2018-07-21 01:27:48 +08:00
|
|
|
//===- MicrosoftDemangle.cpp ----------------------------------------------===//
|
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is dual licensed under the MIT and the University of Illinois Open
|
|
|
|
// Source Licenses. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file defines a demangler for MSVC-style mangled symbols.
|
|
|
|
//
|
|
|
|
// This file has no dependencies on the rest of LLVM so that it can be
|
|
|
|
// easily reused in other programs such as libcxxabi.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#include "llvm/Demangle/Demangle.h"
|
|
|
|
|
Move Itanium demangler implementation into a header file and add visitation support.
Summary:
This transforms the Itanium demangler into a generic reusable library that can
be used to build, traverse, and transform Itanium mangled name trees.
This is in preparation for adding a canonicalizing demangler, which
cannot live in the Demangle library for layering reasons. In order to
keep the diffs simpler, this patch moves more code to the new header
than is strictly necessary: in particular, all of the printLeft /
printRight implementations can be moved to the implementation file.
(And indeed we could make them non-virtual now if we wished, and remove
the vptr from Node.)
All nodes are now included in the Kind enumeration, rather than omitting
some of the Expr nodes, and the three different floating-point literal
node types now have distinct Kind values.
As a proof of concept for the visitation / matching mechanism, this
patch implements a Node dumping facility on top of it, replacing the
prior mechanism that produced the pretty-printed output rather than a
tree dump. Sample dump output:
FunctionEncoding(
NameType("int"),
NameWithTemplateArgs(
NestedName(
NameWithTemplateArgs(
NameType("A"),
TemplateArgs(
{NameType("B")})),
NameType("f")),
TemplateArgs(
{NameType("int")})),
{},
<null>,
QualConst, FunctionRefQual::FrefQualLValue)
As a next step, it would make sense to move the LLVM high-level interface to
the demangler (the itaniumDemangler function and ItaniumPartialDemangler class)
into the Support library, and implement them in terms of the Demangle library.
This would allow the libc++abi demangler implementation to be an identical copy
of the llvm Demangle library, and would allow the LLVM implementation to reuse
LLVM components such as llvm::BumpPtrAllocator, but we'll need to decide how to
coordinate that with the MS ABI demangler, so I'm not doing that in this patch.
No functionality change intended other than the behavior of dump().
Reviewers: erik.pilkington, zturner, chandlerc, dlj
Subscribers: aheejin, llvm-commits
Differential Revision: https://reviews.llvm.org/D50930
llvm-svn: 340203
2018-08-21 03:44:01 +08:00
|
|
|
#include "llvm/Demangle/Compiler.h"
|
|
|
|
#include "llvm/Demangle/StringView.h"
|
|
|
|
#include "llvm/Demangle/Utility.h"
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-21 03:15:35 +08:00
|
|
|
#include <array>
|
2018-07-21 01:27:48 +08:00
|
|
|
#include <cctype>
|
2018-08-02 02:44:12 +08:00
|
|
|
#include <cstdio>
|
2018-07-27 03:56:09 +08:00
|
|
|
#include <tuple>
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// This memory allocator is extremely fast, but it doesn't call dtors
|
|
|
|
// for allocated objects. That means you can't use STL containers
|
|
|
|
// (such as std::vector) with this allocator. But it pays off --
|
|
|
|
// the demangler is 3x faster with this allocator compared to one with
|
|
|
|
// STL containers.
