self.field
-            } else {
-                self.resource
-            };
+            let tantivy_field = if is_field { self.field } else { self.resource };
             Term::from_field_bytes(tantivy_field, k.as_bytes())
         })))
     }
@@ -134,7 +130,10 @@ impl ParagraphSearcher {
             reader: ParagraphReaderService {
                 index: index.clone(),
                 schema: ParagraphSchema::new(),
-                reader: index.reader_builder().reload_policy(tantivy::ReloadPolicy::Manual).try_into()?,
+                reader: index
+                    .reader_builder()
+                    .reload_policy(tantivy::ReloadPolicy::Manual)
+                    .try_into()?,
             },
         })
     }
@@ -157,7 +156,7 @@ impl ParagraphSearcher {
         self.reader.suggest(request, prefilter)
     }
 
-    pub fn iterator(&self, request: &StreamRequest) -> anyhow::Result<impl Iterator<Item = ParagraphItem>> {
+    pub fn iterator(&self, request: &StreamRequest) -> anyhow::Result<impl Iterator<Item = ParagraphItem> + use<>> {
         self.reader.iterator(request)
     }
 }

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/nidx_paragraph/src/reader.rs

@@ -26,14 +26,14 @@ use nidx_protos::{OrderBy, ParagraphItem, ParagraphSearchResponse, StreamRequest
 use nidx_types::prefilter::PrefilterResult;
 use tantivy::collector::{Collector, Count, FacetCollector, TopDocs};
 use tantivy::query::{AllQuery, Query, QueryParser};
-use tantivy::{schema::*, DateTime, Order};
+use tantivy::{DateTime, Order, schema::*};
 use tantivy::{DocAddress, Index, IndexReader};
 use tracing::*;
 
 use super::schema::ParagraphSchema;
 use crate::request_types::{ParagraphSearchRequest, ParagraphSuggestRequest};
-use crate::search_query::{search_query, streaming_query, suggest_query, SharedTermC};
-use crate::search_response::{extract_labels, SearchBm25Response, SearchFacetsResponse, SearchIntResponse};
+use crate::search_query::{SharedTermC, search_query, streaming_query, suggest_query};
+use crate::search_response::{SearchBm25Response, SearchFacetsResponse, SearchIntResponse, extract_labels};
 
 const FUZZY_DISTANCE: u8 = 1;
 const NUMBER_OF_RESULTS_SUGGEST: usize = 10;
@@ -46,7 +46,10 @@ pub struct ParagraphReaderService {
 
 impl Debug for ParagraphReaderService {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        f.debug_struct("TextService").field("index", &self.index).field("schema", &self.schema).finish()
+        f.debug_struct("TextService")
+            .field("index", &self.index)
+            .field("schema", &self.schema)
+            .finish()
     }
 }
 
@@ -94,7 +97,7 @@ impl ParagraphReaderService {
         }))
     }
 
-    pub fn iterator(&self, request: &StreamRequest) -> anyhow::Result<impl Iterator<Item = ParagraphItem>> {
+    pub fn iterator(&self, request: &StreamRequest) -> anyhow::Result<impl Iterator<Item = ParagraphItem> + use<>> {
         let producer = BatchProducer {
             offset: 0,
             total: self.count()?,
@@ -136,7 +139,11 @@ impl ParagraphReaderService {
         let v = time.elapsed().as_millis();
         debug!("{id:?} - Searching: starts at {v} ms");
 
-        let advanced = request.advanced_query.as_ref().map(|query| parser.parse_query(query)).transpose()?;
+        let advanced = request
+            .advanced_query
+            .as_ref()
+            .map(|query| parser.parse_query(query))
+            .transpose()?;
         #[rustfmt::skip] let (original, termc, fuzzied) = search_query(
             &parser,
             &text,
@@ -245,7 +252,10 @@ impl Iterator for BatchProducer {
             return None;
         };
         let mut items = vec![];
-        for doc in top_docs.into_iter().flat_map(|i| self.searcher.doc::<TantivyDocument>(i.1)) {
+        for doc in top_docs
+            .into_iter()
+            .flat_map(|i| self.searcher.doc::<TantivyDocument>(i.1))
+        {
             let id = doc
                 .get_first(self.paragraph_field)
                 .expect("document doesn't appear to have uuid.")
@@ -254,10 +264,7 @@ impl Iterator for BatchProducer {
                 .to_string();
 
