[2.10.4] Parsing fails

[resah]

After updating to version 2.10.4 the enclosed Java file cannot be parsed.

Java File

package id.bare.celprovider.function;

import static org.hamcrest.CoreMatchers.is;
import static org.hamcrest.MatcherAssert.assertThat;
import static org.junit.jupiter.api.Assertions.assertThrows;

import dev.cel.runtime.CelFunctionBinding;
import dev.cel.runtime.CelFunctionOverload;
import id.bare.celprovider.CelRuntimeException;
import java.util.List;
import org.junit.jupiter.api.Test;

class UrlFunctionsTest {

	private final UrlFunctions urlFunctions = new UrlFunctions();

	@Test
	void testUrlEncodeFunctionality() throws Exception {
		var urlEncodeFunc = getFuncBinding("url_encode_string");

		// spaces become %20, reserved characters are percent-encoded
		assertThat(urlEncodeFunc.apply(new Object[] { "a b@c.de" }), is("a%20b%40c.de"));
		// a literal + must not survive as a space
		assertThat(urlEncodeFunc.apply(new Object[] { "1+1=2" }), is("1%2B1%3D2"));
		// already encoded input is encoded again instead of being passed through
		assertThat(urlEncodeFunc.apply(new Object[] { "a%2Fb" }), is("a%252Fb"));
		// non-ASCII is UTF-8 encoded, including characters outside the BMP
		assertThat(urlEncodeFunc.apply(new Object[] { "Müller" }), is("M%C3%BCller"));
		assertThat(urlEncodeFunc.apply(new Object[] { "😀" }), is("%F0%9F%98%80"));
		assertThat(urlEncodeFunc.apply(new Object[] { "" }), is(""));
	}

	@Test
	void testUrlEncodeQueryFunctionality() throws Exception {
		var urlEncodeQueryFunc = getFuncBinding("url_encodeQuery_string");

		// form encoding: spaces become +
		assertThat(urlEncodeQueryFunc.apply(new Object[] { "a b@c.de" }), is("a+b%40c.de"));
		assertThat(urlEncodeQueryFunc.apply(new Object[] { "1+1=2" }), is("1%2B1%3D2"));
		assertThat(urlEncodeQueryFunc.apply(new Object[] { "a%2Fb" }), is("a%252Fb"));
		assertThat(urlEncodeQueryFunc.apply(new Object[] { "Müller" }), is("M%C3%BCller"));
		assertThat(urlEncodeQueryFunc.apply(new Object[] { "😀" }), is("%F0%9F%98%80"));
		assertThat(urlEncodeQueryFunc.apply(new Object[] { "" }), is(""));
	}

	@Test
	void testUrlDecodeFunctionality() throws Exception {
		var urlDecodeFunc = getFuncBinding("url_decode_string");

		assertThat(urlDecodeFunc.apply(new Object[] { "a%20b%40c.de" }), is("a b@c.de"));
		// + is not a space here
		assertThat(urlDecodeFunc.apply(new Object[] { "a+b" }), is("a+b"));
		assertThat(urlDecodeFunc.apply(new Object[] { "M%C3%BCller" }), is("Müller"));
		assertThat(urlDecodeFunc.apply(new Object[] { "%F0%9F%98%80" }), is("😀"));
		// malformed escapes are passed through instead of failing
		assertThat(urlDecodeFunc.apply(new Object[] { "100%ZZ" }), is("100%ZZ"));
	}

	@Test
	void testUrlDecodeQueryFunctionality() throws Exception {
		var urlDecodeQueryFunc = getFuncBinding("url_decodeQuery_string");

		assertThat(urlDecodeQueryFunc.apply(new Object[] { "a+b%40c.de" }), is("a b@c.de"));
		assertThat(urlDecodeQueryFunc.apply(new Object[] { "M%C3%BCller" }), is("Müller"));
		assertThat(urlDecodeQueryFunc.apply(new Object[] { "%F0%9F%98%80" }), is("😀"));

		// error
		assertThrows(CelRuntimeException.class, () -> {
			urlDecodeQueryFunc.apply(new Object[] { "100%ZZ" });
		});
	}