|
|
|
|
namespace {
|
2018-07-30 11:25:27 +08:00
|
|
|
constexpr size_t AllocUnit = 4096;
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
class ArenaAllocator {
|
|
|
|
struct AllocatorNode {
|
|
|
|
uint8_t *Buf = nullptr;
|
|
|
|
size_t Used = 0;
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
size_t Capacity = 0;
|
2018-07-21 01:27:48 +08:00
|
|
|
AllocatorNode *Next = nullptr;
|
|
|
|
};
|
|
|
|
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
void addNode(size_t Capacity) {
|
|
|
|
AllocatorNode *NewHead = new AllocatorNode;
|
|
|
|
NewHead->Buf = new uint8_t[Capacity];
|
|
|
|
NewHead->Next = Head;
|
|
|
|
NewHead->Capacity = Capacity;
|
|
|
|
Head = NewHead;
|
|
|
|
NewHead->Used = 0;
|
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
public:
|
2018-07-30 11:25:27 +08:00
|
|
|
ArenaAllocator() { addNode(AllocUnit); }
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
~ArenaAllocator() {
|
|
|
|
while (Head) {
|
|
|
|
assert(Head->Buf);
|
|
|
|
delete[] Head->Buf;
|
2018-07-24 02:21:43 +08:00
|
|
|
AllocatorNode *Next = Head->Next;
|
|
|
|
delete Head;
|
|
|
|
Head = Next;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
char *allocUnalignedBuffer(size_t Length) {
|
|
|
|
uint8_t *Buf = Head->Buf + Head->Used;
|
|
|
|
|
|
|
|
Head->Used += Length;
|
|
|
|
if (Head->Used > Head->Capacity) {
|
|
|
|
// It's possible we need a buffer which is larger than our default unit
|
|
|
|
// size, so we need to be careful to add a node with capacity that is at
|
|
|
|
// least as large as what we need.
|
2018-07-30 11:25:27 +08:00
|
|
|
addNode(std::max(AllocUnit, Length));
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
Head->Used = Length;
|
|
|
|
Buf = Head->Buf;
|
|
|
|
}
|
|
|
|
|
|
|
|
return reinterpret_cast<char *>(Buf);
|
|
|
|
}
|
|
|
|
|
2018-07-21 02:35:06 +08:00
|
|
|
template <typename T, typename... Args> T *alloc(Args &&... ConstructorArgs) {
|
|
|
|
|
|
|
|
size_t Size = sizeof(T);
|
2018-07-21 01:27:48 +08:00
|
|
|
assert(Head && Head->Buf);
|
|
|
|
|
2018-07-21 02:35:06 +08:00
|
|
|
size_t P = (size_t)Head->Buf + Head->Used;
|
|
|
|
uintptr_t AlignedP =
|
|
|
|
(((size_t)P + alignof(T) - 1) & ~(size_t)(alignof(T) - 1));
|
|
|
|
uint8_t *PP = (uint8_t *)AlignedP;
|
|
|
|
size_t Adjustment = AlignedP - P;
|
|
|
|
|
|
|
|
Head->Used += Size + Adjustment;
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
if (Head->Used < Head->Capacity)
|
2018-07-21 02:35:06 +08:00
|
|
|
return new (PP) T(std::forward<Args>(ConstructorArgs)...);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-30 11:25:27 +08:00
|
|
|
addNode(AllocUnit);
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
Head->Used = Size;
|
|
|
|
return new (Head->Buf) T(std::forward<Args>(ConstructorArgs)...);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
AllocatorNode *Head = nullptr;
|
|
|
|
};
|
|
|
|
} // namespace
|
|
|
|
|
|
|
|
static bool startsWithDigit(StringView S) {
|
|
|
|
return !S.empty() && std::isdigit(S.front());
|
|
|
|
}
|
|
|
|
|
|
|
|
// Writes a space if the last token does not end with a punctuation.
