Merge branch 'master' into typst-support

README.md

@@ -4,9 +4,10 @@
 </div>
 
 [![Harper Binaries](https://github.com/automattic/harper/actions/workflows/build_harper_binaries.yml/badge.svg)](https://github.com/automattic/harper/actions/workflows/build_harper_binaries.yml)
-[![Web](https://github.com/automattic/harper/actions/workflows/build_web.yml/badge.svg)](https://github.com/automattic/harper/actions/workflows/build_web.yml)
+[![Website](https://github.com/automattic/harper/actions/workflows/build_web.yml/badge.svg)](https://github.com/automattic/harper/actions/workflows/build_web.yml)
 [![Precommit](https://github.com/automattic/harper/actions/workflows/precommit.yml/badge.svg)](https://github.com/automattic/harper/actions/workflows/precommit.yml)
 [![Crates.io](https://img.shields.io/crates/v/harper-ls)](https://crates.io/crates/harper-ls)
+![NPM Version](https://img.shields.io/npm/v/harper.js)
 
 Harper is an English grammar checker designed to be _just right._
 I created it after years of dealing with the shortcomings of the competition.
@@ -31,25 +32,6 @@ Harper is even small enough to load via [WebAssembly.](https://writewithharper.c
 
 Harper currently only supports American English, but the core is extensible to support other languages, so we welcome contributions that allow for other language support.
 
-## Installation
-
-If you want to use Harper on your machine, you have three choices.
-
-### `harper-ls`
-
-`harper-ls` provides an integration that works for most code editors.
-
-[Read more here.](https://writewithharper.com/docs/integrations/language-server)
-
-### Harper Obsidian Integration
-
-If you use [Obsidian](https://obsidian.md/), you may install the [Harper Obsidian Plugin](https://github.com/automattic/harper-obsidian-plugin) by searching for "Harper" in the community plugin store.
-
-### Zed Plugin
-
-If you use [Zed](https://zed.dev/), [Stef16Robbe](https://github.com/Stef16Robbe) has developed a fantastic [plugin](https://github.com/Stef16Robbe/harper_zed) that works out-of-the box.
-No setup required.
-
 ## Performance Issues
 
 We consider long lint times bugs.
@@ -58,15 +40,16 @@ If you encounter any significant performance issues, please create an issue on t
 If you find a fix to any performance issue, we are open the contribution.
 Just make sure to read [our contribution guidelines first.](https://github.com/automattic/harper/blob/master/CONTRIBUTING.md)
 
-## FAQs
-
-### Where did the name Harper come from?
+## Links
 
-See [this blog post](https://elijahpotter.dev/articles/naming_harper).
+- [Frequently Asked Questions](https://writewithharper.com/docs/faq)
+- [`harper-ls` Documentation](https://writewithharper.com/docs/integrations/language-server)
+- [Neovim Support](https://writewithharper.com/docs/integrations/neovim)
+- [`harper.js` Documentation](https://writewithharper.com/docs/harperjs/introduction)
 
 ## Huge Thanks
 
-This project would not be possible without the hard work from those who [contribute](/CONTRIBUTING.md).
+This project would not be possible without the hard work from those who [contribute](https://writewithharper.com/docs/contributors/introduction).
 
 <a href="https://github.com/automattic/harper/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=automattic/harper" />

demo.md

@@ -4,7 +4,7 @@ checkers don't cut it. That s where Harper comes in handy.
 Harper is an language checker for developers. it can detect
 improper capitalization and misspellled words,
 as well as a number of other issues.
-Like if you break up words you shouldn't.
+Like if you break up words you shoul dn't.
 