	@Test
	void testUrlEncodeDecodeRoundTrip() throws Exception {
		var urlEncodeFunc = getFuncBinding("url_encode_string");
		var urlDecodeFunc = getFuncBinding("url_decode_string");
		var urlEncodeQueryFunc = getFuncBinding("url_encodeQuery_string");
		var urlDecodeQueryFunc = getFuncBinding("url_decodeQuery_string");

		for (String input : List.of("a b@c.de", "1+1=2", "a%2Fb", "Müller & Söhne", "5€", "😀", "?&=#/")) {
			assertThat(urlDecodeFunc.apply(new Object[] { urlEncodeFunc.apply(new Object[] { input }) }), is(input));
			assertThat(
				urlDecodeQueryFunc.apply(new Object[] { urlEncodeQueryFunc.apply(new Object[] { input }) }),
				is(input)
			);
		}
	}

	private CelFunctionOverload getFuncBinding(String overloadId) {
		CelFunctionBinding funcBinding = urlFunctions
			.stream()
			.map(CelFunctionDefinition::binding)
			.filter(b -> overloadId.equals(b.getOverloadId()))
			.findFirst()
			.orElseThrow();
		return funcBinding.getDefinition();
	}
}

Log

2026-09-24T09:22:00.646458Z 01O Checking formatting...
2026-09-24T09:22:04.114116Z 01E [�[31merror�[39m] celprovider/src/test/java/id/bare/celprovider/function/UrlFunctionsTest.java: Error: Failed to parse: (program (package_declaration (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (identifier) name: (identifier)) name: (identifier)) name: (identifier))) (import_declaration (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (identifier) name: (identifier)) name: (identifier)) name: (identifier))) (import_declaration (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (identifier) name: (identifier)) name: (identifier)) name: (identifier))) (import_declaration (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (identifier) name: (identifier)) name: (identifier)) name: (identifier)) name: (identifier)) name: (identifier))) (import_declaration (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (identifier) name: (identifier)) name: (identifier)) name: (identifier))) (import_declaration (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (identifier) name: (identifier)) name: (identifier)) name: (identifier))) (import_declaration (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (identifier) name: (identifier)) name: (identifier)) name: (identifier))) (import_declaration (scoped_identifier scope: (scoped_identifier scope: (identifier) name: (identifier)) name: (identifier))) (import_declaration (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (scoped_identifier scope: (identifier) name: (identifier)) name: (identifier)) name: (identifier)) name: (identifier))) (class_declaration name: (identifier) body: (class_body (field_declaration (modifiers (visibility) (modifier)) type: (type_identifier) declarator: (variable_declarator name: (identifier) value: (object_creation_expression type: (type_identifier) arguments: (argument_list)))) (method_declaration (modifiers (marker_annotation name: (identifier))) type: (void_type) name: (identifier) parameters: (formal_parameters) (throws (type_identifier)) body: (block (local_variable_declaration type: (type_identifier) declarator: (variable_declarator name: (identifier) value: (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment)))))) (line_comment) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (line_comment) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (line_comment) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (line_comment) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (ERROR (UNEXPECTED 128512))))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal)))))))) (method_declaration (modifiers (marker_annotation name: (identifier))) type: (void_type) name: (identifier) parameters: (formal_parameters) (throws (type_identifier)) body: (block (local_variable_declaration type: (type_identifier) declarator: (variable_declarator name: (identifier) value: (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment)))))) (line_comment) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (ERROR (UNEXPECTED 128512))))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal)))))))) (method_declaration (modifiers (marker_annotation name: (identifier))) type: (void_type) name: (identifier) parameters: (formal_parameters) (throws (type_identifier)) body: (block (local_variable_declaration type: (type_identifier) declarator: (variable_declarator name: (identifier) value: (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment)))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (line_comment) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (ERROR (UNEXPECTED 128512)))))))) (line_comment) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))))) (method_declaration (modifiers (marker_annotation name: (identifier))) type: (void_type) name: (identifier) parameters: (formal_parameters) (throws (type_identifier)) body: (block (local_variable_declaration type: (type_identifier) declarator: (variable_declarator name: (identifier) value: (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment)))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment))))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))) (method_invocation name: (identifier) arguments: (argument_list (string_literal (ERROR (UNEXPECTED 128512)))))))) (line_comment) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (class_literal (type_identifier)) (lambda_expression parameters: (formal_parameters) body: (block (expression_statement (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (string_literal (string_fragment)))))))))))))) (method_declaration (modifiers (marker_annotation name: (identifier))) type: (void_type) name: (identifier) parameters: (formal_parameters) (throws (type_identifier)) body: (block (local_variable_declaration type: (type_identifier) declarator: (variable_declarator name: (identifier) value: (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment)))))) (local_variable_declaration type: (type_identifier) declarator: (variable_declarator name: (identifier) value: (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment)))))) (local_variable_declaration type: (type_identifier) declarator: (variable_declarator name: (identifier) value: (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment)))))) (local_variable_declaration type: (type_identifier) declarator: (variable_declarator name: (identifier) value: (method_invocation name: (identifier) arguments: (argument_list (string_literal (string_fragment)))))) (enhanced_for_statement type: (type_identifier) name: (identifier) value: (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (string_literal (string_fragment)) (string_literal (string_fragment)) (string_literal (string_fragment)) (string_literal (string_fragment)) (string_literal (string_fragment)) (string_literal (ERROR (UNEXPECTED 128512))) (string_literal (string_fragment)))) body: (block (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (identifier))))))))) (method_invocation name: (identifier) arguments: (argument_list (identifier)))))) (expression_statement (method_invocation name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (array_creation_expression type: (type_identifier) dimensions: (dimensions) value: (array_initializer (identifier))))))))) (method_invocation name: (identifier) arguments: (argument_list (identifier)))))))))) (method_declaration (modifiers (visibility)) type: (type_identifier) name: (identifier) parameters: (formal_parameters (formal_parameter type: (type_identifier) name: (identifier))) body: (block (local_variable_declaration type: (type_identifier) declarator: (variable_declarator name: (identifier) value: (method_invocation object: (method_invocation object: (method_invocation object: (method_invocation object: (method_invocation object: (identifier) name: (identifier) arguments: (argument_list)) name: (identifier) arguments: (argument_list (method_reference (identifier) (identifier)))) name: (identifier) arguments: (argument_list (lambda_expression parameters: (identifier) body: (method_invocation object: (identifier) name: (identifier) arguments: (argument_list (method_invocation object: (identifier) name: (identifier) arguments: (argument_list))))))) name: (identifier) arguments: (argument_list)) name: (identifier) arguments: (argument_list)))) (return_statement (method_invocation object: (identifier) name: (identifier) arguments: (argument_list))))))))
2026-09-24T09:22:04.114194Z 01E [�[31merror�[39m]     at Object.parse (file:///builds/.../node_modules/prettier-plugin-java/dist/index.mjs:2366:32)
2026-09-24T09:22:04.114196Z 01E [�[31merror�[39m]     at async parse8 (file:///builds/.../node_modules/prettier/index.mjs:17739:11)
2026-09-24T09:22:04.114201Z 01E [�[31merror�[39m]     at async coreFormat (file:///builds/.../node_modules/prettier/index.mjs:18282:7)
2026-09-24T09:22:04.114202Z 01E [�[31merror�[39m]     at async formatWithCursor (file:///builds/.../node_modules/prettier/index.mjs:18502:14)
2026-09-24T09:22:04.114202Z 01E [�[31merror�[39m]     at async formatFiles (file:///builds/.../node_modules/prettier/internal/legacy-cli.mjs:6661:18)
2026-09-24T09:22:04.114203Z 01E [�[31merror�[39m]     at async main (file:///builds/.../node_modules/prettier/internal/legacy-cli.mjs:7050:5)
2026-09-24T09:22:04.114204Z 01E [�[31merror�[39m]     at async Module.run (file:///builds/.../node_modules/prettier/internal/legacy-cli.mjs:6993:5)