|
|
|
|
static void outputSpaceIfNecessary(OutputStream &OS) {
|
|
|
|
if (OS.empty())
|
|
|
|
return;
|
|
|
|
|
|
|
|
char C = OS.back();
|
|
|
|
if (isalnum(C) || C == '>')
|
|
|
|
OS << " ";
|
|
|
|
}
|
|
|
|
|
|
|
|
// Storage classes
|
|
|
|
enum Qualifiers : uint8_t {
|
|
|
|
Q_None = 0,
|
|
|
|
Q_Const = 1 << 0,
|
|
|
|
Q_Volatile = 1 << 1,
|
|
|
|
Q_Far = 1 << 2,
|
|
|
|
Q_Huge = 1 << 3,
|
|
|
|
Q_Unaligned = 1 << 4,
|
|
|
|
Q_Restrict = 1 << 5,
|
|
|
|
Q_Pointer64 = 1 << 6
|
|
|
|
};
|
|
|
|
|
|
|
|
enum class StorageClass : uint8_t {
|
|
|
|
None,
|
|
|
|
PrivateStatic,
|
|
|
|
ProtectedStatic,
|
|
|
|
PublicStatic,
|
|
|
|
Global,
|
2018-08-18 00:14:05 +08:00
|
|
|
FunctionLocalStatic,
|
2018-07-21 01:27:48 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
enum class QualifierMangleMode { Drop, Mangle, Result };
|
2018-07-27 03:56:09 +08:00
|
|
|
|
2018-07-31 07:02:10 +08:00
|
|
|
enum class PointerAffinity { Pointer, Reference, RValueReference };
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// Calling conventions
|
|
|
|
enum class CallingConv : uint8_t {
|
|
|
|
None,
|
|
|
|
Cdecl,
|
|
|
|
Pascal,
|
|
|
|
Thiscall,
|
|
|
|
Stdcall,
|
|
|
|
Fastcall,
|
|
|
|
Clrcall,
|
|
|
|
Eabi,
|
|
|
|
Vectorcall,
|
|
|
|
Regcall,
|
|
|
|
};
|
|
|
|
|
|
|
|
enum class ReferenceKind : uint8_t { None, LValueRef, RValueRef };
|
|
|
|
|
|
|
|
// Types
|
|
|
|
enum class PrimTy : uint8_t {
|
|
|
|
Unknown,
|
|
|
|
None,
|
|
|
|
Function,
|
|
|
|
Ptr,
|
2018-07-27 03:56:09 +08:00
|
|
|
MemberPtr,
|
2018-07-21 01:27:48 +08:00
|
|
|
Array,
|
|
|
|
|
|
|
|
Struct,
|
|
|
|
Union,
|
|
|
|
Class,
|
|
|
|
Enum,
|
|
|
|
|
|
|
|
Void,
|
|
|
|
Bool,
|
|
|
|
Char,
|
|
|
|
Schar,
|
|
|
|
Uchar,
|
2018-07-31 07:02:10 +08:00
|
|
|
Char16,
|
|
|
|
Char32,
|
2018-07-21 01:27:48 +08:00
|
|
|
Short,
|
|
|
|
Ushort,
|
|
|
|
Int,
|
|
|
|
Uint,
|
|
|
|
Long,
|
|
|
|
Ulong,
|
|
|
|
Int64,
|
|
|
|
Uint64,
|
|
|
|
Wchar,
|
|
|
|
Float,
|
|
|
|
Double,
|
|
|
|
Ldouble,
|
2018-08-18 00:14:05 +08:00
|
|
|
Nullptr,
|
|
|
|
Vftable,
|
|
|
|
Vbtable,
|
|
|
|
LocalStaticGuard
|
|
|
|
};
|
|
|
|
|
|
|
|
enum class OperatorTy : uint8_t {
|
|
|
|
Ctor, // ?0 # Foo::Foo()
|
|
|
|
Dtor, // ?1 # Foo::~Foo()
|
|
|
|
New, // ?2 # operator new
|
|
|
|
Delete, // ?3 # operator delete
|
|
|
|
Assign, // ?4 # operator=
|
|
|
|
RightShift, // ?5 # operator>>
|
|
|
|
LeftShift, // ?6 # operator<<
|
|
|
|
LogicalNot, // ?7 # operator!