 Harper works everywhere, even offline. Since you r data
 never leaves your device, you don't ned to worry aout us

harper-cli/src/main.rs

@@ -8,7 +8,7 @@ use clap::Parser;
 use harper_comments::CommentParser;
 use harper_core::linting::{LintGroup, LintGroupConfig, Linter};
 use harper_core::parsers::Markdown;
-use harper_core::{remove_overlaps, Dictionary, Document, FstDictionary};
+use harper_core::{remove_overlaps, Dictionary, Document, FstDictionary, TokenKind};
 
 #[derive(Debug, Parser)]
 enum Args {
@@ -30,8 +30,13 @@ enum Args {
     Spans {
         /// The file you wish to display the spans.
         file: PathBuf,
+        /// Include newlines in the output
+        #[arg(short, long)]
+        include_newlines: bool,
     },
-    /// Emit decompressed, line-separated list of words in Harper's dictionary.
+    /// Get the metadata associated with a particular word.
+    Metadata { word: String },
+    /// Emit a decompressed, line-separated list of the words in Harper's dictionary.
     Words,
 }
 
@@ -89,11 +94,15 @@ fn main() -> anyhow::Result<()> {
 
             Ok(())
         }
-        Args::Spans { file } => {
+        Args::Spans {
+            file,
+            include_newlines,
+        } => {
             let (doc, source) = load_file(&file)?;
 
             let primary_color = Color::Blue;
             let secondary_color = Color::Magenta;
+            let unlintable_color = Color::Red;
             let filename = file
                 .file_name()
                 .map(|s| s.to_string_lossy().into())
@@ -102,11 +111,19 @@ fn main() -> anyhow::Result<()> {
             let mut report_builder =
                 Report::build(ReportKind::Custom("Spans", primary_color), &filename, 0);
             let mut color = primary_color;
-            for token in doc.tokens() {
+
+            for token in doc.tokens().filter(|t| {
+                include_newlines
+                    || !matches!(t.kind, TokenKind::Newline(_) | TokenKind::ParagraphBreak)
+            }) {
                 report_builder = report_builder.with_label(
                     Label::new((&filename, token.span.into()))
                         .with_message(format!("[{}, {})", token.span.start, token.span.end))
-                        .with_color(color),
+                        .with_color(if matches!(token.kind, TokenKind::Unlintable) {
+                            unlintable_color
+                        } else {
+                            color
+                        }),
                 );
 
                 // Alternate colors so spans are clear
@@ -134,6 +151,15 @@ fn main() -> anyhow::Result<()> {
                 println!("{}", word_str);
             }
 
+            Ok(())
+        }
+        Args::Metadata { word } => {
+            let dict = FstDictionary::curated();
+            let metadata = dict.get_word_metadata_str(&word);
+            let json = serde_json::to_string_pretty(&metadata).unwrap();
+
+            println!("{json}");
+
             Ok(())
         }
     }

harper-comments/src/lib.rs

@@ -1,6 +1,5 @@
 #![doc = include_str!("../README.md")]
 
-mod better;
 mod comment_parser;
 mod comment_parsers;
 pub use comment_parser::CommentParser;

harper-comments/tests/language_support_sources/javadoc_complex.java

@@ -19,7 +19,7 @@ public static void main(String[] args) {
   /**
    * This doc has a link in it: {@link this sould b ignor} but not tis
    *
-   * @param name this is an other test.
+   * @param name this is anoher test.
    */
   public static void greet(String name) {
     System.out.println("Hello " + name + ".");

harper-core/affixes.json

@@ -483,7 +483,9 @@
       "replacements": [],
       "adds_metadata": {},
       "gifts_metadata": {
-        "noun": {}
+        "noun": {
+          "is_plural": false
+        }
       }
     },
     "2": {
@@ -557,6 +559,17 @@
         }
       }
     },
+    "9": {
+      "suffix": true,
+      "cross_product": true,
+      "replacements": [],
+      "adds_metadata": {},
+      "gifts_metadata": {
+        "noun": {
+          "is_plural": true
+        }
+      }
+    },
     "~": {
       "suffix": true,
       "cross_product": true,

