Merge remote-tracking branch 'upstream/master' into literate-haskell

README.md

@@ -39,7 +39,7 @@ If you want to use Harper on your machine, you have three choices.
 
 `harper-ls` provides an integration that works for most code editors.
 
-[Read more here.](./harper-ls/README.md)
+[Read more here.](https://writewithharper.com/docs/integrations/language-server)
 
 ### Harper Obsidian Integration
 

harper-cli/Cargo.toml

@@ -10,7 +10,7 @@ repository = "https://github.com/automattic/harper"
 anyhow = "1.0.95"
 ariadne = "0.4.1"
 clap = { version = "4.5.23", features = ["derive"] }
-harper-core = { path = "../harper-core", version = "0.13.0" }
-harper-literate-haskell = { path = "../harper-literate-haskell", version = "0.13.0" }
-harper-comments = { path = "../harper-comments", version = "0.13.0" }
+harper-core = { path = "../harper-core", version = "0.14.0" }
+harper-literate-haskell = { path = "../harper-literate-haskell", version = "0.14.0" }
+harper-comments = { path = "../harper-comments", version = "0.14.0" }
 serde_json = "1.0.133"

harper-comments/Cargo.toml

@@ -1,16 +1,16 @@
 [package]
 name = "harper-comments"
-version = "0.13.0"
+version = "0.14.0"
 edition = "2021"
 description = "The language checker for developers."
 license = "Apache-2.0"
 readme = "README.md"
 repository = "https://github.com/automattic/harper"
 
 [dependencies]
-harper-core = { path = "../harper-core", version = "0.13.0" }
-harper-html = { path = "../harper-html", version = "0.13.0" }
-harper-tree-sitter = { path = "../harper-tree-sitter", version = "0.13.0" }
+harper-core = { path = "../harper-core", version = "0.14.0" }
+harper-html = { path = "../harper-html", version = "0.14.0" }
+harper-tree-sitter = { path = "../harper-tree-sitter", version = "0.14.0" }
 tree-sitter = "0.20.10"
 tree-sitter-rust = "0.20.4"
 tree-sitter-typescript = "0.20.3"

harper-core/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "harper-core"
-version = "0.13.0"
+version = "0.14.0"
 edition = "2021"
 description = "The language checker for developers."
 license = "Apache-2.0"

harper-core/src/linting/an_a.rs

@@ -62,6 +62,10 @@ impl Linter for AnA {
 
         lints
     }
+
+    fn description(&self) -> &'static str {
+        "A rule that looks for incorrect indefinite articles. For example, \"this is an mule\" would be flagged as incorrect."
+    }
 }
 
 fn to_lower_word(word: &[char]) -> Cow<'_, [char]> {

harper-core/src/linting/avoid_curses.rs

@@ -18,6 +18,10 @@ impl Linter for AvoidCurses {
             })
             .collect()
     }
+
+    fn description(&self) -> &'static str {
+        "A rule that looks for common offensive language."
+    }
 }
 
 #[cfg(test)]

harper-core/src/linting/boring_words.rs

@@ -44,4 +44,8 @@ impl PatternLinter for BoringWords {
             priority: 127,
         }
     }
+
+    fn description(&self) -> &'static str {
+        "This rule looks for particularly boring or overused words. Using varied language is an easy way to keep a reader's attention."
+    }
 }

harper-core/src/linting/capitalize_personal_pronouns.rs

@@ -34,6 +34,10 @@ impl Linter for CapitalizePersonalPronouns {
 
         lints
     }
+
+    fn description(&self) -> &'static str {
+        "Forgetting to capitalize personal pronouns, like \"I\" or \"I'm\" is one of the most common errors. This rule helps with that."
+    }
 }
 
 #[cfg(test)]

harper-core/src/linting/correct_number_suffix.rs

@@ -31,6 +31,10 @@ impl Linter for CorrectNumberSuffix {
 
         output
     }
+
+    fn description(&self) -> &'static str {
+        "When making quick edits, it is common for authors to change the value of a number without changing its suffix. This rule looks for these cases, for example: \"2st\"."
+    }
 }
 