|
|
|
|
Equals, // ?8 # operator==
|
|
|
|
NotEquals, // ?9 # operator!=
|
|
|
|
ArraySubscript, // ?A # operator[]
|
|
|
|
Conversion, // ?B # Foo::operator <type>()
|
|
|
|
Pointer, // ?C # operator->
|
|
|
|
Dereference, // ?D # operator*
|
|
|
|
Increment, // ?E # operator++
|
|
|
|
Decrement, // ?F # operator--
|
|
|
|
Minus, // ?G # operator-
|
|
|
|
Plus, // ?H # operator+
|
|
|
|
BitwiseAnd, // ?I # operator&
|
|
|
|
MemberPointer, // ?J # operator->*
|
|
|
|
Divide, // ?K # operator/
|
|
|
|
Modulus, // ?L # operator%
|
|
|
|
LessThan, // ?M operator<
|
|
|
|
LessThanEqual, // ?N operator<=
|
|
|
|
GreaterThan, // ?O operator>
|
|
|
|
GreaterThanEqual, // ?P operator>=
|
|
|
|
Comma, // ?Q operator,
|
|
|
|
Parens, // ?R operator()
|
|
|
|
BitwiseNot, // ?S operator~
|
|
|
|
BitwiseXor, // ?T operator^
|
|
|
|
BitwiseOr, // ?U operator|
|
|
|
|
LogicalAnd, // ?V operator&&
|
|
|
|
LogicalOr, // ?W operator||
|
|
|
|
TimesEqual, // ?X operator*=
|
|
|
|
PlusEqual, // ?Y operator+=
|
|
|
|
MinusEqual, // ?Z operator-=
|
|
|
|
DivEqual, // ?_0 operator/=
|
|
|
|
ModEqual, // ?_1 operator%=
|
|
|
|
RshEqual, // ?_2 operator>>=
|
|
|
|
LshEqual, // ?_3 operator<<=
|
|
|
|
BitwiseAndEqual, // ?_4 operator&=
|
|
|
|
BitwiseOrEqual, // ?_5 operator|=
|
|
|
|
BitwiseXorEqual, // ?_6 operator^=
|
|
|
|
Vftable, // ?_7 # vftable
|
|
|
|
Vbtable, // ?_8 # vbtable
|
|
|
|
Vcall, // ?_9 # vcall
|
|
|
|
Typeof, // ?_A # typeof
|
|
|
|
LocalStaticGuard, // ?_B # local static guard
|
|
|
|
StringLiteral, // ?_C # string literal
|
|
|
|
VbaseDtor, // ?_D # vbase destructor
|
|
|
|
VecDelDtor, // ?_E # vector deleting destructor
|
|
|
|
DefaultCtorClosure, // ?_F # default constructor closure
|
|
|
|
ScalarDelDtor, // ?_G # scalar deleting destructor
|
|
|
|
VecCtorIter, // ?_H # vector constructor iterator
|
|
|
|
VecDtorIter, // ?_I # vector destructor iterator
|
|
|
|
VecVbaseCtorIter, // ?_J # vector vbase constructor iterator
|
|
|
|
VdispMap, // ?_K # virtual displacement map
|
|
|
|
EHVecCtorIter, // ?_L # eh vector constructor iterator
|
|
|
|
EHVecDtorIter, // ?_M # eh vector destructor iterator
|
|
|
|
EHVecVbaseCtorIter, // ?_N # eh vector vbase constructor iterator
|
|
|
|
CopyCtorClosure, // ?_O # copy constructor closure
|
|
|
|
UdtReturning, // ?_P<name> # udt returning <name>
|
|
|
|
Unknown, // ?_Q # <unknown>
|
|
|
|
RttiTypeDescriptor, // ?_R0 # RTTI Type Descriptor
|
|
|
|
RttiBaseClassDescriptor, // ?_R1 # RTTI Base Class Descriptor at (a,b,c,d)
|
|
|
|
RttiBaseClassArray, // ?_R2 # RTTI Base Class Array
|
|
|
|
RttiClassHierarchyDescriptor, // ?_R3 # RTTI Class Hierarchy Descriptor
|
|
|
|
RttiCompleteObjLocator, // ?_R4 # RTTI Complete Object Locator
|
|
|
|
LocalVftable, // ?_S # local vftable
|
|
|
|
LocalVftableCtorClosure, // ?_T # local vftable constructor closure
|
|
|
|
ArrayNew, // ?_U operator new[]
|
|
|
|
ArrayDelete, // ?_V operator delete[]
|
2018-08-21 07:59:21 +08:00
|
|
|
DynamicInitializer, // ?__E dynamic initializer for `T'
|
|
|
|
DynamicAtexitDestructor, // ?__F dynamic atexit destructor for `T'
|
2018-08-18 00:14:05 +08:00
|
|
|
LiteralOperator, // ?__K operator ""_name
|
|
|
|
CoAwait, // ?__L co_await
|
|
|
|
Spaceship, // operator<=>
|
|
|
|
};
|
|
|
|
|
|
|
|
// A map to translate from operator prefix to operator type.
