From f067ca647ce6d2d6a7ddc641f64b59625045682c Mon Sep 17 00:00:00 2001
From: FalsePattern <me@falsepattern.com>
Date: Mon, 11 Nov 2024 09:56:50 +0100
Subject: [PATCH] fix: character literal escape sequences and unicode

---
 CHANGELOG.md                                  | 10 ++++
 core/src/main/grammar/Zig.flex                | 47 ++-----------------
 core/src/main/grammar/ZigString.flex          | 23 ++++++++-
 .../zig/lexer/ZigHighlightingLexer.kt         |  4 +-
 4 files changed, 37 insertions(+), 47 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index cb9d87d9..0c1289fb 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -17,6 +17,16 @@ Changelog structure reference:
 
 ## [Unreleased]
 
+### Added
+
+- Zig
+  - Escape sequence highlighting in char literals
+
+### Fixed
+
+- Zig
+  - Unicode characters in char literals triggered an error
+
 ## [20.0.1]
 
 ### Fixed
diff --git a/core/src/main/grammar/Zig.flex b/core/src/main/grammar/Zig.flex
index 5ebc0e23..3a011010 100644
--- a/core/src/main/grammar/Zig.flex
+++ b/core/src/main/grammar/Zig.flex
@@ -52,49 +52,8 @@ oct_int={oct} {oct_}*
 dec_int={dec} {dec_}*
 hex_int={hex} {hex_}*
 
-ox80_oxBF=[\200-\277]
-oxF4=\364
-ox80_ox8F=[\200-\217]
-oxF1_oxF3=[\361-\363]
-oxF0=\360
-ox90_0xBF=[\220-\277]
-oxEE_oxEF=[\356-\357]
-oxED=\355
-ox80_ox9F=[\200-\237]
-oxE1_oxEC=[\341-\354]
-oxE0=\340
-oxA0_oxBF=[\240-\277]
-oxC2_oxDF=[\302-\337]
-
-// From https://lemire.me/blog/2018/05/09/how-quickly-can-you-check-that-a-string-is-valid-unicode-utf-8/
-// First Byte      Second Byte     Third Byte      Fourth Byte
-// [0x00,0x7F]
-// [0xC2,0xDF]     [0x80,0xBF]
-//    0xE0         [0xA0,0xBF]     [0x80,0xBF]
-// [0xE1,0xEC]     [0x80,0xBF]     [0x80,0xBF]
-//    0xED         [0x80,0x9F]     [0x80,0xBF]
-// [0xEE,0xEF]     [0x80,0xBF]     [0x80,0xBF]
-//    0xF0         [0x90,0xBF]     [0x80,0xBF]     [0x80,0xBF]
-// [0xF1,0xF3]     [0x80,0xBF]     [0x80,0xBF]     [0x80,0xBF]
-//    0xF4         [0x80,0x8F]     [0x80,0xBF]     [0x80,0xBF]
-
-mb_utf8_literal= {oxF4}      {ox80_ox8F} {ox80_oxBF} {ox80_oxBF}
-               | {oxF1_oxF3} {ox80_oxBF} {ox80_oxBF} {ox80_oxBF}
-               | {oxF0}      {ox90_0xBF} {ox80_oxBF} {ox80_oxBF}
-               | {oxEE_oxEF} {ox80_oxBF} {ox80_oxBF}
-               | {oxED}      {ox80_ox9F} {ox80_oxBF}
-               | {oxE1_oxEC} {ox80_oxBF} {ox80_oxBF}
-               | {oxE0}      {oxA0_oxBF} {ox80_oxBF}
-               | {oxC2_oxDF} {ox80_oxBF}
-
-ascii_char_not_nl_slash_squote=[\000-\011\013-\046\050-\133\135-\177]
-
-char_escape= "\\x" {hex} {hex}
-           | "\\u{" {hex}+ "}"
-           | "\\" [nr\\t'\"]
-char_char= {mb_utf8_literal}
-         | {char_escape}
-         | {ascii_char_not_nl_slash_squote}
+char_char= \\ .
+         | [^\'\n]
 
 string_char= \\ .
            | [^\"\n]
@@ -261,7 +220,7 @@ BUILTINIDENTIFIER="@"[A-Za-z_][A-Za-z0-9_]*
 <YYINITIAL>      "while"                  { return KEYWORD_WHILE; }
 
