From 4a907b0a5ec1c25eef259ba54b387865edbe0451 Mon Sep 17 00:00:00 2001
From: Thomas Lively <tlively@google.com>
Date: Thu, 18 Apr 2024 17:08:20 -0700
Subject: [Parser][NFC] Solve performance issue by adding maybeLabelidx (#6514)

Creating an error in the parser is an extremely expensive operation for very
large files because it has to traverse the input buffer and count newlines to
compute the error message. Despite that, there are a few places were we create
errors just to discard them and continue parsing. The most notable of these
places was where we parsed the list of label index immediates for the br_table
instruction. The parser determined the end of the list by intercepting the error
produced when trying to parse one more label index.

Fix this significant performance problem causing parsing to be quadratic by
introducing and using `maybeLabelidx`, which tries to parse a label index but
does not produce an error if it fails.
---
 src/parser/parsers.h | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

(limited to 'src/parser/parsers.h')

diff --git a/src/parser/parsers.h b/src/parser/parsers.h
index bcae62e14..bbb50b664 100644
--- a/src/parser/parsers.h
+++ b/src/parser/parsers.h
@@ -330,6 +330,9 @@ template<typename Ctx> Result<typename Ctx::ElemIdxT> elemidx(Ctx&);
 template<typename Ctx> Result<typename Ctx::DataIdxT> dataidx(Ctx&);
 template<typename Ctx> Result<typename Ctx::LocalIdxT> localidx(Ctx&);
 template<typename Ctx>
+MaybeResult<typename Ctx::LabelIdxT> maybeLabelidx(Ctx&,
+                                                   bool inDelegate = false);
+template<typename Ctx>
 Result<typename Ctx::LabelIdxT> labelidx(Ctx&, bool inDelegate = false);
 template<typename Ctx> Result<typename Ctx::TagIdxT> tagidx(Ctx&);
 template<typename Ctx> Result<typename Ctx::TypeUseT> typeuse(Ctx&);
@@ -1969,16 +1972,18 @@ Result<> makeBreakTable(Ctx& ctx,
                         Index pos,
                         const std::vector<Annotation>& annotations) {
   std::vector<typename Ctx::LabelIdxT> labels;
+  // Parse at least one label; return an error only if we parse none.
   while (true) {
-    // Parse at least one label; return an error only if we parse none.
-    auto label = labelidx(ctx);
-    if (labels.empty()) {
-      CHECK_ERR(label);
-    } else if (label.getErr()) {
+    auto label = maybeLabelidx(ctx);
+    if (!label) {
       break;
     }
+    CHECK_ERR(label);
     labels.push_back(*label);
   }
+  if (labels.empty()) {
+    return ctx.in.err("expected label");
+  }
   auto defaultLabel = labels.back();
   labels.pop_back();
   return ctx.makeSwitch(pos, annotations, labels, defaultLabel);
@@ -2701,17 +2706,26 @@ template<typename Ctx> Result<typename Ctx::LocalIdxT> localidx(Ctx& ctx) {
   return ctx.in.err("expected local index or identifier");
 }
 
+template<typename Ctx>
+Result<typename Ctx::LabelIdxT> labelidx(Ctx& ctx, bool inDelegate) {
+  if (auto idx = maybeLabelidx(ctx, inDelegate)) {
+    CHECK_ERR(idx);
+    return *idx;
+  }
+  return ctx.in.err("expected label index or identifier");
+}
+
 // labelidx ::= x:u32 => x
 //            | v:id => x (if labels[x] = v)
 template<typename Ctx>
-Result<typename Ctx::LabelIdxT> labelidx(Ctx& ctx, bool inDelegate) {
+MaybeResult<typename Ctx::LabelIdxT> maybeLabelidx(Ctx& ctx, bool inDelegate) {
   if (auto x = ctx.in.takeU32()) {
     return ctx.getLabelFromIdx(*x, inDelegate);
   }
   if (auto id = ctx.in.takeID()) {
     return ctx.getLabelFromName(*id, inDelegate);
   }
-  return ctx.in.err("expected label index or identifier");
+  return {};
 }
 
 // tagidx ::= x:u32 => x
-- 
cgit v1.2.3