             let labels = extract_labels(doc.get_all(self.facet_field));
-            items.push(ParagraphItem {
-                id,
-                labels,
-            });
+            items.push(ParagraphItem { id, labels });
         }
         self.offset += Self::BATCH;
         let v = time.elapsed().as_millis();
@@ -290,7 +297,9 @@ impl<'a> Searcher<'a> {
             OrderType::Desc => Order::Desc,
             OrderType::Asc => Order::Asc,
         };
-        TopDocs::with_limit(limit).and_offset(offset).order_by_fast_field(order_field, order_direction)
+        TopDocs::with_limit(limit)
+            .and_offset(offset)
+            .order_by_fast_field(order_field, order_direction)
     }
     fn do_search(
         &self,
@@ -300,10 +309,13 @@ impl<'a> Searcher<'a> {
         min_score: f32,
     ) -> anyhow::Result<ParagraphSearchResponse> {
         let searcher = service.reader.searcher();
-        let facet_collector = self.facets.iter().fold(FacetCollector::for_field("facets"), |mut collector, facet| {
-            collector.add_facet(Facet::from(facet));
-            collector
-        });
+        let facet_collector = self
+            .facets
+            .iter()
+            .fold(FacetCollector::for_field("facets"), |mut collector, facet| {
+                collector.add_facet(Facet::from(facet));
+                collector
+            });
         if self.only_faceted {
             // No query search, just facets
             let facets_count = searcher.search(&query, &facet_collector).unwrap();

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/nidx_paragraph/src/resource_indexer.rs

@@ -49,8 +49,12 @@ pub fn index_paragraphs(
     };
 
     let empty_paragraph = HashMap::with_capacity(0);
-    let inspect_paragraph =
-        |field: &str| resource.paragraphs.get(field).map_or_else(|| &empty_paragraph, |i| &i.paragraphs);
+    let inspect_paragraph = |field: &str| {
+        resource
+            .paragraphs
+            .get(field)
+            .map_or_else(|| &empty_paragraph, |i| &i.paragraphs)
+    };
 
     let resource_labels = resource
         .labels

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/nidx_paragraph/src/schema.rs

@@ -17,13 +17,13 @@
 // You should have received a copy of the GNU Affero General Public License
 // along with this program. If not, see <http://www.gnu.org/licenses/>.
 //
-use nidx_protos::prost::*;
 use nidx_protos::ParagraphMetadata;
-use tantivy::schema::Value;
-use tantivy::schema::{FacetOptions, Field, NumericOptions, Schema, STORED, STRING, TEXT};
+use nidx_protos::prost::*;
 use tantivy::DateOptions;
 use tantivy::DateTime;
 use tantivy::TantivyDocument;
+use tantivy::schema::Value;
+use tantivy::schema::{FacetOptions, Field, NumericOptions, STORED, STRING, Schema, TEXT};
 
 #[derive(Debug, Clone)]
 pub struct ParagraphSchema {
@@ -70,7 +70,8 @@ impl ParagraphSchema {
 
     /// Returns the paragraph metadata for the given document, if any.
     pub fn metadata(&self, doc: &TantivyDocument) -> Option<ParagraphMetadata> {
-        doc.get_first(self.metadata).and_then(|value| ParagraphMetadata::decode(value.as_bytes()?).ok())
+        doc.get_first(self.metadata)
+            .and_then(|value| ParagraphMetadata::decode(value.as_bytes()?).ok())
     }
 }
 

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/nidx_paragraph/src/search_query.rs

