mirror of
https://github.com/storytold/craft-libs.git
synced 2026-11-19 08:45:16 +00:00
Proofing options reach the Russian and Turkish checks too
storytold/wordcraft#3966 made Ignore words in UPPERCASE and Ignore words that contain numbers reach six languages' own checks, one copy at a time, and Russian and Turkish were left out. lib.rs still called `ru::is_correct(word)` and `tr::is_correct(word)`, which accept words with digits (both) and short words in capitals (Russian) whatever the options say, so turning either option off changed nothing in those languages. Both now have `is_correct_with_options`, like the others. Russian's rule for a part in capitals (`ИИ-консультант`) follows the option too, as Indonesian's does, and its digits rule keeps counting superscripts (`м²`). Turkish had no test dictionary, so its two dictionary tests returned early wherever none was installed, CI included; it has a synthetic one now, also in the dictionaries-folder test. Tests: proofing_options_reach_the_russian_check and proofing_options_reach_the_turkish_check. Calling the old checks from lib.rs fails each, and so does ungating the Russian part rule or the Turkish hyphen recursion.
This commit is contained in:
1 parent
47e630e98a
commit
f417d88631
5 files changed
+99
-21
No files matched your search
@@ -778,8 +778,8 @@ pub fn is_correct_in_with(word: &str, lang: ProofLang, opts: &Options) -> bool {
|
||||
ProofLang::Hr => accepted_by_options(word, opts) || hr::is_correct_with_options(word, opts),
|
||||
ProofLang::Pt => accepted_by_options(word, opts) || pt::is_correct_with_options(word, opts),
|
||||
ProofLang::It => accepted_by_options(word, opts) || it::is_correct_with_options(word, opts),
|
||||
ProofLang::Tr => accepted_by_options(word, opts) || tr::is_correct(word),
|
||||
ProofLang::Ru => accepted_by_options(word, opts) || ru::is_correct(word),
|
||||
ProofLang::Tr => accepted_by_options(word, opts) || tr::is_correct_with_options(word, opts),
|
||||
ProofLang::Ru => accepted_by_options(word, opts) || ru::is_correct_with_options(word, opts),
|
||||
ProofLang::Es | ProofLang::EsMx | ProofLang::Es419 | ProofLang::EsUy => {
|
||||
accepted_by_options(word, opts) || es::is_correct_with_options(word, lang, opts)
|
||||
}
|
||||
@@ -1075,6 +1075,7 @@ mod tests {
|
||||
("pt_BR", pt::test_dict::AFF, pt::test_dict::DIC),
|
||||
("it_IT", it::test_dict::AFF, it::test_dict::DIC),
|
||||
("hr_HR", hr::test_dict::AFF, hr::test_dict::DIC),
|
||||
("tr_TR", tr::test_dict::AFF, tr::test_dict::DIC),
|
||||
("ru_RU", ru::test_dict::AFF, ru::test_dict::DIC),
|
||||
("cs_CZ", cs::test_dict::AFF, cs::test_dict::DIC),
|
||||
("id_ID", id::test_dict::AFF, id::test_dict::DIC),
|
||||
@@ -1094,9 +1095,9 @@ mod tests {
|
||||
let before = dictionary_generation();
|
||||
set_dictionaries_folder(Some(dir.clone()));
|
||||
assert!(dictionary_generation() > before, "cached checks are dropped");
|
||||
// Turkish has no test dictionary to put in the folder; Russian, Czech, Indonesian and the Spanishes follow it.
|
||||
// Turkish follows the four below; Russian, Czech, Indonesian and the Spanishes follow it.
|
||||
let found = installed_dictionaries();
|
||||
assert_eq!(found.get(4).map(|(lang, _)| *lang), Some(ProofLang::Tr));
|
||||
assert_eq!(found.get(4), Some(&(ProofLang::Tr, Some(dir.join("tr_TR.dic")))));
|
||||
assert_eq!(
|
||||
found[7..],
|
||||
[
|
||||
|
||||
@@ -130,18 +130,30 @@ pub fn is_correct(word: &str) -> bool {
|
||||
is_correct_with(&dictionary(), word)
|
||||
}
|
||||
|
||||
/// [`is_correct`] with the File › Options › Proofing choices: with Ignore words in UPPERCASE off,
|
||||
/// short words in capitals are checked against the dictionary too, and with Ignore words that
|
||||
/// contain numbers off, so are words with digits or superscripts.