 #[cfg(test)]

harper-core/src/linting/dot_initialisms.rs

@@ -51,6 +51,10 @@ impl PatternLinter for DotInitialisms {
             priority: 63,
         }
     }
+
+    fn description(&self) -> &'static str {
+        "Ensures common initialisms (like \"i.e.\") are properly dot-separated."
+    }
 }
 
 #[cfg(test)]

harper-core/src/linting/ellipsis_length.rs

@@ -35,6 +35,10 @@ impl Linter for EllipsisLength {
 
         lints
     }
+
+    fn description(&self) -> &'static str {
+        "Make sure you have the correct number of dots in your ellipsis."
+    }
 }
 
 #[cfg(test)]

harper-core/src/linting/linking_verbs.rs

@@ -34,6 +34,10 @@ impl Linter for LinkingVerbs {
 
         output
     }
+
+    fn description(&self) -> &'static str {
+        "Linking verbs connect nouns to other ideas. Make sure you do not accidentaly link words that aren't nouns."
+    }
 }
 
 #[cfg(test)]

harper-core/src/linting/lint_group.rs

@@ -13,6 +13,10 @@ use super::long_sentences::LongSentences;
 use super::matcher::Matcher;
 use super::multiple_sequential_pronouns::MultipleSequentialPronouns;
 use super::number_suffix_capitalization::NumberSuffixCapitalization;
+use super::proper_noun_capitalization_linters::{
+    AmazonNames, Americas, AppleNames, AzureNames, ChineseCommunistParty, GoogleNames, Holidays,
+    MetaNames, MicrosoftNames, UnitedOrganizations,
+};
 use super::repeated_words::RepeatedWords;
 use super::sentence_capitalization::SentenceCapitalization;
 use super::spaces::Spaces;
@@ -29,6 +33,16 @@ use crate::{Dictionary, Document};
 macro_rules! create_lint_group_config {
     ($($linter:ident => $default:expr),*) => {
         paste! {
+            /// A collection of all the descriptions from the composing linters.
+            #[derive(Debug, Clone, Copy, Serialize, Deserialize, Default)]
+            pub struct LintGroupDescriptions<'a> {
+                $(
+                    #[doc = "The description for the [`" $linter "`] linter."]
+                    pub [<$linter:snake>]: &'a str,
+                )*
+                pub spell_check: &'a str
+            }
+
             #[derive(Debug, Clone, Copy, Serialize, Deserialize, Default)]
             pub struct LintGroupConfig {
                 $(
@@ -85,10 +99,19 @@ macro_rules! create_lint_group_config {
                         config,
                     }
                 }
+
+                pub fn all_descriptions(&self) -> LintGroupDescriptions<'_> {
+                    LintGroupDescriptions {
+                        $(
+                            [<$linter:snake>]: self.[<$linter:snake>].description(),
+                        )*
+                        spell_check: self.spell_check.description(),
+                    }
+                }
             }
 
             impl<T: Dictionary> Linter for LintGroup<T> {
-                fn lint(&mut self, document: &Document) -> Vec<Lint>{
+                fn lint(&mut self, document: &Document) -> Vec<Lint> {
                     let mut lints = Vec::new();
 
                     let mut config = self.config.clone();
@@ -107,6 +130,10 @@ macro_rules! create_lint_group_config {
 
                     lints
                 }
+
+                fn description(&self) -> &'static str {
+                    "A collection of linters that can be run as one."
+                }
             }
         }
     };
@@ -133,11 +160,34 @@ create_lint_group_config!(
     BoringWords => false,
     UseGenitive => false,
     ThatWhich => true,
-    CapitalizePersonalPronouns => true
+    CapitalizePersonalPronouns => true,
+    Americas => true,
+    ChineseCommunistParty => true,
+    UnitedOrganizations => true,
+    Holidays => true,
+    AmazonNames => true,
+    GoogleNames => true,
+    MetaNames => true,
+    MicrosoftNames => true,
+    AppleNames => true,
+    AzureNames => true
 );
 
 impl<T: Dictionary + Default> Default for LintGroup<T> {
     fn default() -> Self {
         Self::new(LintGroupConfig::default(), T::default())
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use crate::FullDictionary;
+
+    use super::LintGroup;
+
+    #[test]
+    fn can_get_all_descriptions() {
+        let group = LintGroup::<FullDictionary>::default();
+        group.all_descriptions();
+    }
+}