|
|
|
|
struct OperatorMapEntry {
|
|
|
|
StringView Prefix;
|
|
|
|
StringView Name;
|
|
|
|
OperatorTy Operator;
|
|
|
|
};
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
// The entries here must be in the same order as the enumeration so that it can
|
|
|
|
// be indexed by enum value.
|
2018-08-18 00:14:05 +08:00
|
|
|
OperatorMapEntry OperatorMap[] = {
|
|
|
|
{"0", " <ctor>", OperatorTy::Ctor},
|
|
|
|
{"1", " <dtor>", OperatorTy::Dtor},
|
|
|
|
{"2", "operator new", OperatorTy::New},
|
|
|
|
{"3", "operator delete", OperatorTy::Delete},
|
|
|
|
{"4", "operator=", OperatorTy::Assign},
|
|
|
|
{"5", "operator>>", OperatorTy::RightShift},
|
|
|
|
{"6", "operator<<", OperatorTy::LeftShift},
|
|
|
|
{"7", "operator!", OperatorTy::LogicalNot},
|
|
|
|
{"8", "operator==", OperatorTy::Equals},
|
|
|
|
{"9", "operator!=", OperatorTy::NotEquals},
|
|
|
|
{"A", "operator[]", OperatorTy::ArraySubscript},
|
|
|
|
{"B", "operator <conversion>", OperatorTy::Conversion},
|
|
|
|
{"C", "operator->", OperatorTy::Pointer},
|
|
|
|
{"D", "operator*", OperatorTy::Dereference},
|
|
|
|
{"E", "operator++", OperatorTy::Increment},
|
|
|
|
{"F", "operator--", OperatorTy::Decrement},
|
|
|
|
{"G", "operator-", OperatorTy::Minus},
|
|
|
|
{"H", "operator+", OperatorTy::Plus},
|
|
|
|
{"I", "operator&", OperatorTy::BitwiseAnd},
|
|
|
|
{"J", "operator->*", OperatorTy::MemberPointer},
|
|
|
|
{"K", "operator/", OperatorTy::Divide},
|
|
|
|
{"L", "operator%", OperatorTy::Modulus},
|
|
|
|
{"M", "operator<", OperatorTy::LessThan},
|
|
|
|
{"N", "operator<=", OperatorTy::LessThanEqual},
|
|
|
|
{"O", "operator>", OperatorTy::GreaterThan},
|
|
|
|
{"P", "operator>=", OperatorTy::GreaterThanEqual},
|
|
|
|
{"Q", "operator,", OperatorTy::Comma},
|
|
|
|
{"R", "operator()", OperatorTy::Parens},
|
|
|
|
{"S", "operator~", OperatorTy::BitwiseNot},
|
|
|
|
{"T", "operator^", OperatorTy::BitwiseXor},
|
|
|
|
{"U", "operator|", OperatorTy::BitwiseOr},
|
|
|
|
{"V", "operator&&", OperatorTy::LogicalAnd},
|
|
|
|
{"W", "operator||", OperatorTy::LogicalOr},
|
|
|
|
{"X", "operator*=", OperatorTy::TimesEqual},
|
|
|
|
{"Y", "operator+=", OperatorTy::PlusEqual},
|
|
|
|
{"Z", "operator-=", OperatorTy::MinusEqual},
|
|
|
|
{"_0", "operator/=", OperatorTy::DivEqual},
|
|
|
|
{"_1", "operator%=", OperatorTy::ModEqual},
|
|
|
|
{"_2", "operator>>=", OperatorTy::RshEqual},
|
|
|
|
{"_3", "operator<<=", OperatorTy::LshEqual},
|
|
|
|
{"_4", "operator&=", OperatorTy::BitwiseAndEqual},
|
|
|
|
{"_5", "operator|=", OperatorTy::BitwiseOrEqual},
|
|
|
|
{"_6", "operator^=", OperatorTy::BitwiseXorEqual},
|
|
|
|
{"_7", "`vftable'", OperatorTy::Vftable},
|
|