|
||||
pub fn is_correct_with_options(word: &str, opts: &crate::Options) -> bool {
|
||||
check(&dictionary(), word, opts)
|
||||
}
|
||||
|
||||
/// [`is_correct`] against a given dictionary (an empty one accepts everything).
|
||||
pub fn is_correct_with(d: &AffixDict, word: &str) -> bool {
|
||||
check(d, word, &crate::Options::default())
|
||||
}
|
||||
|
||||
/// [`is_correct_with_options`] against a given dictionary.
|
||||
fn check(d: &AffixDict, word: &str, opts: &crate::Options) -> bool {
|
||||
if d.is_empty() {
|
||||
return true; // no Russian dictionary installed: no spelling marks
|
||||
}
|
||||
let w = word.trim_matches(|c: char| !c.is_alphanumeric() && c != '-');
|
||||
let w = w.trim_matches('-');
|
||||
let n = w.chars().count();
|
||||
if n <= 1 || w.chars().any(char::is_numeric) || !w.chars().any(char::is_alphabetic) {
|
||||
if n <= 1 || (opts.ignore_numbers && w.chars().any(char::is_numeric)) || !w.chars().any(char::is_alphabetic) {
|
||||
return true;
|
||||
}
|
||||
if w.chars().all(|c| !c.is_lowercase()) && n <= ABBREVIATION_LETTERS {
|
||||
if opts.ignore_uppercase && w.chars().all(|c| !c.is_lowercase()) && n <= ABBREVIATION_LETTERS {
|
||||
return true;
|
||||
}
|
||||
// Camel case (`ВКонтакте`, `МирКрасок`): a brand or an identifier, not a dictionary word.
|
||||
@@ -161,7 +173,7 @@ pub fn is_correct_with(d: &AffixDict, word: &str) -> bool {
|
||||
return true;
|
||||
}
|
||||
if w.contains('-') {
|
||||
return hyphenated(d, w);
|
||||
return hyphenated(d, w, opts);
|
||||
}
|
||||
solid_compound(d, w)
|
||||
}
|
||||
@@ -340,7 +352,7 @@ fn known(d: &AffixDict, w: &str) -> bool {
|
||||
|
||||
/// A hyphenated word that isn't in the dictionary whole: its parts, with the particles,
|
||||
/// prefixes and linking vowels Russian joins with a hyphen.
|
||||
fn hyphenated(d: &AffixDict, w: &str) -> bool {
|
||||
fn hyphenated(d: &AffixDict, w: &str, opts: &crate::Options) -> bool {
|
||||
let parts: Vec<&str> = w.split('-').collect();
|
||||
if parts.iter().any(|p| p.is_empty()) || parts.len() > 4 {
|
||||
return false;
|
||||
@@ -353,7 +365,7 @@ fn hyphenated(d: &AffixDict, w: &str) -> bool {
|
||||
&& lp.iter().skip(k).all(|p| PARTICLES.contains(p))
|
||||
{
|
||||
let base = parts.get(..k).map(|b| b.join("-")).unwrap_or_default();
|
||||
return known(d, &base) || (base.contains('-') && hyphenated(d, &base));
|
||||
return known(d, &base) || (base.contains('-') && hyphenated(d, &base, opts));
|
||||
}
|
||||
match lp.as_slice() {
|
||||
// `кое-кто`, `кой-какой`.
|
||||
@@ -369,7 +381,7 @@ fn hyphenated(d: &AffixDict, w: &str) -> bool {
|
||||
let last = parts.len() - 1;
|
||||
parts.iter().enumerate().all(|(i, p)| {
|
||||
// An abbreviation part (`ИИ-консультант`, `SMS-рассылка`) or a known word.