@@ -66,11 +66,7 @@ impl TermCollector {
             let term_dict = index.terms();
             let mut term_s = vec![];
             let found = term_dict.ord_to_term(term, &mut term_s).unwrap_or(false);
-            let elem = if found {
-                term_s
-            } else {
-                vec![]
-            };
+            let elem = if found { term_s } else { vec![] };
             match String::from_utf8(elem).ok() {
                 Some(v) if v.len() > 2 => terms.push(v),
                 _ => (),
@@ -123,9 +119,11 @@ fn queryp_map(queries: Vec<QueryP>, distance: u8, as_prefix: Option<usize>, term
 }
 
 fn flat_bool_query(query: BooleanQuery, collector: (usize, Vec<QueryP>)) -> (usize, Vec<QueryP>) {
-    query.clauses().iter().map(|(occur, subq)| (*occur, subq.box_clone())).fold(
-        collector,
-        |(mut id, mut c), (occur, subq)| {
+    query
+        .clauses()
+        .iter()
+        .map(|(occur, subq)| (*occur, subq.box_clone()))
+        .fold(collector, |(mut id, mut c), (occur, subq)| {
             if subq.is::<BooleanQuery>() {
                 let subq: Box<BooleanQuery> = subq.downcast().unwrap();
                 flat_bool_query(*subq, (id, c))
@@ -137,8 +135,7 @@ fn flat_bool_query(query: BooleanQuery, collector: (usize, Vec<QueryP>)) -> (usi
                 c.push((occur, subq));
                 (id, c)
             }
-        },
-    )
+        })
 }
 
 fn flat_and_adapt(query: Box<dyn Query>, prefixed: bool, distance: u8, termc: SharedTermC) -> Vec<QueryP> {
@@ -155,16 +152,7 @@ fn flat_and_adapt(query: Box<dyn Query>, prefixed: bool, distance: u8, termc: Sh
         let as_prefix = 1;
         (queries, as_prefix)
     };
-    queryp_map(
-        queries,
-        distance,
-        if prefixed {
-            Some(as_prefix)
-        } else {
-            None
-        },
-        termc,
-    )
+    queryp_map(queries, distance, if prefixed { Some(as_prefix) } else { None }, termc)
 }
 
 fn fuzzied_queries(query: Box<dyn Query>, prefixed: bool, distance: u8, termc: SharedTermC) -> Vec<QueryP> {
@@ -192,9 +180,12 @@ fn parse_query(parser: &QueryParser, text: &str) -> Box<dyn Query> {
 /// The last term of the query is a prefix fuzzy term and must be preserved.
 fn remove_stop_words(query: &str) -> Cow<'_, str> {
     match query.rsplit_once(' ') {
-        Some((query, last_term)) => {
-            query.split(' ').filter(|term| !is_stop_word(&term.to_lowercase())).chain([last_term]).join(" ").into()
-        }
+        Some((query, last_term)) => query
+            .split(' ')
+            .filter(|term| !is_stop_word(&term.to_lowercase()))
+            .chain([last_term])
+            .join(" ")
+            .into(),
         None => query.into(),
     }
 }
@@ -222,7 +213,10 @@ fn preprocess_raw_query(query: &str, tc: &mut TermCollector) -> ProcessedQuery {
         let unquote = query[start..qstart].trim();
         let unquote = remove_stop_words(unquote);
 
-        unquote.split(' ').filter(|s| !s.is_empty()).for_each(|t| tc.log_eterm(t.to_string()));
+        unquote
+            .split(' ')
+            .filter(|s| !s.is_empty())
+            .for_each(|t| tc.log_eterm(t.to_string()));
         tc.log_eterm(quote.to_string());
 
         if !regular_query.is_empty() {
@@ -245,7 +239,9 @@ fn preprocess_raw_query(query: &str, tc: &mut TermCollector) -> ProcessedQuery {
         let tail = query[start..].trim();
         let tail = remove_stop_words(tail);
 