|
|
{"_8", "`vbtable'", OperatorTy::Vbtable},
|
|
|
|
{"_9", "`vcall'", OperatorTy::Vcall},
|
|
|
|
{"_A", "`typeof'", OperatorTy::Typeof},
|
|
|
|
{"_B", "`local static guard'", OperatorTy::LocalStaticGuard},
|
|
|
|
{"_C", "`string'", OperatorTy::StringLiteral},
|
|
|
|
{"_D", "`vbase dtor'", OperatorTy::VbaseDtor},
|
|
|
|
{"_E", "`vector deleting dtor'", OperatorTy::VecDelDtor},
|
|
|
|
{"_F", "`default ctor closure'", OperatorTy::DefaultCtorClosure},
|
|
|
|
{"_G", "`scalar deleting dtor'", OperatorTy::ScalarDelDtor},
|
|
|
|
{"_H", "`vector ctor iterator'", OperatorTy::VecCtorIter},
|
|
|
|
{"_I", "`vector dtor iterator'", OperatorTy::VecDtorIter},
|
|
|
|
{"_J", "`vector vbase ctor iterator'", OperatorTy::VecVbaseCtorIter},
|
|
|
|
{"_K", "`virtual displacement map'", OperatorTy::VdispMap},
|
|
|
|
{"_L", "`eh vector ctor iterator'", OperatorTy::EHVecCtorIter},
|
|
|
|
{"_M", "`eh vector dtor iterator'", OperatorTy::EHVecDtorIter},
|
|
|
|
{"_N", "`eh vector vbase ctor iterator'", OperatorTy::EHVecVbaseCtorIter},
|
|
|
|
{"_O", "`copy ctor closure'", OperatorTy::CopyCtorClosure},
|
|
|
|
{"_P", "`udt returning'", OperatorTy::UdtReturning},
|
|
|
|
{"_Q", "`unknown'", OperatorTy::Unknown},
|
|
|
|
{"_R0", "`RTTI Type Descriptor'", OperatorTy::RttiTypeDescriptor},
|
2018-08-18 05:18:05 +08:00
|
|
|
{"_R1", "RTTI Base Class Descriptor", OperatorTy::RttiBaseClassDescriptor},
|
2018-08-18 00:14:05 +08:00
|
|
|
{"_R2", "`RTTI Base Class Array'", OperatorTy::RttiBaseClassArray},
|
|
|
|
{"_R3", "`RTTI Class Hierarchy Descriptor'",
|
|
|
|
OperatorTy::RttiClassHierarchyDescriptor},
|
|
|
|
{"_R4", "`RTTI Complete Object Locator'",
|
|
|
|
OperatorTy::RttiCompleteObjLocator},
|
|
|
|
{"_S", "`local vftable'", OperatorTy::LocalVftable},
|
|
|
|
{"_T", "`local vftable ctor closure'", OperatorTy::LocalVftableCtorClosure},
|
|
|
|
{"_U", "operator new[]", OperatorTy::ArrayNew},
|
|
|
|
{"_V", "operator delete[]", OperatorTy::ArrayDelete},
|
2018-08-21 07:59:21 +08:00
|
|
|
{"__E", "dynamic initializer", OperatorTy::DynamicInitializer},
|
|
|
|
{"__F", "dynamic atexit destructor", OperatorTy::DynamicAtexitDestructor},
|
2018-08-18 00:14:05 +08:00
|
|
|
{"__K", "operator \"\"", OperatorTy::LiteralOperator},
|
|
|
|
{"__L", "co_await", OperatorTy::CoAwait},
|
2018-07-21 01:27:48 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
// Function classes
|
2018-08-11 05:09:05 +08:00
|
|
|
enum FuncClass : uint16_t {
|
2018-08-18 05:18:05 +08:00
|
|
|
None = 0,
|
2018-07-21 01:27:48 +08:00
|
|
|
Public = 1 << 0,
|
|
|
|
Protected = 1 << 1,
|
|
|
|
Private = 1 << 2,
|
|
|
|
Global = 1 << 3,
|
|
|
|
Static = 1 << 4,
|
|
|
|