|
||||
if known(d, p) || (p.chars().all(|c| !c.is_lowercase()) && p.chars().count() <= ABBREVIATION_LETTERS) {
|
||||
if known(d, p) || (opts.ignore_uppercase && p.chars().all(|c| !c.is_lowercase()) && p.chars().count() <= ABBREVIATION_LETTERS) {
|
||||
return true;
|
||||
}
|
||||
// A first part with a linking vowel: the stem (`северо` → `север`) or its adjective
|
||||
@@ -497,4 +509,25 @@ mod tests {
|
||||
crate::add_word("Зкщфрусскоеслово");
|
||||
assert!(is_correct("зкщфрусскоеслово"));
|
||||
}
|
||||
|
||||
/// With Ignore words in UPPERCASE or Ignore words that contain numbers off, Russian checks
|
||||
/// those words against the dictionary instead of accepting them.
|
||||
#[test]
|
||||
fn proofing_options_reach_the_russian_check() {
|
||||
test_dict::install();
|
||||
let lang = crate::ProofLang::Ru;
|
||||
let defaults = crate::Options::default();
|
||||
let check_caps = crate::Options { ignore_uppercase: false, ..defaults };
|
||||
let check_digits = crate::Options { ignore_numbers: false, ..defaults };
|
||||
assert!(crate::is_correct_in_with("ПРЕВЕТ", lang, &defaults), "short capitals are abbreviations by default");
|
||||
assert!(!crate::is_correct_in_with("ПРЕВЕТ", lang, &check_caps));
|
||||
assert!(crate::is_correct_in_with("ПРИВЕТ", lang, &check_caps));
|
||||
assert!(crate::is_correct_in_with("ИИ-консультант", lang, &defaults));
|
||||
assert!(!crate::is_correct_in_with("ИИ-консультант", lang, &check_caps), "a part in capitals is checked too");
|
||||
assert!(crate::is_correct_in_with("превет2", lang, &defaults));
|
||||
assert!(!crate::is_correct_in_with("превет2", lang, &check_digits));
|
||||
assert!(!crate::is_correct_in_with("м²", lang, &check_digits), "a superscript is a number too");
|
||||
assert!(crate::is_correct_in_with("2026", lang, &check_digits), "numbers alone stay correct");
|
||||
assert!(is_correct("ПРЕВЕТ"), "direct checks keep the defaults");
|
||||
}
|
||||
}
|
||||
@@ -15,6 +15,8 @@ pub mod dict;
|
||||
pub mod grammar;
|
||||
pub mod hyphen;
|
||||
pub mod suggest;
|
||||
#[cfg(test)]
|
||||
pub(crate) mod test_dict;
|
||||
|
||||
use std::sync::{Arc, RwLock};
|
||||
|
||||
@@ -87,15 +89,26 @@ pub fn is_correct(word: &str) -> bool {
|
||||
is_correct_with(&dictionary(), word)
|
||||
}
|
||||
|
||||
/// [`is_correct`] with the File › Options › Proofing choices: with Ignore words that contain
|
||||
/// numbers off, words with digits are checked against the dictionary too.
|
||||
pub fn is_correct_with_options(word: &str, opts: &crate::Options) -> bool {
|
||||
check(&dictionary(), word, opts)
|
||||
}
|
||||
|
||||
/// [`is_correct`] against a given dictionary.
|
||||
pub fn is_correct_with(d: &TrDict, word: &str) -> bool {
|
||||
check(d, word, &crate::Options::default())
|
||||
}
|
||||
|
||||
/// [`is_correct_with_options`] against a given dictionary.
