feat(config): Allow ignoring words by regex

Fixes #852
This commit is contained in:
Ed Page 2023-10-16 12:37:00 -05:00
parent 35a8bc6787
commit be8628fcb3
8 changed files with 58 additions and 6 deletions

View file

@ -425,6 +425,8 @@ pub struct DictConfig {
#[serde(with = "serde_regex")] #[serde(with = "serde_regex")]
pub extend_ignore_identifiers_re: Vec<regex::Regex>, pub extend_ignore_identifiers_re: Vec<regex::Regex>,
pub extend_identifiers: HashMap<kstring::KString, kstring::KString>, pub extend_identifiers: HashMap<kstring::KString, kstring::KString>,
#[serde(with = "serde_regex")]
pub extend_ignore_words_re: Vec<regex::Regex>,
pub extend_words: HashMap<kstring::KString, kstring::KString>, pub extend_words: HashMap<kstring::KString, kstring::KString>,
} }
@ -435,6 +437,7 @@ impl DictConfig {
locale: Some(empty.locale()), locale: Some(empty.locale()),
extend_ignore_identifiers_re: Default::default(), extend_ignore_identifiers_re: Default::default(),
extend_identifiers: Default::default(), extend_identifiers: Default::default(),
extend_ignore_words_re: Default::default(),
extend_words: Default::default(), extend_words: Default::default(),
} }
} }
@ -451,6 +454,8 @@ impl DictConfig {
.iter() .iter()
.map(|(key, value)| (key.clone(), value.clone())), .map(|(key, value)| (key.clone(), value.clone())),
); );
self.extend_ignore_words_re
.extend(source.extend_ignore_words_re.iter().cloned());
self.extend_words.extend( self.extend_words.extend(
source source
.extend_words .extend_words
@ -475,6 +480,10 @@ impl DictConfig {
) )
} }
pub fn extend_ignore_words_re(&self) -> Box<dyn Iterator<Item = &regex::Regex> + '_> {
Box::new(self.extend_ignore_words_re.iter())
}
pub fn extend_words(&self) -> Box<dyn Iterator<Item = (&str, &str)> + '_> { pub fn extend_words(&self) -> Box<dyn Iterator<Item = (&str, &str)> + '_> {
Box::new( Box::new(
self.extend_words self.extend_words
@ -503,6 +512,11 @@ impl PartialEq for DictConfig {
.map(|r| r.as_str()) .map(|r| r.as_str())
.eq(rhs.extend_ignore_identifiers_re.iter().map(|r| r.as_str())) .eq(rhs.extend_ignore_identifiers_re.iter().map(|r| r.as_str()))
&& self.extend_identifiers == rhs.extend_identifiers && self.extend_identifiers == rhs.extend_identifiers
&& self
.extend_ignore_words_re
.iter()
.map(|r| r.as_str())
.eq(rhs.extend_ignore_words_re.iter().map(|r| r.as_str()))
&& self.extend_words == rhs.extend_words && self.extend_words == rhs.extend_words
} }
} }

