feat: precommit script

.github/workflows/precommit.yml

@@ -0,0 +1,22 @@
+name: Precommit
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  precommit:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-node@v4
+    - name: Install Rust Nightly
+      run: rustup toolchain install nightly && rustup component add rustfmt --toolchain nightly
+    - name: Precommit
+      run: ./precommit.sh

README.md

@@ -3,8 +3,9 @@
     <h1>Harper</h1>
 </div>
 
-[![Build](https://github.com/chilipepperhott/harper/actions/workflows/build.yml/badge.svg)](https://github.com/chilipepperhott/harper/actions/workflows/build.yml)
-[![Rust Tests](https://github.com/chilipepperhott/harper/actions/workflows/rust-tests.yml/badge.svg)](https://github.com/chilipepperhott/harper/actions/workflows/rust-tests.yml)
+[![Harper LS](https://github.com/chilipepperhott/harper/actions/workflows/build_harper_ls.yml/badge.svg)](https://github.com/chilipepperhott/harper/actions/workflows/build_harper_ls.yml)
+[![Web](https://github.com/chilipepperhott/harper/actions/workflows/build_web.yml/badge.svg)](https://github.com/chilipepperhott/harper/actions/workflows/build_web.yml)
+[![Precommit](https://github.com/chilipepperhott/harper/actions/workflows/precommit.yml/badge.svg)](https://github.com/chilipepperhott/harper/actions/workflows/precommit.yml)
 
 Harper is a an English grammar checker designed to be _just right._
 I created it after years of dealing with the shortcomings of the competition.

harper-core/src/document.rs

@@ -2,20 +2,16 @@ use std::fmt::Display;
 
 use itertools::Itertools;
 
+use crate::linting::Suggestion;
 use crate::parsers::{Markdown, Parser, PlainEnglish};
-use crate::TokenStringExt;
-use crate::{
-    linting::Suggestion,
-    span::Span,
-    FatToken,
-    Punctuation::{self},
-    Token, TokenKind,
-};
+use crate::span::Span;
+use crate::Punctuation::{self};
+use crate::{FatToken, Token, TokenKind, TokenStringExt};
 
 pub struct Document {
     source: Vec<char>,
     tokens: Vec<Token>,
-    parser: Box<dyn Parser>,
+    parser: Box<dyn Parser>
 }
 
 impl Default for Document {
@@ -33,7 +29,7 @@ impl Document {
         let mut doc = Self {
             source,
             tokens: Vec::new(),
-            parser,
+            parser
         };
         doc.parse();
 
@@ -137,7 +133,7 @@ impl Document {
     pub fn get_full_string(&self) -> String {
         self.get_span_content_str(Span {
             start: 0,
-            end: self.source.len(),
+            end: self.source.len()
         })
     }
 
@@ -165,8 +161,9 @@ impl Document {
         self.parse();
     }
 
-    /// Searches for quotation marks and fills the [`Punctuation::Quote::twin_loc`] field.
-    /// This is on a best effort basis.
+    /// Searches for quotation marks and fills the
+    /// [`Punctuation::Quote::twin_loc`] field. This is on a best effort
+    /// basis.
     ///
     /// Current algorithm is very basic and could use some work.
     fn match_quotes(&mut self) {
@@ -188,7 +185,8 @@ impl Document {
         }
     }
 
-    /// Searches for contractions and condenses them down into single self.tokens
+    /// Searches for contractions and condenses them down into single
+    /// self.tokens
     fn condense_contractions(&mut self) {
         if self.tokens.len() < 3 {
             return;
@@ -233,7 +231,7 @@ impl Document {
             &old[0..replace_starts
                 .first()
                 .copied()
-                .unwrap_or(replace_starts.len())],
+                .unwrap_or(replace_starts.len())]
         );
 
         let mut iter = replace_starts.iter().peekable();
@@ -251,7 +249,7 @@ impl Document {
             &old[replace_starts
                 .last()
                 .map(|v| v + 3)
-                .unwrap_or(replace_starts.len())..],
+                .unwrap_or(replace_starts.len())..]
         )
     }
 }
@@ -321,21 +319,19 @@ fn is_sentence_terminator(token: &TokenKind) -> bool {
         TokenKind::Punctuation(punct) => [
             Punctuation::Period,
             Punctuation::Bang,
-            Punctuation::Question,
+            Punctuation::Question
         ]
         .contains(punct),
         TokenKind::Newline(_) => true,
-        _ => false,
+        _ => false
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::Document;
-    use crate::{
-        parsers::{Markdown, PlainEnglish},
-        token::TokenStringExt,
-    };
+    use crate::parsers::{Markdown, PlainEnglish};
+    use crate::token::TokenStringExt;
 
     #[test]
     fn parses_sentences_correctly() {

harper-core/src/lexing/email_address.rs

@@ -1,8 +1,7 @@
 use itertools::Itertools;
 
-use crate::TokenKind;
-
 use super::FoundToken;
+use crate::TokenKind;
 
 pub fn lex_email_address(source: &[char]) -> Option<FoundToken> {
     // Location of the @ sign
@@ -31,7 +30,7 @@ pub fn lex_email_address(source: &[char]) -> Option<FoundToken> {
 
     Some(FoundToken {
         next_index: at_loc + 1 + domain_part_len,
-        token: TokenKind::EmailAddress,
+        token: TokenKind::EmailAddress
     })
 }
 
@@ -103,7 +102,7 @@ fn valid_unquoted_character(c: char) -> bool {
 
     let others = [
         '!', '#', '$', '%', '&', '\'', '*', '+', '-', '/', '=', '?', '^', '_', '`', '{', '|', '}',
-        '~', '.',
+        '~', '.'
     ];
 
     if others.contains(&c) {
@@ -136,9 +135,8 @@ fn validate_hostname(source: &[char]) -> bool {
 
