WIP

biomejs · Feb 25, 2025 · b9a1cb9 · b9a1cb9
1 parent 7b7ef04
commit b9a1cb9
Show file tree

Hide file tree

Showing 4 changed files with 64 additions and 1 deletion.
diff --git a/crates/biome_markdown_parser/src/lexer/mod.rs b/crates/biome_markdown_parser/src/lexer/mod.rs
@@ -181,10 +181,31 @@ impl<'src> MarkdownLexer<'src> {
         match dispatched {
             WHS => self.consume_newline_or_whitespace(),
             MUL | MIN | IDT => self.consume_thematic_break_literal(),
+            HSH => self.consume_header(),
             _ => self.consume_textual(),
         }
     }
 
+    fn consume_header(&mut self) -> MarkdownSyntaxKind {
+        self.assert_at_char_boundary();
+
+        let mut level = 0;
+        while matches!(self.current_byte(), Some(b'#')) {
+            self.advance(1);
+            level += 1;
+        }
+
+        match level {
+            1 => MD_HEADER1,
+            2 => MD_HEADER2,
+            3 => MD_HEADER3,
+            4 => MD_HEADER4,
+            5 => MD_HEADER5,
+            6 => MD_HEADER6,
+            _ => ERROR_TOKEN,
+        }
+    }
+
     fn text_position(&self) -> TextSize {
         TextSize::try_from(self.position).expect("Input to be smaller than 4 GB")
     }

diff --git a/crates/biome_markdown_parser/src/lexer/tests.rs b/crates/biome_markdown_parser/src/lexer/tests.rs
@@ -140,6 +140,36 @@ fn whitespace() {
     }
 }
 
+#[test]
+fn heading_level_1() {
+    assert_lex! {
+        "# Heading 1",
+        MD_HEADER1:1,
+        WHITESPACE:1,
+        MD_TEXTUAL_LITERAL:9,
+    }
+}
+
+#[test]
+fn heading_level_2() {
+    assert_lex! {
+        "## Heading 2",
+        MD_HEADER2:2,
+        WHITESPACE:1,
+        MD_TEXTUAL_LITERAL:9,
+    }
+}
+
+#[test]
+fn heading_level_3() {
+    assert_lex! {
+        "### Heading 3",
+        MD_HEADER3:3,
+        WHITESPACE:1,
+        MD_TEXTUAL_LITERAL:9,
+    }
+}
+
 #[test]
 fn thematic_break_literal() {
     assert_lex! {

diff --git a/xtask/codegen/markdown.ungram b/xtask/codegen/markdown.ungram
@@ -58,6 +58,13 @@ AnyContainerBlock = MdQuote | MdBulletListItem | MdOrderListItem
 // h1..h6
 MdHeader = before:MdHashList MdParagraph? after:MdHashList
 
+MdHeader1 = before:MdHashList MdParagraph? after:MdHashList
+MdHeader2 = before:MdHashList MdParagraph? after:MdHashList
+MdHeader3 = before:MdHashList MdParagraph? after:MdHashList
+MdHeader4 = before:MdHashList MdParagraph? after:MdHashList
+MdHeader5 = before:MdHashList MdParagraph? after:MdHashList
+MdHeader6 = before:MdHashList MdParagraph? after:MdHashList
+
 MdHashList = MdHash*
 
 MdHash = '#'

diff --git a/xtask/codegen/src/markdown_kinds_src.rs b/xtask/codegen/src/markdown_kinds_src.rs
@@ -40,7 +40,12 @@ pub const MARKDOWN_KINDS_SRC: KindsSrc = KindsSrc {
         "MD_BLOCK_LIST",
         "MD_HASH_LIST",
         "MD_HASH",
-        "MD_HEADER",
+        "MD_HEADER1",
+        "MD_HEADER2",
+        "MD_HEADER3",
+        "MD_HEADER4",
+        "MD_HEADER5",
+        "MD_HEADER6",
         "MD_INDENT_CODE_BLOCK",
         "MD_FENCED_CODE_BLOCK",
         "MD_HTML_BLOCK",