From b3fea30f84fef3ff7aa77775e00b83ba62d997cc Mon Sep 17 00:00:00 2001 From: Thomas Lively Date: Fri, 22 Mar 2024 16:56:33 -0700 Subject: [Strings] Represent string values as WTF-16 internally (#6418) WTF-16, i.e. arbitrary sequences of 16-bit values, is the encoding of Java and JavaScript strings, and using the same encoding makes the interpretation of string operations trivial, even when accounting for non-ascii characters. Specifically, use little-endian WTF-16. Re-encode string constants from WTF-8 to WTF-16 in the parsers, then back to WTF-8 in the writers. Update the constructor for string `Literal`s to interpret the string as WTF-16 and store a sequence of WTF-16 code units, i.e. 16-bit integers. Update `Builder::makeConstantExpression` accordingly to convert from the new `Literal` string representation back to a WTF-16 string. Update the interpreter to remove the logic for detecting non-ascii characters and bailing out. The naive implementations of all the string operations are correct now that our string encoding matches the JS string encoding. --- src/passes/Print.cpp | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'src/passes/Print.cpp') diff --git a/src/passes/Print.cpp b/src/passes/Print.cpp index 643f1cc3f..80047a281 100644 --- a/src/passes/Print.cpp +++ b/src/passes/Print.cpp @@ -2232,7 +2232,13 @@ struct PrintExpressionContents } void visitStringConst(StringConst* curr) { printMedium(o, "string.const "); - String::printEscaped(o, curr->string.str); + // Re-encode from WTF-16 to WTF-8. + std::stringstream wtf8; + [[maybe_unused]] bool valid = + String::convertWTF16ToWTF8(wtf8, curr->string.str); + assert(valid); + // TODO: Use wtf8.view() once we have C++20. + String::printEscaped(o, wtf8.str()); } void visitStringMeasure(StringMeasure* curr) { switch (curr->op) { -- cgit v1.2.3