|
||||
fn check(d: &TrDict, word: &str, opts: &crate::Options) -> bool {
|
||||
if d.is_empty() {
|
||||
return true; // No Turkish dictionary installed: no spelling marks
|
||||
}
|
||||
let w = word.trim_matches(|c: char| !c.is_alphanumeric() && c != '\'' && c != '’');
|
||||
let w = w.trim_matches(['\'', '’']);
|
||||
let n = w.chars().count();
|
||||
if n <= 1 || w.chars().any(|c| c.is_ascii_digit()) || !w.chars().any(char::is_alphabetic) {
|
||||
if n <= 1 || (opts.ignore_numbers && w.chars().any(|c| c.is_ascii_digit())) || !w.chars().any(char::is_alphabetic) {
|
||||
return true;
|
||||
}
|
||||
// Check user dictionary first
|
||||
@@ -120,7 +133,7 @@ pub fn is_correct_with(d: &TrDict, word: &str) -> bool {
|
||||
}
|
||||
|
||||
// Compound words separated by hyphens (e.g., `afyon-karahisar`)
|
||||
if w.contains('-') && w.split('-').all(|part| part.is_empty() || is_correct_with(d, part)) {
|
||||
if w.contains('-') && w.split('-').all(|part| part.is_empty() || check(d, part, opts)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -146,11 +159,8 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn installed_dictionary_checks_words_if_present() {
|
||||
// Machines without a Turkish Hunspell dictionary (CI, most desktops) have nothing to check.
|
||||
if !has_dictionary() {
|
||||
return;
|
||||
}
|
||||
fn installed_dictionary_checks_words() {
|
||||
test_dict::install();
|
||||
assert!(is_correct("kitap"));
|
||||
assert!(is_correct("kitaplar"));
|
||||
assert!(is_correct("evde"));
|
||||
@@ -165,4 +175,19 @@ mod tests {
|
||||
crate::add_word("benimbilmedigimkelime");
|
||||
assert!(is_correct("benimbilmedigimkelime"));
|
||||
}
|
||||
|
||||
/// With Ignore words that contain numbers off, Turkish checks words with digits against the
|
||||
/// dictionary instead of accepting them, hyphen parts included.
|
||||
#[test]
|
||||
fn proofing_options_reach_the_turkish_check() {
|
||||
test_dict::install();
|
||||
let lang = crate::ProofLang::Tr;
|
||||
let defaults = crate::Options::default();
|
||||
let check_digits = crate::Options { ignore_numbers: false, ..defaults };
|
||||
assert!(crate::is_correct_in_with("kitapp2", lang, &defaults));
|
||||
assert!(!crate::is_correct_in_with("kitapp2", lang, &check_digits));
|
||||
assert!(!crate::is_correct_in_with("ev-kitapp2", lang, &check_digits));
|
||||
assert!(crate::is_correct_in_with("2026", lang, &check_digits), "numbers alone stay correct");
|
||||
assert!(is_correct("kitapp2"), "direct checks keep the defaults");
|
||||
}
|
||||
}
|
||||
@@ -285,10 +285,7 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn typo_transposition_is_suggested() {
|
||||
// Suggestions come from the installed Turkish dictionary; without one there are none.
|
||||
if !super::super::has_dictionary() {
|
||||
return;
|
||||
}
|
||||
crate::tr::test_dict::install();
|
||||
let sugs = suggest("sorna", 3);
|
||||
assert!(sugs.contains(&"sonra".to_string()), "sorna should suggest sonra, got {sugs:?}");
|
||||
|
||||
|
||||
@@ -0,0 +1,22 @@
|
||||
//! A tiny synthetic Turkish Hunspell dictionary for tests (written for these tests; not taken from
|
||||
//! any real dictionary). Real dictionaries are installed on the system, never bundled.
|
||||
|
||||
/// No affix rules: the forms the tests look up are listed whole.
|
||||
pub const AFF: &str = "SET UTF-8\n";
|
||||
|
||||
/// The words the Turkish tests expect to be known.
|
||||
pub const DIC: &str = "7
|
||||
kitap
|
||||
kitaplar
|
||||
ev
|
||||
evde
|
||||
olacaklardan
|
||||
sonra
|
||||
geldin
|
||||
";
|
||||
|
||||
pub fn install() {
|
||||
if let Err(e) = super::install_dictionary(AFF, DIC) {
|
||||
panic!("test dictionary: {e}");
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user