From 8376f15b9a377b557af6796e9870bbb8663f61a1 Mon Sep 17 00:00:00 2001
From: overlookmotel <theoverlookmotel@gmail.com>
Date: Fri, 9 Feb 2024 04:02:51 +0000
Subject: [PATCH] perf(parser): eat whitespace after line break (#2353)

Uses the `byte_search!` macro introduced in #2352 to consume whitespace after a line break.
---
 crates/oxc_parser/src/lexer/byte_handlers.rs |  3 +--
 crates/oxc_parser/src/lexer/mod.rs           |  1 +
 crates/oxc_parser/src/lexer/whitespace.rs    | 28 ++++++++++++++++++++
 3 files changed, 30 insertions(+), 2 deletions(-)
 create mode 100644 crates/oxc_parser/src/lexer/whitespace.rs

diff --git a/crates/oxc_parser/src/lexer/byte_handlers.rs b/crates/oxc_parser/src/lexer/byte_handlers.rs
index ef720d115..67beef8ee 100644
--- a/crates/oxc_parser/src/lexer/byte_handlers.rs
+++ b/crates/oxc_parser/src/lexer/byte_handlers.rs
@@ -203,8 +203,7 @@ ascii_byte_handler!(ISP(lexer) {
 // '\r' '\n'
 ascii_byte_handler!(LIN(lexer) {
     lexer.consume_char();
-    lexer.token.is_on_new_line = true;
-    Kind::Skip
+    lexer.line_break_handler()
 });
 
 // !
diff --git a/crates/oxc_parser/src/lexer/mod.rs b/crates/oxc_parser/src/lexer/mod.rs
index ac18ad91d..41ed2c6eb 100644
--- a/crates/oxc_parser/src/lexer/mod.rs
+++ b/crates/oxc_parser/src/lexer/mod.rs
@@ -25,6 +25,7 @@ mod token;
 mod trivia_builder;
 mod typescript;
 mod unicode;
+mod whitespace;
 
 use rustc_hash::FxHashMap;
 use std::collections::VecDeque;
diff --git a/crates/oxc_parser/src/lexer/whitespace.rs b/crates/oxc_parser/src/lexer/whitespace.rs
new file mode 100644
index 000000000..1f6300341
--- /dev/null
+++ b/crates/oxc_parser/src/lexer/whitespace.rs
@@ -0,0 +1,28 @@
+use super::{
+    search::{byte_search, safe_byte_match_table, SafeByteMatchTable},
+    Kind, Lexer,
+};
+
+static NOT_REGULAR_WHITESPACE_OR_LINE_BREAK_TABLE: SafeByteMatchTable =
+    safe_byte_match_table!(|b| !matches!(b, b' ' | b'\t' | b'\r' | b'\n'));
+
+impl<'a> Lexer<'a> {
+    pub(super) fn line_break_handler(&mut self) -> Kind {
+        self.token.is_on_new_line = true;
+
+        // Indentation is common after a line break.
+        // Consume it, along with any further line breaks.
+        // Irregular line breaks and whitespace are not consumed.
+        // They're uncommon, so leave them for the next call to `handle_byte` to take care of.
+        byte_search! {
+            lexer: self,
+            table: NOT_REGULAR_WHITESPACE_OR_LINE_BREAK_TABLE,
+            handle_match: |_next_byte, _start| {
+                Kind::Skip
+            },
+            handle_eof: |_start| {
+                Kind::Skip
+            },
+        };
+    }
+}