-        tail.split(' ').filter(|s| !s.is_empty()).for_each(|t| tc.log_eterm(t.to_string()));
+        tail.split(' ')
+            .filter(|s| !s.is_empty())
+            .for_each(|t| tc.log_eterm(t.to_string()));
 
         if !regular_query.is_empty() {
             regular_query.push(' ');
@@ -270,11 +266,7 @@ fn filter_query(
     filter_or: bool,
 ) -> Option<Box<dyn Query>> {
     let mut filter_terms = vec![];
-    let operator = if filter_or {
-        Occur::Should
-    } else {
-        Occur::Must
-    };
+    let operator = if filter_or { Occur::Should } else { Occur::Must };
 
     // Paragraph filter
     if let Some(formula) = &paragraph_formula {
@@ -286,7 +278,9 @@ fn filter_query(
     if let PrefilterResult::Some(field_keys) = prefilter {
         let set_query = Box::new(SetQuery::new(
             schema.field_uuid,
-            field_keys.iter().map(|x| format!("{}{}", x.resource_id.simple(), x.field_id)),
+            field_keys
+                .iter()
+                .map(|x| format!("{}{}", x.resource_id.simple(), x.field_id)),
         ));
         filter_terms.push((operator, set_query));
     }
@@ -434,8 +428,14 @@ mod tests {
 
     #[test]
     fn test() {
-        let subqueries0: Vec<_> = vec![dummy_term_query; 12].into_iter().map(|f| (Occur::Must, f())).collect();
-        let subqueries1: Vec<_> = vec![dummy_term_query; 12].into_iter().map(|f| (Occur::Must, f())).collect();
+        let subqueries0: Vec<_> = vec![dummy_term_query; 12]
+            .into_iter()
+            .map(|f| (Occur::Must, f()))
+            .collect();
+        let subqueries1: Vec<_> = vec![dummy_term_query; 12]
+            .into_iter()
+            .map(|f| (Occur::Must, f()))
+            .collect();
         let boolean0: Box<dyn Query> = Box::new(BooleanQuery::new(subqueries0));
         let boolean1: Box<dyn Query> = Box::new(BooleanQuery::new(subqueries1));
         let nested = BooleanQuery::new(vec![(Occur::Should, boolean0), (Occur::Should, boolean1)]);
@@ -448,7 +448,10 @@ mod tests {
     #[test]
     fn it_removes_stop_word_fterms() {
         let tests = [
-            ("nuclia is a database for unstructured data", "nuclia database unstructured data"),
+            (
+                "nuclia is a database for unstructured data",
+                "nuclia database unstructured data",
+            ),
             (
                 "nuclia is a database for the",
                 // keeps last term even if is a stop word
@@ -457,8 +460,14 @@ mod tests {
             ("is a for and", "and"),
             ("what does stop is?", "stop is?"),
             ("", ""),
-            ("comment s'appelle le train à grande vitesse", "comment s'appelle train grande vitesse"),
-            ("¿Qué significa la palabra sentence en español?", "¿Qué significa palabra sentence español?"),
+            (
+                "comment s'appelle le train à grande vitesse",
+                "comment s'appelle train grande vitesse",
+            ),
+            (
+                "¿Qué significa la palabra sentence en español?",
+                "¿Qué significa palabra sentence español?",
+            ),
             ("Per què les vaques no són de color rosa?", "vaques color rosa?"),
             ("How can I learn to make a flat white?", "learn make flat white?"),
             ("Qué es escalada en bloque?", "escalada bloque?"),
@@ -466,7 +475,10 @@ mod tests {
                 "Wer hat gesagt: 'Kaffeetrinken ist integraler Bestandteil des Kletterns'?",
                 "Wer gesagt: 'Kaffeetrinken integraler Bestandteil Kletterns'?",
             ),
-            ("i pistacchi siciliani sono i migliori al mondo?", "pistacchi siciliani migliori mondo?"),
+            (
+                "i pistacchi siciliani sono i migliori al mondo?",
+                "pistacchi siciliani migliori mondo?",
+            ),
         ];
 
         for (query, expected_fuzzy_query) in tests {

{nidx_binding-6.3.1.post46 → nidx_binding-6.3.1.post48}/nidx_paragraph/src/search_response.rs

