Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Armenian letters should be lowercased #328

Merged
merged 6 commits into from
Feb 24, 2025
+101 −50
Merged

Armenian letters should be lowercased #328

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
88aadbd
Armenian letters should be lowercased
NarHakobyan Feb 7, 2025
99f1841
add .DS_Store gitignore
NarHakobyan Feb 10, 2025
d929c01
fix linter errors
NarHakobyan Feb 10, 2025
98c1db8
add test for Armenian
NarHakobyan Feb 12, 2025
5f50203
fix linter issues
NarHakobyan Feb 13, 2025
98a479c
change Armenian word for test
NarHakobyan Feb 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,3 +9,4 @@ charabia/target
/data.ms
Cargo.lock
.idea
.DS_Store
146 changes: 98 additions & 48 deletions charabia/src/normalizer/lowercase.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,8 +27,10 @@ impl CharNormalizer for LowercaseNormalizer {

fn should_normalize(&self, token: &Token) -> bool {
// https://en.wikipedia.org/wiki/Letter_case#Capitalisation
matches!(token.script, Script::Latin | Script::Cyrillic | Script::Greek | Script::Georgian)
&& token.lemma.chars().any(char::is_uppercase)
matches!(
token.script,
Script::Latin | Script::Cyrillic | Script::Greek | Script::Georgian | Script::Armenian
) && token.lemma.chars().any(char::is_uppercase)
}
}

Expand All @@ -41,58 +43,106 @@ mod test {
use crate::token::TokenKind;

fn tokens() -> Vec<Token<'static>> {
vec![Token {
lemma: Owned("PascalCase".to_string()),
char_end: 10,
byte_end: 10,
script: Script::Latin,
..Default::default()
}]
vec![
Token {
lemma: Owned("PascalCase".to_string()),
char_end: 10,
byte_end: 10,
script: Script::Latin,
..Default::default()
},
Token {
lemma: Owned("ՀայասՏան".to_string()),
char_end: 8,
byte_end: 16,
script: Script::Armenian,
..Default::default()
},
]
}

fn normalizer_result() -> Vec<Token<'static>> {
vec![Token {
lemma: Owned("pascalcase".to_string()),
char_end: 10,
byte_end: 10,
script: Script::Latin,
char_map: Some(vec![
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
]),
..Default::default()
}]
vec![
Token {
lemma: Owned("pascalcase".to_string()),
char_end: 10,
byte_end: 10,
script: Script::Latin,
char_map: Some(vec![
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
]),
..Default::default()
},
Token {
lemma: Owned("հայաստան".to_string()),
char_end: 8,
byte_end: 16,
script: Script::Armenian,
char_map: Some(vec![
(2, 2),
(2, 2),
(2, 2),
(2, 2),
(2, 2),
(2, 2),
(2, 2),
(2, 2),
]),
..Default::default()
},
]
}

fn normalized_tokens() -> Vec<Token<'static>> {
vec![Token {
lemma: Owned("pascalcase".to_string()),
char_end: 10,
byte_end: 10,
script: Script::Latin,
kind: TokenKind::Word,
char_map: Some(vec![
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
]),
..Default::default()
}]
vec![
Token {
lemma: Owned("pascalcase".to_string()),
char_end: 10,
byte_end: 10,
script: Script::Latin,
kind: TokenKind::Word,
char_map: Some(vec![
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
]),
..Default::default()
},
Token {
lemma: Owned("հայաստան".to_string()),
char_end: 8,
byte_end: 16,
script: Script::Armenian,
kind: TokenKind::Word,
char_map: Some(vec![
(2, 2),
(2, 2),
(2, 2),
(2, 2),
(2, 2),
(2, 2),
(2, 2),
(2, 2),
]),
..Default::default()
},
]
}

test_normalizer!(LowercaseNormalizer, tokens(), normalizer_result(), normalized_tokens());
Expand Down
2 changes: 1 addition & 1 deletion charabia/src/separators.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ pub const CONTEXT_SEPARATORS: &[&str] = &[
"᠆", // Mongolian Todo Soft Hyphen, mark the end of a paragraph.
"᚛", "᚜", // Oghams, mark start and end of text
"!", ". ", ", ", ";", "?", "¡", "§", "¶", "¿", ";", // Latin
"՜", // Armenian exclamation mark
"՜", "´", // Armenian exclamation mark
"՝", // Armenian comma
"՞", // Armenian question mark
"։", // Armenian full stop or period, used to indicate the end of a sentence
Expand Down
2 changes: 1 addition & 1 deletion charabia/src/token.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@ impl Token<'_> {

/// Returns true if the current token is a separator.
pub fn is_separator(&self) -> bool {
self.separator_kind().map_or(false, |_| true)
self.separator_kind().is_some_and(|_| true)
}

/// Returns Some([`SeparatorKind`]) if the token is a separator and None if it's a word or a stop word.
Expand Down