 <YYINITIAL>      "'"                      { yybegin(CHAR_LIT); }
-<CHAR_LIT>       {char_char}"'"           { yybegin(YYINITIAL); return CHAR_LITERAL; }
+<CHAR_LIT>       {char_char}*"'"          { yybegin(YYINITIAL); return CHAR_LITERAL; }
 <CHAR_LIT>       [^]                      { yypushback(1); yybegin(UNT_QUOT); }
 
 <YYINITIAL>      {FLOAT}                  { return FLOAT; }
diff --git a/core/src/main/grammar/ZigString.flex b/core/src/main/grammar/ZigString.flex
index 5b5b6a86..24fb085d 100644
--- a/core/src/main/grammar/ZigString.flex
+++ b/core/src/main/grammar/ZigString.flex
@@ -40,17 +40,21 @@ import static com.intellij.psi.StringEscapesTokenTypes.*;
 hex=[0-9a-fA-F]
 
 char_escape_unicode= "\\x" {hex} {hex} | "\\u{" {hex}+ "}"
-char_escape_unicode_invalid= "\\x" | "\\u"
+char_escape_unicode_invalid= "\\x" .? .? | "\\u" ("{" [^}]* "}"?)?
 
 char_escape_single_valid= "\\" [nr\\t'\"]
 char_escape_single_invalid= "\\" [^nr\\t'\"]
 
 %state STR
+%state CHAR
+%state CHAR_END
+%state CHAR_FINISH
 %%
 
 
 <YYINITIAL> {
       "\"" { yybegin(STR); return STRING_LITERAL_SINGLE; }
+      "'"  { yybegin(CHAR); return CHAR_LITERAL; }
       [^]  { return STRING_LITERAL_SINGLE; }
 }
 
@@ -61,3 +65,20 @@ char_escape_single_invalid= "\\" [^nr\\t'\"]
       {char_escape_single_invalid} { return INVALID_CHARACTER_ESCAPE_TOKEN; }
       [^] { return STRING_LITERAL_SINGLE; }
 }
+
+<CHAR> {
+      {char_escape_unicode} { yybegin(CHAR_END); return VALID_STRING_ESCAPE_TOKEN; }
+      {char_escape_unicode_invalid} { yybegin(CHAR_END); return INVALID_UNICODE_ESCAPE_TOKEN; }
+      {char_escape_single_valid} { yybegin(CHAR_END); return VALID_STRING_ESCAPE_TOKEN; }
+      {char_escape_single_invalid} { yybegin(CHAR_END); return INVALID_CHARACTER_ESCAPE_TOKEN; }
+      [^] { yybegin(CHAR_END); return CHAR_LITERAL; }
+}
+
+<CHAR_END> {
+      "'" { yybegin(CHAR_FINISH); return CHAR_LITERAL; }
+      [^] { return BAD_CHARACTER; }
+}
+
+<CHAR_FINISH> {
+      [^] { return BAD_CHARACTER; }
+}
\ No newline at end of file
diff --git a/core/src/main/kotlin/com/falsepattern/zigbrains/zig/lexer/ZigHighlightingLexer.kt b/core/src/main/kotlin/com/falsepattern/zigbrains/zig/lexer/ZigHighlightingLexer.kt
index 798f39d2..0a9006fc 100644
--- a/core/src/main/kotlin/com/falsepattern/zigbrains/zig/lexer/ZigHighlightingLexer.kt
+++ b/core/src/main/kotlin/com/falsepattern/zigbrains/zig/lexer/ZigHighlightingLexer.kt
@@ -34,9 +34,9 @@ class ZigHighlightingLexer: LayeredLexer(ZigLexerAdapter()) {
         registerSelfStoppingLayer(
             MergingLexerAdapter(
                 ZigLexerStringAdapter(),
-                TokenSet.create(ZigTypes.STRING_LITERAL_SINGLE)
+                TokenSet.create(ZigTypes.STRING_LITERAL_SINGLE, ZigTypes.CHAR_LITERAL)
             ),
-            arrayOf(ZigTypes.STRING_LITERAL_SINGLE),
+            arrayOf(ZigTypes.STRING_LITERAL_SINGLE, ZigTypes.CHAR_LITERAL),
             IElementType.EMPTY_ARRAY
         )
     }