Add JSON pre-processor (#17125)

This PR adds a small JSON pre processor to improve parsing JSON files.

Due to the sheer amount of potential `[` and `]` brackets, it could be
that parsing JSON files are way slower than they need to be.

We saw this while debugging this issue:
#17092


# Test plan

1. Added test to verify the pre processing works
2. Existing tests still pass

Author: RobinMalfait

CHANGELOG.md

@@ -23,6 +23,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Ensure classes between `>` and `<` are properly extracted ([#17094](https://github.com/tailwindlabs/tailwindcss/pull/17094))
 - Treat starting single quote as verbatim text in Slim ([#17085](https://github.com/tailwindlabs/tailwindcss/pull/17085))
 - Ensure `.node` and `.wasm` files are not scanned for utilities ([#17123](https://github.com/tailwindlabs/tailwindcss/pull/17123))
+- Improve performance when scanning `JSON` files ([#17125](https://github.com/tailwindlabs/tailwindcss/pull/17125))
 
 ## [4.0.12] - 2025-03-07
 

crates/oxide/src/extractor/pre_processors/json.rs

@@ -0,0 +1,63 @@
+use crate::cursor;
+use crate::extractor::pre_processors::pre_processor::PreProcessor;
+
+#[derive(Debug, Default)]
+pub struct Json;
+
+impl PreProcessor for Json {
+    fn process(&self, content: &[u8]) -> Vec<u8> {
+        let len = content.len();
+        let mut result = content.to_vec();
+        let mut cursor = cursor::Cursor::new(content);
+
+        while cursor.pos < len {
+            match cursor.curr {
+                // Consume strings as-is
+                b'"' => {
+                    cursor.advance();
+
+                    while cursor.pos < len {
+                        match cursor.curr {
+                            // Escaped character, skip ahead to the next character
+                            b'\\' => cursor.advance_twice(),
+
+                            // End of the string
+                            b'"' => break,
+
+                            // Everything else is valid
+                            _ => cursor.advance(),
+                        };
+                    }
+                }
+
+                // Replace brackets and curlies with spaces
+                b'[' | b'{' | b']' | b'}' => {
+                    result[cursor.pos] = b' ';
+                }
+
+                // Consume everything else
+                _ => {}
+            };
+
+            cursor.advance();
+        }
+
+        result
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::Json;
+    use crate::extractor::pre_processors::pre_processor::PreProcessor;
+
+    #[test]
+    fn test_json_pre_processor() {
+        let (input, expected) = (
+            r#"[1,[2,[3,4,["flex flex-1 content-['hello_world']"]]], {"flex": true}]"#,
+            r#" 1, 2, 3,4, "flex flex-1 content-['hello_world']"   ,  "flex": true  "#,
+        );
+
+        Json::test(input, expected);
+    }
+}

crates/oxide/src/extractor/pre_processors/mod.rs

@@ -1,4 +1,5 @@
 pub mod haml;
+pub mod json;
 pub mod pre_processor;
 pub mod pug;
 pub mod razor;
@@ -7,6 +8,7 @@ pub mod slim;
 pub mod svelte;
 
 pub use haml::*;
+pub use json::*;
 pub use pre_processor::*;
 pub use pug::*;
 pub use razor::*;

crates/oxide/src/lib.rs

@@ -470,6 +470,7 @@ pub fn pre_process_input(content: &[u8], extension: &str) -> Vec<u8> {
     match extension {
         "cshtml" | "razor" => Razor.process(content),
         "haml" => Haml.process(content),
+        "json" => Json.process(content),
         "pug" => Pug.process(content),
         "rb" | "erb" => Ruby.process(content),
         "slim" => Slim.process(content),