harper-core/dictionary.dict

@@ -28344,7 +28344,7 @@ inimitably/
 iniquitous/5Y
 iniquity/1SM
 initial/514SGMDY
-initialism/1
+initialism/1MS
 initialization/1
 initialize/4DSG
 initialized/4AU
@@ -44053,7 +44053,7 @@ subbed/4
 subbing/41
 subbranch/1MS
 subcategory/1SM
-subclass/14
+subclass/14G
 subcommittee/1SM
 subcompact/15SM
 subconscious/51PMY
@@ -45485,7 +45485,7 @@ therapeutically/
 therapeutics/1M
 therapist/1SM
 therapy/14SM
-there/18~
+there/~
 there's/
 thereabout/S
 thereafter/1
@@ -45519,7 +45519,7 @@ thermostatic/5
 thermostatically/
 thesauri/1
 thesaurus/1MS
-these/8S~
+these/8S~9
 thesis/1M
 thespian/51SM
 theta/1SM
@@ -45544,9 +45544,8 @@ thieve/4DSG
 thievery/1M
 thieving/451M
 thievish/5
-thigh/1M
+thigh/1MS
 thighbone/1MS
-thighs/1
 thimble/14MS
 thimbleful/1SM
 thin/514YSP
@@ -45628,7 +45627,7 @@ threesome/1SM
 threnody/1SM
 thresh/4MDRSZG
 thresher/1M
-threshold/1SM
+threshold/1SMG
 threw/4
 thrice/
 thrift/14SM
@@ -49637,7 +49636,6 @@ scatterplot/14SMG
 Wikilink/MS1
 stacktrace/SM1
 scrollbar/1SM
-break-up/1SM
 sweetgrass/1SM
 PowerShell/SM
 WebSocket/SM
@@ -49762,3 +49760,11 @@ glymph/SM
 Snapchat/SM
 middleware/SM
 OpenSearch/SM
+OpenGL/SM
+WebGPU/SM
+backfill/SM
+downsample/SMG
+uncheck/SM
+upsample/SMG
+organoid/SM
+centric/SM

harper-core/src/document.rs

@@ -7,10 +7,9 @@ use paste::paste;
 use crate::parsers::{Markdown, Parser, PlainEnglish};
 use crate::patterns::{PatternExt, RepeatingPattern, SequencePattern};
 use crate::punctuation::Punctuation;
-use crate::token::NumberSuffix;
 use crate::vec_ext::VecExt;
-use crate::Span;
 use crate::{Dictionary, FatToken, FstDictionary, Lrc, Token, TokenKind, TokenStringExt};
+use crate::{NumberSuffix, Span};
 
 /// A document containing some amount of lexed and parsed English text.
 #[derive(Debug, Clone)]

harper-core/src/fat_token.rs

@@ -0,0 +1,11 @@
+use serde::{Deserialize, Serialize};
+
+use crate::TokenKind;
+
+/// A [`Token`] that holds its content as a fat [`Vec<char>`] rather than as a
+/// [`Span`].
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, PartialOrd)]
+pub struct FatToken {
+    pub content: Vec<char>,
+    pub kind: TokenKind,
+}

harper-core/src/language_detection.rs

@@ -106,7 +106,7 @@ mod tests {
     #[test]
     fn detects_python_fib() {
         assert_not_english(
-            r#"
+            r"
 def fibIter(n):
     if n < 2:
         return n
@@ -115,7 +115,7 @@ def fibIter(n):
     for _ in range(2, n):
         fibPrev, fib = fib, fib + fibPrev
     return fib
-        "#,
+        ",
         );
     }
 

harper-core/src/lexing/email_address.rs

@@ -109,23 +109,23 @@ mod tests {
 
     fn example_local_parts() -> impl Iterator<Item = Vec<char>> {
         [
-            r#"simple"#,
-            r#"very.common"#,
-            r#"x"#,
-            r#"long.email-address-with-hyphens"#,
-            r#"user.name+tag+sorting"#,
-            r#"name/surname"#,
-            r#"admin"#,
-            r#"example"#,
+            r"simple",
+            r"very.common",
+            r"x",
+            r"long.email-address-with-hyphens",
+            r"user.name+tag+sorting",
+            r"name/surname",
+            r"admin",
+            r"example",
             r#"" ""#,
             r#""john..doe""#,
-            r#"mailhost!username"#,
+            r"mailhost!username",
             r#""very.(),:;<>[]\".VERY.\"very@\\ \"very\".unusual""#,
-            r#"user%example.com"#,
-            r#"user-"#,
-            r#"postmaster"#,
-            r#"postmaster"#,
-            r#"_test"#,
+            r"user%example.com",
+            r"user-",
+            r"postmaster",
+            r"postmaster",
+            r"_test",
         ]
         .into_iter()
         .map(|s| s.chars().collect())