Merge remote-tracking branch 'upstream/master' into typst-support

demo.md

@@ -5,6 +5,8 @@ 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 shoul dn't.
+Harper can be a lifesaver when writing technical documents, 
+emails or other formal forms of communication.
 
 Harper works everywhere, even offline. Since you r data
 never leaves your device, you don't ned to worry aout us

harper-comments/Cargo.toml

@@ -19,6 +19,7 @@ tree-sitter-javascript = "0.20.1"
 tree-sitter-go = "0.20.0"
 tree-sitter-c = "0.20.7"
 tree-sitter-cpp = "0.20.5"
+tree-sitter-cmake = "=0.4.1"
 tree-sitter-ruby = "0.20.1"
 tree-sitter-swift = "=0.4.0"
 tree-sitter-c-sharp = "0.20.0"
@@ -27,7 +28,7 @@ tree-sitter-lua = "0.0.19"
 tree-sitter-bash = "0.20.0"
 tree-sitter-java = "0.20.0"
 tree-sitter-nix = "0.0.1"
-itertools = "0.13.0"
+itertools = "0.14.0"
 tree-sitter-haskell = "0.15.0"
 
 [dev-dependencies]

harper-comments/src/comment_parser.rs

@@ -29,6 +29,7 @@ impl CommentParser {
             "go" => tree_sitter_go::language(),
             "c" => tree_sitter_c::language(),
             "cpp" => tree_sitter_cpp::language(),
+            "cmake" => tree_sitter_cmake::language(),
             "ruby" => tree_sitter_ruby::language(),
             "swift" => tree_sitter_swift::language(),
             "csharp" => tree_sitter_c_sharp::language(),
@@ -77,6 +78,7 @@ impl CommentParser {
             "go" => "go",
             "c" => "c",
             "cpp" => "cpp",
+            "cmake" => "cmake",
             "h" => "cpp",
             "rb" => "ruby",
             "swift" => "swift",

harper-core/Cargo.toml

@@ -12,7 +12,7 @@ blanket = "0.4.0"
 fst = "0.4.7"
 hashbrown = { version = "0.15.2", features = ["serde"] }
 is-macro = "0.3.6"
-itertools = "0.13.0"
+itertools = "0.14.0"
 lazy_static = "1.5.0"
 ordered-float = { version = "4.6.0", features = ["serde"] }
 paste = "1.0.14"

harper-core/dictionary.dict

@@ -1,5 +1,4 @@
 50000
-A/125SM
 AA/1254M
 AAA/12
 AB/215M
@@ -10758,7 +10757,7 @@ Zworykin/M
 Zyrtec/M
 Zyuganov/M
 Zzz
-a/1-+4857S~
+a/-+457S~
 aah/14
 aardvark/1SM
 ab/14+SDY
@@ -11894,7 +11893,7 @@ amusing/45Y
 amygdala/1
 amylase/1M
 amyloid/15
-an/-71+CS~
+an/-7+CS~
 anabolism/1M
 anachronism/1SM
 anachronistic/5
@@ -11955,7 +11954,7 @@ anchovy/1SM
 ancient/51SPMRYT
 ancientness/1M
 ancillary/51SM
-and/714~
+and/74~
 andante/15SM
 andiron/1SM
 androgen/1M
@@ -13329,7 +13328,7 @@ bamboozle/41DSG
 ban/41SM
 banal/5Y
 banality/1SM
-banana/15SM
+banana/1SM
 band's
 band/14ESGD
 bandage/14DSMG
@@ -15269,7 +15268,7 @@ bureaucratization/1M
 bureaucratize/4GDS
 burg/1MRZS
 burgeon/14DSG
-burger/1M
+burger/1MS
 burgh/1MRZ
 burgher/1M
 burghs/1
@@ -31305,7 +31304,7 @@ marital/5Y
 maritime/5
 marjoram/1M
 mark/14AMDSG
-markdown/12SM
+Markdown/12SM
 marked/54U
 markedly/
 marker/14MS
@@ -49003,7 +49002,7 @@ wit/14+SM
 witch/14MDSG
 witchcraft/1M
 witchery/1M
-with/+1~
+with/+~
 withal/+
 withdraw/41SG
 withdrawal/1MS
@@ -49768,3 +49767,4 @@ uncheck/SM
 upsample/SMG
 organoid/SM
 centric/SM
+Harper/SM

harper-core/src/document.rs

@@ -496,6 +496,7 @@ macro_rules! create_fns_on_doc {
 
 impl TokenStringExt for Document {
     create_fns_on_doc!(word);
+    create_fns_on_doc!(conjunction);
     create_fns_on_doc!(space);
     create_fns_on_doc!(apostrophe);
     create_fns_on_doc!(pipe);

harper-core/src/fat_token.rs

@@ -2,8 +2,8 @@ use serde::{Deserialize, Serialize};
 
 use crate::TokenKind;
 
-/// A [`Token`] that holds its content as a fat [`Vec<char>`] rather than as a
-/// [`Span`].
+/// A [`Token`](crate::Token) that holds its content as a fat [`Vec<char>`] rather than as a
+/// [`Span`](crate::Span).
 #[derive(Debug, Clone, Serialize, Deserialize, PartialEq, PartialOrd)]
 pub struct FatToken {
     pub content: Vec<char>,

harper-core/src/linting/an_a.rs

@@ -103,6 +103,7 @@ fn starts_with_vowel(word: &[char]) -> bool {
         [] | ['u', 'k', ..]
             | ['e', 'u', 'p', 'h', ..]
             | ['e', 'u', 'g' | 'l' | 'c', ..]
+            | ['o', 'n', 'e']
             | ['o', 'n', 'c', 'e']
     ) {
         return false;