summaryrefslogtreecommitdiff
path: root/clang-tools-extra/pseudo
diff options
context:
space:
mode:
authorHaojian Wu <hokein.wu@gmail.com>2022-08-16 21:23:11 +0200
committerHaojian Wu <hokein.wu@gmail.com>2022-08-17 14:30:53 +0200
commit6a9f79e1020db9f581d00791f1f644b64facfebe (patch)
tree45cfe7ce4c9905c96fa39cb7c24ad82d991919b7 /clang-tools-extra/pseudo
parentd7e06d5675b62b5d3d89e6d6210c34b74a1a8356 (diff)
downloadllvm-6a9f79e1020db9f581d00791f1f644b64facfebe.tar.gz
[pseudo] Eliminate the type-name identifier ambiguities in the grammar.
See https://reviews.llvm.org/D130626 for motivation. Identifier in the grammar has different categories (type-name, template-name, namespace-name), they requires semantic information to resolve. This patch is to eliminate the "local" ambiguities in type-name, and namespace-name, which gives us a performance boost of the parser: - eliminate all different type rules (class-name, enum-name, typedef-name), and fold them into a unified type-name, this removes the #1 type-name ambiguity, and gives us a big performance boost; - remove the namespace-alis rules, as they're hard and uninteresting; Note that we could eliminate more and gain more performance (like fold template-name, type-name, namespace together), but at current stage, we'd like keep all existing categories of the identifier (as they might assist in correlated disambiguation & keep the representation of important concepts uniform). | file |ambiguous nodes | forest size | glrParse performance | |SemaCodeComplete.cpp| 11k -> 5.7K | 10.4MB -> 7.9MB | 7.1MB/s -> 9.98MB/s | | AST.cpp | 1.3k -> 0.73K | 0.99MB -> 0.77MB | 6.7MB/s -> 8.4MB/s | Differential Revision: https://reviews.llvm.org/D130747
Diffstat (limited to 'clang-tools-extra/pseudo')
-rw-r--r--clang-tools-extra/pseudo/lib/cxx/cxx.bnf20
-rw-r--r--clang-tools-extra/pseudo/test/glr.cpp10
2 files changed, 12 insertions, 18 deletions
diff --git a/clang-tools-extra/pseudo/lib/cxx/cxx.bnf b/clang-tools-extra/pseudo/lib/cxx/cxx.bnf
index bc6599c4e3c4..7221a5086acf 100644
--- a/clang-tools-extra/pseudo/lib/cxx/cxx.bnf
+++ b/clang-tools-extra/pseudo/lib/cxx/cxx.bnf
@@ -34,14 +34,9 @@ _ := statement-seq
_ := declaration-seq
# gram.key
-typedef-name := IDENTIFIER
-typedef-name := simple-template-id
+#! we don't distinguish between namespaces and namespace aliases, as it's hard
+#! and uninteresting.
namespace-name := IDENTIFIER
-namespace-name := namespace-alias
-namespace-alias := IDENTIFIER
-class-name := IDENTIFIER
-class-name := simple-template-id
-enum-name := IDENTIFIER
template-name := IDENTIFIER
# gram.basic
@@ -391,9 +386,12 @@ builtin-type := INT
builtin-type := FLOAT
builtin-type := DOUBLE
builtin-type := VOID
-type-name := class-name
-type-name := enum-name
-type-name := typedef-name
+#! Unlike C++ standard grammar, we don't distinguish the underlying type (class,
+#! enum, typedef) of the IDENTIFIER, as these ambiguities are "local" and don't
+#! affect the final parse tree. Eliminating them gives a significant performance
+#! boost to the parser.
+type-name := IDENTIFIER
+type-name := simple-template-id
elaborated-type-specifier := class-key nested-name-specifier_opt IDENTIFIER
elaborated-type-specifier := class-key simple-template-id
elaborated-type-specifier := class-key nested-name-specifier TEMPLATE_opt simple-template-id
@@ -551,7 +549,7 @@ private-module-fragment := module-keyword : PRIVATE ; declaration-seq_opt
class-specifier := class-head { member-specification_opt [recover=Brackets] }
class-head := class-key class-head-name class-virt-specifier_opt base-clause_opt
class-head := class-key base-clause_opt
-class-head-name := nested-name-specifier_opt class-name
+class-head-name := nested-name-specifier_opt type-name
class-virt-specifier := contextual-final
class-key := CLASS
class-key := STRUCT
diff --git a/clang-tools-extra/pseudo/test/glr.cpp b/clang-tools-extra/pseudo/test/glr.cpp
index 221725c6f089..f805e42ffa6d 100644
--- a/clang-tools-extra/pseudo/test/glr.cpp
+++ b/clang-tools-extra/pseudo/test/glr.cpp
@@ -12,10 +12,7 @@ void foo() {
// CHECK-NEXT: │ └─; := tok[8]
// CHECK-NEXT: └─statement~simple-declaration := decl-specifier-seq init-declarator-list ;
// CHECK-NEXT: ├─decl-specifier-seq~simple-type-specifier := <ambiguous>
-// CHECK-NEXT: │ ├─simple-type-specifier~type-name := <ambiguous>
-// CHECK-NEXT: │ │ ├─type-name~IDENTIFIER := tok[5]
-// CHECK-NEXT: │ │ ├─type-name~IDENTIFIER := tok[5]
-// CHECK-NEXT: │ │ └─type-name~IDENTIFIER := tok[5]
+// CHECK-NEXT: │ ├─simple-type-specifier~IDENTIFIER := tok[5]
// CHECK-NEXT: │ └─simple-type-specifier~IDENTIFIER := tok[5]
// CHECK-NEXT: ├─init-declarator-list~ptr-declarator := ptr-operator ptr-declarator
// CHECK-NEXT: │ ├─ptr-operator~* := tok[6]
@@ -23,12 +20,11 @@ void foo() {
// CHECK-NEXT: └─; := tok[8]
}
-// CHECK: 3 Ambiguous nodes:
+// CHECK: 2 Ambiguous nodes:
// CHECK-NEXT: 1 simple-type-specifier
// CHECK-NEXT: 1 statement
-// CHECK-NEXT: 1 type-name
// CHECK-EMPTY:
// CHECK-NEXT: 0 Opaque nodes:
// CHECK-EMPTY:
-// CHECK-NEXT: Ambiguity: 0.40 misparses/token
+// CHECK-NEXT: Ambiguity: 0.20 misparses/token
// CHECK-NEXT: Unparsed: 0.00%