[demangler] Stricter NestedName parsing
The parsing of nested names is a little lax. This corrects that.
1) The 'L' local name prefix cannot appear before a NestedName -- only
within it. Let's remove that check from parseName, and then adjust
parseUnscopedName to allow it with or without the 'St' prefix.
2) In a nested name, a <template-param>, <decltype> or <substitution>
can only appear as the first element. Let's enforce that. Note I do
not remove these from the loop, to make the change easier to follow
(such a change will come later).
3) Given that, there's no need to special case 'St' outside of the
loop, handle it with the other 'S' elements.
4) There's no need to reset 'EndsWithTemplateArgs' after each
non-template-arg component. Rather, always clear it and then set it
in the template-args case.
5) An template-args cannot immediately follow a template-args.
6) The parsing of a CDtor name with ABITags would attach the tags to
the NestedName node, rather than the CDTor node. This is different to
how ABITags are attached to an unscopedName. Make it consistent.
7) We remain with only CDTor and UnscopedName requireing construction
of a NestedName, so let's drop the PushComponent lambda.
8) Add some tests to catch the new rejected manglings.
Reviewed By: ChuanqiXu
Differential Revision: https://reviews.llvm.org/D118132
GitOrigin-RevId: ad46cf14d408018edad17defe6d2911093d35503
diff --git a/src/demangle/ItaniumDemangle.h b/src/demangle/ItaniumDemangle.h
index c8a77ad..d0eaf6d 100644
--- a/src/demangle/ItaniumDemangle.h
+++ b/src/demangle/ItaniumDemangle.h
@@ -2572,8 +2572,6 @@
// ::= <substitution>
template <typename Derived, typename Alloc>
Node *AbstractManglingParser<Derived, Alloc>::parseName(NameState *State) {
- consumeIf('L'); // extension
-
if (look() == 'N')
return getDerived().parseNestedName(State);
if (look() == 'Z')
@@ -2649,15 +2647,14 @@
return make<LocalName>(Encoding, Entity);
}
-// <unscoped-name> ::= <unqualified-name>
-// ::= St <unqualified-name> # ::std::
-// extension ::= StL<unqualified-name>
+// <unscoped-name> ::= [L]* <unqualified-name>
+// ::= St [L]* <unqualified-name> # ::std::
+// [*] extension
template <typename Derived, typename Alloc>
Node *
AbstractManglingParser<Derived, Alloc>::parseUnscopedName(NameState *State) {
bool IsStd = consumeIf("St");
- if (IsStd)
- consumeIf('L');
+ consumeIf('L');
Node *Result = getDerived().parseUnqualifiedName(State);
if (Result == nullptr)
@@ -3148,14 +3145,14 @@
// <nested-name> ::= N [<CV-Qualifiers>] [<ref-qualifier>] <prefix> <unqualified-name> E
// ::= N [<CV-Qualifiers>] [<ref-qualifier>] <template-prefix> <template-args> E
//
-// <prefix> ::= <prefix> <unqualified-name>
+// <prefix> ::= <prefix> [L]* <unqualified-name>
// ::= <template-prefix> <template-args>
// ::= <template-param>
// ::= <decltype>
// ::= # empty
// ::= <substitution>
// ::= <prefix> <data-member-prefix>
-// extension ::= L
+// [*] extension
//
// <data-member-prefix> := <member source-name> [<template-args>] M
//
@@ -3175,88 +3172,85 @@
if (State) State->ReferenceQualifier = FrefQualRValue;
} else if (consumeIf('R')) {
if (State) State->ReferenceQualifier = FrefQualLValue;
- } else
+ } else {
if (State) State->ReferenceQualifier = FrefQualNone;
-
- Node *SoFar = nullptr;
- auto PushComponent = [&](Node *Comp) {
- if (!Comp) return false;
- if (SoFar) SoFar = make<NestedName>(SoFar, Comp);
- else SoFar = Comp;
- if (State) State->EndsWithTemplateArgs = false;
- return SoFar != nullptr;
- };
-
- if (consumeIf("St")) {
- SoFar = make<NameType>("std");
- if (!SoFar)
- return nullptr;
}
+ Node *SoFar = nullptr;
while (!consumeIf('E')) {
consumeIf('L'); // extension
- // <data-member-prefix> := <member source-name> [<template-args>] M
if (consumeIf('M')) {
+ // <data-member-prefix> := <member source-name> [<template-args>] M
if (SoFar == nullptr)
return nullptr;
continue;
}
- // ::= <template-param>
+ if (State)
+ // Only set end-with-template on the case that does that.
+ State->EndsWithTemplateArgs = false;
+
if (look() == 'T') {
- if (!PushComponent(getDerived().parseTemplateParam()))
- return nullptr;
- Subs.push_back(SoFar);
- continue;
- }
-
- // ::= <template-prefix> <template-args>
- if (look() == 'I') {
+ // ::= <template-param>
+ if (SoFar != nullptr)
+ return nullptr; // Cannot have a prefix.