View file

@ -216,6 +216,7 @@ fn case_correct(correction: &mut Cow<'_, str>, case: Case) {
pub struct Override<'i, 'w, D> { pub struct Override<'i, 'w, D> {
ignored_identifiers: Vec<regex::Regex>, ignored_identifiers: Vec<regex::Regex>,
identifiers: HashMap<&'i str, Status<'i>, ahash::RandomState>, identifiers: HashMap<&'i str, Status<'i>, ahash::RandomState>,
ignored_words: Vec<regex::Regex>,
words: HashMap<unicase::UniCase<&'w str>, Status<'w>, ahash::RandomState>, words: HashMap<unicase::UniCase<&'w str>, Status<'w>, ahash::RandomState>,
inner: D, inner: D,
} }
@ -225,6 +226,7 @@ impl<'i, 'w, D: typos::Dictionary> Override<'i, 'w, D> {
Self { Self {
ignored_identifiers: Default::default(), ignored_identifiers: Default::default(),
identifiers: Default::default(), identifiers: Default::default(),
ignored_words: Default::default(),
words: Default::default(), words: Default::default(),
inner, inner,
} }
@ -238,6 +240,10 @@ impl<'i, 'w, D: typos::Dictionary> Override<'i, 'w, D> {
self.identifiers = Self::interpret(identifiers).collect(); self.identifiers = Self::interpret(identifiers).collect();
} }
pub fn ignored_words<'r>(&mut self, ignored: impl Iterator<Item = &'r regex::Regex>) {
self.ignored_words.extend(ignored.cloned());
}
pub fn words<I: Iterator<Item = (&'w str, &'w str)>>(&mut self, words: I) { pub fn words<I: Iterator<Item = (&'w str, &'w str)>>(&mut self, words: I) {
self.words = Self::interpret(words) self.words = Self::interpret(words)
.map(|(k, v)| (UniCase::new(k), v)) .map(|(k, v)| (UniCase::new(k), v))
@ -283,15 +289,22 @@ impl<'i, 'w, D: typos::Dictionary> typos::Dictionary for Override<'i, 'w, D> {
return None; return None;
} }
for ignored in &self.ignored_words {
if ignored.is_match(word.token()) {
return Some(Status::Valid);
}
}
// Skip hashing if we can // Skip hashing if we can
let custom = if !self.words.is_empty() { if !self.words.is_empty() {
let w = UniCase::new(word.token()); let w = UniCase::new(word.token());
// HACK: couldn't figure out the lifetime issue with replacing `cloned` with `borrow` // HACK: couldn't figure out the lifetime issue with replacing `cloned` with `borrow`
self.words.get(&w).cloned() if let Some(status) = self.words.get(&w).cloned() {
} else { return Some(status);
None }
}; }
custom.or_else(|| self.inner.correct_word(word))
self.inner.correct_word(word)
} }
} }

View file

@ -255,6 +255,7 @@ impl<'s> ConfigEngine<'s> {
.extend_identifiers() .extend_identifiers()
.map(|(k, v)| (self.storage.get(k), self.storage.get(v))), .map(|(k, v)| (self.storage.get(k), self.storage.get(v))),
); );
dict.ignored_words(dict_config.extend_ignore_words_re());
dict.words( dict.words(
dict_config dict_config
.extend_words() .extend_words()

View file

@ -0,0 +1,9 @@
[default.extend-words]
hello = "goodbye"
[type.fail]
extend-glob = ["*.fail"]
[type.ignore]
extend-glob = ["*.ignore"]
extend-ignore-words-re = ["he.*"]

View file

@ -0,0 +1 @@
hello

View file

@ -0,0 +1 @@
hello

View file

@ -0,0 +1,12 @@
bin.name = "typos"
status.code = 2
stdin = ""
stdout = """
error: `hello` should be `goodbye`
--> ./file.fail:1:1
|
1 | hello
| ^^^^^
|
"""
stderr = ""

View file

@ -34,6 +34,7 @@ Configuration is read from the following (in precedence order)
| default.extend-identifiers | \- | table of strings | Corrections for [identifiers](./design.md#identifiers-and-words). When the correction is blank, the identifier is never valid. When the correction is the key, the identifier is always valid. | | default.extend-identifiers | \- | table of strings | Corrections for [identifiers](./design.md#identifiers-and-words). When the correction is blank, the identifier is never valid. When the correction is the key, the identifier is always valid. |
| default.extend-ignore-identifiers-re | \- | list of [regexes](https://docs.rs/regex/latest/regex/index.html#syntax) | Pattern-match always-valid identifiers | | default.extend-ignore-identifiers-re | \- | list of [regexes](https://docs.rs/regex/latest/regex/index.html#syntax) | Pattern-match always-valid identifiers |
| default.extend-words | \- | table of strings | Corrections for [words](./design.md#identifiers-and-words). When the correction is blank, the word is never valid. When the correction is the key, the word is always valid. | | default.extend-words | \- | table of strings | Corrections for [words](./design.md#identifiers-and-words). When the correction is blank, the word is never valid. When the correction is the key, the word is always valid. |
| default.extend-ignore-words-re | \- | list of [regexes](https://docs.rs/regex/latest/regex/index.html#syntax) | Pattern-match always-valid words. Note: you must handle case insensitivity yourself |
| type.\<name>.\<field> | \<varied> | \<varied> | See `default.` for child keys. Run with `--type-list` to see available `<name>`s | | type.\<name>.\<field> | \<varied> | \<varied> | See `default.` for child keys. Run with `--type-list` to see available `<name>`s |
| type.\<name>.extend-glob | \- | list of strings | File globs for matching `<name>` | | type.\<name>.extend-glob | \- | list of strings | File globs for matching `<name>` |