feat(core): more rules (#2107)

Author: elijah-potter

harper-comments/tests/language_support_sources/clean.sol

@@ -11,9 +11,8 @@ contract TestContract {
      * @notice This is another test function.
      * @dev It has another [link](https://example.com) embedded inside
      * @param p This is a parameter
-     * @return fooBar The return value.
      */
-    function testFunction2(uint256 p) external returns (address fooBar) {}
+    function testFunction2(uint256 p) external {}
 
     // This is some gibberish to try to trigger a lint for sentences that continue for too long
     //

harper-comments/tests/language_support_sources/javadoc_clean_simple.java

@@ -1,7 +1,7 @@
 class TestClass {
 
   /**
-   * This is a Javadoc without any of the fancy frills that come with it.
+   * This is a JavaDoc without any of the fancy frills that come with it.
    */
   public static void main(String[] args) {
     System.out.println("Hello world.");

harper-core/dictionary.dict

@@ -28667,7 +28667,6 @@ howsoever/
 hoyden/NgSJV
 hoydenish/J
 hp/~N
-hr/~NS
 ht/~N
 huarache/NSg
 hub/~NOSg
@@ -33014,7 +33013,6 @@ marital/~JY
 maritime/~J
 marjoram/Ng
 mark/~NgSVdGr
-markdown/NgS
 marked/~JVtTU
 markedly/~R
 marker/~NgSV
@@ -52984,7 +52982,6 @@ JWT/Ng              # JSON Web Token
 Jacoco/Sg
 JavaDoc/Sg
 JavaScript/ONSg     # programming language
-Javadoc/Sg
 JetBrains
 Jetpack/Og
 Jira/Og             # issue tracker

harper-core/proper_noun_rules.json

@@ -527,6 +527,7 @@
 			"Las Vegas",
 			"Los Angeles",
 			"New York",
+			"New York City",
 			"Niagara Falls",
 			"Novi Sad",
 			"Panama Canal",

harper-core/src/char_ext.rs

@@ -13,6 +13,7 @@ pub trait CharExt {
     ///
     /// Checks whether the character is in the set (A, E, I, O, U); case-insensitive.
     fn is_vowel(&self) -> bool;
+    fn normalized(self) -> Self;
 }
 
 impl CharExt for char {
@@ -27,6 +28,13 @@ impl CharExt for char {
             && self.script() == Script::Latin
     }
 
+    fn normalized(self) -> Self {
+        match self {
+            '’' | '‘' | 'ʼ' | '＇' => '\'',
+            _ => self,
+        }
+    }
+
     fn is_emoji(&self) -> bool {
         let Some(block) = unicode_blocks::find_unicode_block(*self) else {
             return false;

harper-core/src/char_string.rs

@@ -1,3 +1,4 @@
+use crate::char_ext::CharExt;
 use std::borrow::Cow;
 
 use smallvec::SmallVec;
@@ -58,12 +59,12 @@ impl CharStringExt for [char] {
     /// Convert a given character sequence to the standard character set
     /// the dictionary is in.
     fn normalized(&'_ self) -> Cow<'_, [char]> {
-        if self.as_ref().iter().any(|c| char_to_normalized(*c) != *c) {
+        if self.as_ref().iter().any(|c| c.normalized() != *c) {
             Cow::Owned(
                 self.as_ref()
                     .iter()
                     .copied()
-                    .map(char_to_normalized)
+                    .map(|c| c.normalized())
                     .collect(),
             )
         } else {
@@ -120,15 +121,6 @@ impl CharStringExt for [char] {
     }
 }
 
-fn char_to_normalized(c: char) -> char {
-    match c {
-        '’' => '\'',
-        '‘' => '\'',
-        '＇' => '\'',
-        _ => c,
-    }
-}
-
 macro_rules! char_string {
     ($string:literal) => {{
         use crate::char_string::CharString;