Merge #323

323: Upgrade compatible dependencies r=ManyTheFish a=Kerollmops

In this PR I upgrade the compatible dependencies of charabia.

Co-authored-by: Clément Renault <clement@meilisearch.com>

charabia/Cargo.toml

@@ -13,21 +13,21 @@ exclude = ["dictionaries/txt/thai/words.txt"]
 
 [dependencies]
 aho-corasick = "1.1.3"
-csv = "1.3.0"
+csv = "1.3.1"
 either = "1.13.0"
-finl_unicode = { version= "1.2.0", optional = true }
+finl_unicode = { version= "1.3.0", optional = true }
 fst = "0.4"
 jieba-rs = { version = "0.7", optional = true }
-once_cell = "1.19.0"
-serde = "1.0.192"
+once_cell = "1.20.2"
+serde = "1.0.217"
 slice-group-by = "0.3.1"
 whatlang = "0.16.4"
 lindera = { version = "=0.32.2", default-features = false, optional = true }
 pinyin = { version = "0.10", default-features = false, features = [
   "with_tone",
 ], optional = true }
 wana_kana = { version = "4.0.0", optional = true }
-unicode-normalization = "0.1.23"
+unicode-normalization = "0.1.24"
 irg-kvariants = { path = "../irg-kvariants", version = "=0.1.1" }
 
 [features]

charabia/src/normalizer/ae_oe_normalizer.rs

@@ -4,7 +4,6 @@ use crate::{Script, Token};
 /// This module contains the implementation of the `AeOeNormalizer` struct, which is a character normalizer
 /// that replaces the characters 'œ', 'æ', 'Œ', and 'Æ' with their respective replacements 'oe', 'ae', 'OE', and 'AE'.
 /// It also provides a test suite to validate the normalizer's functionality.
-
 pub struct AeOeNormalizer;
 
 // All normalizers only need to implement the method `normalize_char` and the method `should_normalize` of the `CharNormalizer` trait.

charabia/src/normalizer/arabic.rs

@@ -10,7 +10,6 @@ use crate::{Script, Token};
 /// - Normalizing the arabic Taa Marbuta 'ة' to 'ه'
 ///   https://en.wikipedia.org/wiki/Arabic_alphabet
 ///   https://en.wikipedia.org/wiki/Kashida
-
 pub struct ArabicNormalizer;
 
 // All normalizers only need to implement the method `normalize_char` and the method `should_normalize` of the `CharNormalizer` trait.

charabia/src/segmenter/arabic.rs

@@ -7,7 +7,6 @@ use super::Segmenter;
 /// One possible solution is to segment any word that starts with `ال` into two words. The `ال` and the rest of the word.
 /// with this solution, we will have `الشجرة` (the tree) segmented into `ال` (the) and `شجرة` (tree). and if we search for `شجرة` (tree) or `الشجرة` (thetree) we will find results.
 /// Some Arabic text starts with `ال` and not meant to be (the) like `البانيا` (Albania). In this case, we will have `ال` and `بانيا` segmented. and if we search for `البانيا` we will find results.
-
 pub struct ArabicSegmenter;
 
 // All specialized segmenters only need to implement the method `segment_str` of the `Segmenter` trait.

charabia/src/segmenter/mod.rs

@@ -177,7 +177,7 @@ impl<'o, 'aho, 'lang> SegmentedStrIter<'o, 'aho, 'lang> {
     }
 }
 
-impl<'o, 'aho, 'lang> Iterator for SegmentedStrIter<'o, 'aho, 'lang> {
+impl<'o> Iterator for SegmentedStrIter<'o, '_, '_> {
     type Item = &'o str;
 
     fn next(&mut self) -> Option<Self::Item> {
@@ -220,7 +220,7 @@ impl<'o, 'aho> AhoSegmentedStrIter<'o, 'aho> {
     }
 }
 
-impl<'o, 'aho> Iterator for AhoSegmentedStrIter<'o, 'aho> {
+impl<'o> Iterator for AhoSegmentedStrIter<'o, '_> {
     type Item = (&'o str, MatchType);
 
     fn next(&mut self) -> Option<Self::Item> {

charabia/src/tokenizer.rs

@@ -103,7 +103,7 @@ pub struct Tokenizer<'tb> {
     normalizer_option: Cow<'tb, NormalizerOption<'tb>>,
 }
 
-impl<'tb> Tokenizer<'tb> {
+impl Tokenizer<'_> {
     /// Creates an Iterator over [`Token`]s.
     ///
     /// The provided text is segmented creating tokens,

irg-kvariants/Cargo.toml

@@ -9,10 +9,10 @@ repository = "https://github.com/meilisearch/charabia"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-csv = "1.3.0"
-once_cell = "1.19.0"
-serde = { version = "1.0.203", features = ["derive"] }
+csv = "1.3.1"
+once_cell = "1.20.2"
+serde = { version = "1.0.217", features = ["derive"] }
 
 [build-dependencies]
-csv = "1.3.0"
-serde = { version = "1.0.203", features = ["derive"] }
+csv = "1.3.1"
+serde = { version = "1.0.217", features = ["derive"] }