harper-core/src/linting/long_sentences.rs

@@ -25,4 +25,9 @@ impl Linter for LongSentences {
 
         output
     }
+
+    fn description(&self) -> &'static str {
+        "This rule looks for run-on sentences, which can make your work harder to grok.
+"
+    }
 }

harper-core/src/linting/matcher.rs

@@ -137,12 +137,6 @@ impl Matcher {
             "ngram" => "n-gram",
             "grammer" => "grammar",
             "There","fore" => "Therefore",
-            "south","America" => "South America",
-            "South","america" => "South America",
-            "south","america" => "South America",
-            "North","america" => "North America",
-            "north","America" => "North America",
-            "north","america" => "North America",
             "fatal","outcome" => "death",
             "geiger","counter" => "Geiger counter",
             "veterans","day" => "Veterans Day",
@@ -364,6 +358,10 @@ impl Linter for Matcher {
 
         lints
     }
+
+    fn description(&self) -> &'static str {
+        "A collection of curated rules. A catch-all that will be removed in the future."
+    }
 }
 
 #[cfg(test)]

harper-core/src/linting/mod.rs

@@ -13,6 +13,7 @@ mod matcher;
 mod multiple_sequential_pronouns;
 mod number_suffix_capitalization;
 mod pattern_linter;
+mod proper_noun_capitalization_linters;
 mod repeated_words;
 mod sentence_capitalization;
 mod spaces;
@@ -39,6 +40,10 @@ pub use matcher::Matcher;
 pub use multiple_sequential_pronouns::MultipleSequentialPronouns;
 pub use number_suffix_capitalization::NumberSuffixCapitalization;
 pub use pattern_linter::PatternLinter;
+pub use proper_noun_capitalization_linters::{
+    AmazonNames, Americas, AppleNames, AzureNames, ChineseCommunistParty, GoogleNames, Holidays,
+    MetaNames, MicrosoftNames, UnitedOrganizations,
+};
 pub use repeated_words::RepeatedWords;
 pub use sentence_capitalization::SentenceCapitalization;
 pub use spaces::Spaces;
@@ -55,10 +60,12 @@ use crate::Document;
 #[cfg(not(feature = "concurrent"))]
 pub trait Linter {
     fn lint(&mut self, document: &Document) -> Vec<Lint>;
+    fn description(&self) -> &str;
 }
 #[cfg(feature = "concurrent")]
 pub trait Linter: Send + Sync {
     fn lint(&mut self, document: &Document) -> Vec<Lint>;
+    fn description(&self) -> &str;
 }
 
 #[cfg(test)]

harper-core/src/linting/multiple_sequential_pronouns.rs

@@ -61,6 +61,10 @@ impl PatternLinter for MultipleSequentialPronouns {
             suggestions,
         }
     }
+
+    fn description(&self) -> &'static str {
+        "When editing work to change point of view (i.e. first-person or third-person) it is common to add pronouns while neglecting to remove old ones. This rule catches cases where you have multiple disparate pronouns in sequence."
+    }
 }
 
 impl Default for MultipleSequentialPronouns {

harper-core/src/linting/number_suffix_capitalization.rs

@@ -33,6 +33,10 @@ impl Linter for NumberSuffixCapitalization {
 
         output
     }
+
+    fn description(&self) -> &'static str {
+        "You should never capitalize number suffixes."
+    }
 }
 
 #[cfg(test)]

harper-core/src/linting/pattern_linter.rs

@@ -7,13 +7,15 @@ pub trait PatternLinter {
     /// A simple getter for the pattern to be searched for.
     fn pattern(&self) -> &dyn Pattern;
     fn match_to_lint(&self, matched_tokens: &[Token], source: &[char]) -> Lint;
+    fn description<'a>(&'a self) -> &'a str;
 }
 
 #[cfg(feature = "concurrent")]
 pub trait PatternLinter: Send + Sync {
     /// A simple getter for the pattern to be searched for.
     fn pattern(&self) -> &dyn Pattern;
     fn match_to_lint(&self, matched_tokens: &[Token], source: &[char]) -> Lint;
+    fn description(&self) -> &str;
 }
 
 impl<L> Linter for L
@@ -48,4 +50,8 @@ where
 
         lints
     }
+
+    fn description(&self) -> &str {
+        self.description()
+    }
 }