[dsibilio]

I can confirm this is not isolated to the reproduction above. Same root cause, different codebase, different codepoint.

While migrating several unrelated Java projects to prettier-plugin-java@2.10.4, I hit the identical (ERROR (UNEXPECTED <codepoint>)) failure on any raw astral-plane (>U+FFFF, i.e. surrogate-pair) character inside a Java string literal. BMP characters (accented Latin, Greek, CJK, etc.) in the same strings parse fine, only the surrogate-pair characters trip the lexer.

Minimal public reproduction, from Activiti/Activiti:

Map<String, Object> value = Map.of("message", "hé🙂");

(that last character is U+1F642 🙂, decimal 128578)

[error] .../CountingWriterTest.java: Error: Failed to parse: ... (string_literal (string_fragment) (ERROR (UNEXPECTED 128578))) ...
    at Object.parse (.../prettier-plugin-java/dist/index.cjs:2366:32)

The workaround we're using in the meantime is replacing the literal character with its Java \uXXXX surrogate-pair escape (e.g. \ud83d\ude42), which compiles to the exact same String value and parses/formats fine.

Given #1063 already fixed the NUL-character case for 2.10.4, this looks like the same general "tree-sitter-java-orchard string-literal token doesn't accept the full Unicode range" class of bug, just for supplementary-plane characters instead of NUL.

[jtkiesel]

Thank you for reporting this issue! It was indeed caused by my fix to tree-sitter-java-orchard for the null character. I totally missed that the /v option on my regex would cause [\x00-\uFFFF] to be limited to a maximum of 0xFFFF, which differs from the behavior without /v. I've opened a fix here.