 #[cfg(test)]
 mod tests {
-    use crate::lexing::email_address::validate_hostname;
-
     use super::{lex_email_address, validate_local_part};
+    use crate::lexing::email_address::validate_hostname;
 
     fn example_local_parts() -> impl Iterator<Item = Vec<char>> {
         [
@@ -158,7 +156,7 @@ mod tests {
             r#"user-"#,
             r#"postmaster"#,
             r#"postmaster"#,
-            r#"_test"#,
+            r#"_test"#
         ]
         .into_iter()
         .map(|s| s.chars().collect())
@@ -179,12 +177,11 @@ mod tests {
             r#"example.org"#,
             r#"strange.example.com"#,
             r#"example.org"#,
-            r#"example.org"#,
-            // The existing parser intentionally doesn't support IP addresses
-            // It simply isn't worth the effort at the moment.
-            // r#"[123.123.123.123]"#,
-            // r#"[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:7334]"#,
-            // r#"[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:7334]"#,
+            r#"example.org"# /* The existing parser intentionally doesn't support IP addresses
+                              * It simply isn't worth the effort at the moment.
+                              * r#"[123.123.123.123]"#,
+                              * r#"[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:7334]"#,
+                              * r#"[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:7334]"#, */
         ]
         .into_iter()
         .map(|s| s.chars().collect())

harper-core/src/lexing/mod.rs

@@ -1,17 +1,14 @@
 mod email_address;
 
-use crate::token::Quote;
-
-use crate::token::{Punctuation, TokenKind};
-
 use self::email_address::lex_email_address;
+use crate::token::{Punctuation, Quote, TokenKind};
 
 #[derive(Debug)]
 pub struct FoundToken {
     /// The index of the character __after__ the lexed token
     pub next_index: usize,
     /// Token lexed
-    pub token: TokenKind,
+    pub token: TokenKind
 }
 
 pub fn lex_token(source: &[char]) -> Option<FoundToken> {
@@ -21,7 +18,7 @@ pub fn lex_token(source: &[char]) -> Option<FoundToken> {
         lex_newlines,
         lex_number,
         lex_email_address,
-        lex_word,
+        lex_word
     ];
 
     for lexer in lexers {
@@ -46,7 +43,7 @@ fn lex_word(source: &[char]) -> Option<FoundToken> {
         } else {
             return Some(FoundToken {
                 next_index: end + 1,
-                token: TokenKind::Word,
+                token: TokenKind::Word
             });
         }
     }
@@ -78,7 +75,7 @@ pub fn lex_number(source: &[char]) -> Option<FoundToken> {
         if let Ok(n) = s.parse::<f64>() {
             return Some(FoundToken {
                 token: TokenKind::Number(n),
-                next_index: end + 1,
+                next_index: end + 1
             });
         }
     }
@@ -92,7 +89,7 @@ fn lex_newlines(source: &[char]) -> Option<FoundToken> {
     if count > 0 {
         Some(FoundToken {
             token: TokenKind::Newline(count),
-            next_index: count,
+            next_index: count
         })
     } else {
         None
@@ -105,7 +102,7 @@ fn lex_spaces(source: &[char]) -> Option<FoundToken> {
     if count > 0 {
         Some(FoundToken {
             token: TokenKind::Space(count),
-            next_index: count,
+            next_index: count
         })
     } else {
         None
@@ -156,12 +153,12 @@ fn lex_punctuation(source: &[char]) -> Option<FoundToken> {
         '$' => Dollar,
         '|' => Pipe,
         '_' => Underscore,
-        _ => return None,
+        _ => return None
     };
 
     Some(FoundToken {
         next_index: 1,
-        token: TokenKind::Punctuation(punct),
+        token: TokenKind::Punctuation(punct)
     })
 }
 
@@ -171,7 +168,7 @@ fn lex_quote(source: &[char]) -> Option<FoundToken> {
     if c == '\"' || c == '“' || c == '”' {
         Some(FoundToken {
             next_index: 1,
-            token: TokenKind::Punctuation(Punctuation::Quote(Quote { twin_loc: None })),
+            token: TokenKind::Punctuation(Punctuation::Quote(Quote { twin_loc: None }))
         })
     } else {
         None

harper-core/src/lib.rs

@@ -9,8 +9,7 @@ mod spell;
 mod token;
 
 pub use document::Document;
-pub use linting::LintSet;
-pub use linting::{Lint, LintKind, Linter, Suggestion};
+pub use linting::{Lint, LintKind, LintSet, Linter, Suggestion};
 pub use span::Span;
 pub use spell::{Dictionary, FullDictionary, MergedDictionary};
 pub use token::{FatToken, Punctuation, Token, TokenKind, TokenStringExt};

harper-core/src/linting/lint.rs

@@ -13,7 +13,7 @@ pub struct Lint {
     pub message: String,
     /// A numerical value for the importance of a lint.
     /// Lower = more important.
-    pub priority: u8,
+    pub priority: u8
 }
 
 impl Default for Lint {
@@ -23,7 +23,7 @@ impl Default for Lint {
             lint_kind: Default::default(),
             suggestions: Default::default(),
             message: Default::default(),
-            priority: 127,
+            priority: 127
         }
     }
 }
@@ -36,12 +36,12 @@ pub enum LintKind {
     Repetition,
     Readability,
     #[default]
-    Miscellaneous,
+    Miscellaneous
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize, Is)]
 pub enum Suggestion {
-    ReplaceWith(Vec<char>),
+    ReplaceWith(Vec<char>)
 }
 
 impl Display for Suggestion {