summaryrefslogtreecommitdiffstats
path: root/vendor/elasticlunr-rs/src/lang/fr.rs
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-17 12:02:58 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-17 12:02:58 +0000
commit698f8c2f01ea549d77d7dc3338a12e04c11057b9 (patch)
tree173a775858bd501c378080a10dca74132f05bc50 /vendor/elasticlunr-rs/src/lang/fr.rs
parentInitial commit. (diff)
downloadrustc-698f8c2f01ea549d77d7dc3338a12e04c11057b9.tar.xz
rustc-698f8c2f01ea549d77d7dc3338a12e04c11057b9.zip
Adding upstream version 1.64.0+dfsg1.upstream/1.64.0+dfsg1
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'vendor/elasticlunr-rs/src/lang/fr.rs')
-rw-r--r--vendor/elasticlunr-rs/src/lang/fr.rs56
1 files changed, 56 insertions, 0 deletions
diff --git a/vendor/elasticlunr-rs/src/lang/fr.rs b/vendor/elasticlunr-rs/src/lang/fr.rs
new file mode 100644
index 000000000..ec41f307a
--- /dev/null
+++ b/vendor/elasticlunr-rs/src/lang/fr.rs
@@ -0,0 +1,56 @@
+use super::{
+ common::{RustStemmer, StopWordFilter, RegexTrimmer},
+ Language,
+};
+use crate::pipeline::Pipeline;
+use rust_stemmers::Algorithm;
+
+#[derive(Clone)]
+pub struct French {}
+
+impl French {
+ pub fn new() -> Self {
+ Self {}
+ }
+}
+
+impl Language for French {
+ fn name(&self) -> String {
+ "French".into()
+ }
+ fn code(&self) -> String {
+ "fr".into()
+ }
+
+ fn tokenize(&self, text: &str) -> Vec<String> {
+ super::tokenize_whitespace(text)
+ }
+
+ fn make_pipeline(&self) -> Pipeline {
+ Pipeline {
+ queue: vec![
+ Box::new(RegexTrimmer::new("trimmer-fr", r"\p{Latin}")),
+ Box::new(StopWordFilter::new("stopWordFilter-fr", STOP_WORDS)),
+ Box::new(RustStemmer::new("stemmer-fr", Algorithm::French)),
+ ],
+ }
+ }
+}
+
+const STOP_WORDS: &[&str] = &[
+ "", "ai", "aie", "aient", "aies", "ait", "as", "au", "aura", "aurai", "auraient", "aurais",
+ "aurait", "auras", "aurez", "auriez", "aurions", "aurons", "auront", "aux", "avaient", "avais",
+ "avait", "avec", "avez", "aviez", "avions", "avons", "ayant", "ayez", "ayons", "c", "ce",
+ "ceci", "celà", "ces", "cet", "cette", "d", "dans", "de", "des", "du", "elle", "en", "es",
+ "est", "et", "eu", "eue", "eues", "eurent", "eus", "eusse", "eussent", "eusses", "eussiez",
+ "eussions", "eut", "eux", "eûmes", "eût", "eûtes", "furent", "fus", "fusse", "fussent",
+ "fusses", "fussiez", "fussions", "fut", "fûmes", "fût", "fûtes", "ici", "il", "ils", "j", "je",
+ "l", "la", "le", "les", "leur", "leurs", "lui", "m", "ma", "mais", "me", "mes", "moi", "mon",
+ "même", "n", "ne", "nos", "notre", "nous", "on", "ont", "ou", "par", "pas", "pour", "qu",
+ "que", "quel", "quelle", "quelles", "quels", "qui", "s", "sa", "sans", "se", "sera", "serai",
+ "seraient", "serais", "serait", "seras", "serez", "seriez", "serions", "serons", "seront",
+ "ses", "soi", "soient", "sois", "soit", "sommes", "son", "sont", "soyez", "soyons", "suis",
+ "sur", "t", "ta", "te", "tes", "toi", "ton", "tu", "un", "une", "vos", "votre", "vous", "y",
+ "à", "étaient", "étais", "était", "étant", "étiez", "étions", "été", "étée", "étées", "étés",
+ "êtes",
+];