From c183dc9ce6b6e14581078ba42ff1824f922234ca Mon Sep 17 00:00:00 2001
From: Thomas Lively <tlively@google.com>
Date: Wed, 24 Apr 2024 11:07:28 -0700
Subject: [Parser] Use the new parser in wasm-shell and wasm-as (#6529)

Updating just one or the other of these tools would cause the tests
spec/import-after-*.fail.wast to fail, since only the updated tool would
correctly fail to parse its contents. To avoid this, update both tools at
once. (The tests erroneously pass before this change because check.py does not
ensure that .fail.wast tests fail, only that failing tests end in .fail.wast.)

In wasm-shell, to minimize the diff, only use the new parser to parse modules
and instructions. Continue using the legacy parsing based on s-expressions for
the other wast commands. Updating the parsing of the other commands to use
`Lexer` instead of `SExpressionParser` is left as future work. The boundary
between the two parsing styles is somewhat hacky, but it is worth it to enable
incremental development.

Update the tests to fix incorrect wast rejected by the new parser. Many of the
spec/old_* tests use non-standard forms from before Wasm MVP was standardized,
so fixing them would have been onerous. All of these tests have non-old_*
variants, so simply delete them.
---
 src/parser/wat-parser.cpp | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

(limited to 'src/parser/wat-parser.cpp')

diff --git a/src/parser/wat-parser.cpp b/src/parser/wat-parser.cpp
index 7f6dd2975..cc7d87540 100644
--- a/src/parser/wat-parser.cpp
+++ b/src/parser/wat-parser.cpp
@@ -99,17 +99,11 @@ void propagateDebugLocations(Module& wasm) {
   runner.run();
 }
 
-// ================
-// Parser Functions
-// ================
-
-} // anonymous namespace
-
-Result<> parseModule(Module& wasm, std::string_view input) {
+Result<> doParseModule(Module& wasm, Lexer& input, bool allowExtra) {
   // Parse module-level declarations.
   ParseDeclsCtx decls(input, wasm);
   CHECK_ERR(module(decls));
-  if (!decls.in.empty()) {
+  if (!allowExtra && !decls.in.empty()) {
     return decls.in.err("Unexpected tokens after module");
   }
 
@@ -222,8 +216,27 @@ Result<> parseModule(Module& wasm, std::string_view input) {
   }
 
   propagateDebugLocations(wasm);
+  input = decls.in;
 
   return Ok{};
 }
 
+} // anonymous namespace
+
+Result<> parseModule(Module& wasm, std::string_view in) {
+  Lexer lexer(in);
+  return doParseModule(wasm, lexer, false);
+}
+
+Result<> parseModule(Module& wasm, Lexer& lexer) {
+  return doParseModule(wasm, lexer, true);
+}
+
+Result<Expression*> parseExpression(Module& wasm, Lexer& lexer) {
+  ParseDefsCtx ctx(lexer, wasm, {}, {}, {}, {}, {});
+  auto e = expr(ctx);
+  CHECK_ERR(e);
+  return *e;
+}
+
 } // namespace wasm::WATParser
-- 
cgit v1.2.3