@@ -30,7 +30,11 @@ use crate::reader::ParagraphReaderService;
 use crate::search_query::TermCollector;
 
 pub fn extract_labels<'a>(facets_iterator: impl Iterator<Item = &'a OwnedValue>) -> Vec<String> {
-    facets_iterator.flat_map(|x| x.as_facet()).filter(|x| is_label(x)).map(|x| x.to_path_string()).collect()
+    facets_iterator
+        .flat_map(|x| x.as_facet())
+        .filter(|x| is_label(x))
+        .map(|x| x.to_path_string())
+        .collect()
 }
 
 pub fn is_label(facet: &Facet) -> bool {
@@ -56,14 +60,7 @@ pub fn produce_facets(facets: Vec<String>, facets_count: FacetCounts) -> HashMap
         .map(|facet| (&facets_count, facet))
         .map(|(facets_count, facet)| (facet_count(&facet, facets_count), facet))
         .filter(|(r, _)| !r.is_empty())
-        .map(|(facetresults, facet)| {
-            (
-                facet,
-                FacetResults {
-                    facetresults,
-                },
-            )
-        })
+        .map(|(facetresults, facet)| (facet, FacetResults { facetresults }))
         .collect()
 }
 
@@ -102,7 +99,10 @@ pub struct SearchFacetsResponse<'a> {
 
 impl<'a> From<SearchFacetsResponse<'a>> for ParagraphSearchResponse {
     fn from(response: SearchFacetsResponse) -> Self {
-        let facets = response.facets_count.map(|count| produce_facets(response.facets, count)).unwrap_or_default();
+        let facets = response
+            .facets_count
+            .map(|count| produce_facets(response.facets, count))
+            .unwrap_or_default();
         let results: Vec<ParagraphResult> = Vec::with_capacity(0);
         ParagraphSearchResponse {
             results,
@@ -161,7 +161,12 @@ impl<'a> From<SearchIntResponse<'a>> for ParagraphSearchResponse {
                         .unwrap()
                         .to_string();
 
-                    let split = doc.get_first(schema.split).unwrap_or(&default_split).as_str().unwrap().to_string();
+                    let split = doc
+                        .get_first(schema.split)
+                        .unwrap_or(&default_split)
+                        .as_str()
+                        .unwrap()
+                        .to_string();
 
                     let index = doc.get_first(schema.index).unwrap().as_u64().unwrap();
                     let mut terms: Vec<_> = response.termc.get_fterms(doc_address.doc_id).into_iter().collect();
@@ -186,7 +191,10 @@ impl<'a> From<SearchIntResponse<'a>> for ParagraphSearchResponse {
             }
         }
 
-        let facets = response.facets_count.map(|count| produce_facets(response.facets, count)).unwrap_or_default();
+        let facets = response
+            .facets_count
+            .map(|count| produce_facets(response.facets, count))
+            .unwrap_or_default();
         ParagraphSearchResponse {
             results,
             facets,
@@ -251,7 +259,12 @@ impl<'a> From<SearchBm25Response<'a>> for ParagraphSearchResponse {
                         .unwrap()
                         .to_string();
 
-                    let split = doc.get_first(schema.split).unwrap_or(&default_split).as_str().unwrap().to_string();
+                    let split = doc
+                        .get_first(schema.split)
+                        .unwrap_or(&default_split)
+                        .as_str()
+                        .unwrap()
+                        .to_string();
 
                     let index = doc.get_first(schema.index).unwrap().as_u64().unwrap();
                     let mut terms: Vec<_> = response.termc.get_fterms(doc_address.doc_id).into_iter().collect();
@@ -276,7 +289,10 @@ impl<'a> From<SearchBm25Response<'a>> for ParagraphSearchResponse {
             }
         }
 
-        let facets = response.facets_count.map(|count| produce_facets(response.facets, count)).unwrap_or_default();
+        let facets = response
+            .facets_count
+            .map(|count| produce_facets(response.facets, count))
+            .unwrap_or_default();
         ParagraphSearchResponse {
             results,
             facets,