+ SoFar = getDerived().parseTemplateParam();
+ } else if (look() == 'I') {
+ // ::= <template-prefix> <template-args>
+ if (SoFar == nullptr)
+ return nullptr; // Must have a prefix.
Node *TA = getDerived().parseTemplateArgs(State != nullptr);
- if (TA == nullptr || SoFar == nullptr)
+ if (TA == nullptr)
return nullptr;
+ if (SoFar->getKind() == Node::KNameWithTemplateArgs)
+ // Semantically <template-args> <template-args> cannot be generated by a
+ // C++ entity. There will always be [something like] a name between
+ // them.
+ return nullptr;
+ if (State)
+ State->EndsWithTemplateArgs = true;
SoFar = make<NameWithTemplateArgs>(SoFar, TA);
- if (!SoFar)
- return nullptr;
- if (State) State->EndsWithTemplateArgs = true;
- Subs.push_back(SoFar);
- continue;
- }
-
- // ::= <decltype>
- if (look() == 'D' && (look(1) == 't' || look(1) == 'T')) {
- if (!PushComponent(getDerived().parseDecltype()))
- return nullptr;
- Subs.push_back(SoFar);
- continue;
- }
-
- // ::= <substitution>
- if (look() == 'S' && look(1) != 't') {
- Node *S = getDerived().parseSubstitution();
- if (!PushComponent(S))
- return nullptr;
- if (SoFar != S)
- Subs.push_back(S);
- continue;
- }
-
- // Parse an <unqualified-name> thats actually a <ctor-dtor-name>.
- if (look() == 'C' || (look() == 'D' && look(1) != 'C')) {
+ } else if (look() == 'D' && (look(1) == 't' || look(1) == 'T')) {
+ // ::= <decltype>
+ if (SoFar != nullptr)
+ return nullptr; // Cannot have a prefix.
+ SoFar = getDerived().parseDecltype();
+ } else if (look() == 'S') {
+ // ::= <substitution>
+ if (SoFar != nullptr)
+ return nullptr; // Cannot have a prefix.
+ if (look(1) == 't') {
+ // parseSubstition does not handle 'St'.
+ First += 2;
+ SoFar = make<NameType>("std");
+ } else {
+ SoFar = getDerived().parseSubstitution();
+ }
if (SoFar == nullptr)
return nullptr;
- if (!PushComponent(getDerived().parseCtorDtorName(SoFar, State)))
+ continue; // Do not push a new substitution.
+ } else {
+ Node *N = nullptr;
+ if (look() == 'C' || (look() == 'D' && look(1) != 'C')) {
+ // An <unqualified-name> that's actually a <ctor-dtor-name>.
+ if (SoFar == nullptr)
+ return nullptr;
+ N = getDerived().parseCtorDtorName(SoFar, State);
+ if (N != nullptr)
+ N = getDerived().parseAbiTags(N);
+ } else {
+ // ::= <prefix> <unqualified-name>
+ N = getDerived().parseUnqualifiedName(State);
+ }
+ if (N == nullptr)
return nullptr;
- SoFar = getDerived().parseAbiTags(SoFar);
- if (SoFar == nullptr)
- return nullptr;
- Subs.push_back(SoFar);
- continue;
+ if (SoFar)
+ SoFar = make<NestedName>(SoFar, N);
+ else
+ SoFar = N;
}
-
- // ::= <prefix> <unqualified-name>
- if (!PushComponent(getDerived().parseUnqualifiedName(State)))
+ if (SoFar == nullptr)
return nullptr;
Subs.push_back(SoFar);
}
@@ -5431,6 +5425,7 @@
// <substitution> ::= Si # ::std::basic_istream<char, std::char_traits<char> >
// <substitution> ::= So # ::std::basic_ostream<char, std::char_traits<char> >
// <substitution> ::= Sd # ::std::basic_iostream<char, std::char_traits<char> >
+// The St case is handled specially in parseNestedName.
template <typename Derived, typename Alloc>
Node *AbstractManglingParser<Derived, Alloc>::parseSubstitution() {
if (!consumeIf('S'))
diff --git a/test/test_demangle.pass.cpp b/test/test_demangle.pass.cpp
index 191b4b6..263494a 100644
--- a/test/test_demangle.pass.cpp
+++ b/test/test_demangle.pass.cpp
@@ -29936,6 +29936,11 @@
"FSiIJEENT_IoE ",
"ZTVSiIZTVSiIZTVSiIZTVSiINIJEET_T_T_T_T_ ",
"Ana_T_E_T_IJEffffffffffffffersfffffrsrsffffffbgE",
+
+ "_ZN3TPLS_E",
+ "_ZN3CLSIiEIiEE",
+ "_ZN3CLSDtLi0EEE",
+ "_ZN3CLSIiEEvNS_T_Ev",
};
const unsigned NI = sizeof(invalid_cases) / sizeof(invalid_cases[0]);