Virtual = 1 << 5,
|
2018-07-21 02:07:33 +08:00
|
|
|
Far = 1 << 6,
|
2018-08-11 05:09:05 +08:00
|
|
|
ExternC = 1 << 7,
|
|
|
|
NoPrototype = 1 << 8,
|
2018-08-18 05:18:05 +08:00
|
|
|
VirtualThisAdjust = 1 << 9,
|
|
|
|
VirtualThisAdjustEx = 1 << 10,
|
|
|
|
StaticThisAdjust = 1 << 11
|
2018-07-21 01:27:48 +08:00
|
|
|
};
|
|
|
|
|
2018-08-08 08:43:31 +08:00
|
|
|
enum NameBackrefBehavior : uint8_t {
|
|
|
|
NBB_None = 0, // don't save any names as backrefs.
|
|
|
|
NBB_Template = 1 << 0, // save template instanations.
|
|
|
|
NBB_Simple = 1 << 1, // save simple names.
|
|
|
|
};
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
enum class SymbolCategory {
|
|
|
|
Unknown,
|
|
|
|
NamedFunction,
|
|
|
|
NamedVariable,
|
|
|
|
UnnamedFunction,
|
|
|
|
UnnamedVariable,
|
|
|
|
SpecialOperator
|
|
|
|
};
|
2018-08-02 02:32:47 +08:00
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
namespace {
|
|
|
|
|
|
|
|
struct Type;
|
2018-07-31 07:02:10 +08:00
|
|
|
struct Name;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
struct FunctionParams {
|
2018-07-27 04:20:10 +08:00
|
|
|
bool IsVariadic = false;
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
Type *Current = nullptr;
|
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
FunctionParams *Next = nullptr;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct TemplateParams {
|
|
|
|
bool IsTemplateTemplate = false;
|
|
|
|
bool IsAliasTemplate = false;
|
2018-08-10 22:31:04 +08:00
|
|
|
bool IsIntegerLiteral = false;
|
|
|
|
bool IntegerLiteralIsNegative = false;
|
|
|
|
bool IsEmptyParameterPack = false;
|
|
|
|
bool PointerToSymbol = false;
|
2018-08-21 03:15:35 +08:00
|
|
|
bool NullptrLiteral = false;
|
|
|
|
bool DataMemberPointer = false;
|
2018-08-10 22:31:04 +08:00
|
|
|
bool ReferenceToSymbol = false;
|
|
|
|
|
2018-08-21 03:15:35 +08:00
|
|
|
int ThunkOffsetCount = 0;
|
|
|
|
std::array<int64_t, 3> ThunkOffsets;
|
|
|
|
|
2018-08-10 22:31:04 +08:00
|
|
|
// If IsIntegerLiteral is true, this is a non-type template parameter
|
|
|
|
// whose value is contained in this field.
|
|
|
|
uint64_t IntegralValue = 0;
|
2018-08-01 01:16:44 +08:00
|
|
|
|
|
|
|
// Type can be null if this is a template template parameter. In that case
|
|
|
|
// only Name will be valid.
|
|
|
|
Type *ParamType = nullptr;
|
2018-07-31 07:02:10 +08:00
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
// Name can be valid if this is a template template parameter (see above) or
|
|
|
|
// this is a function declaration (e.g. foo<&SomeFunc>). In the latter case
|
|
|
|
// Name contains the name of the function and Type contains the signature.
|
|
|
|
Name *ParamName = nullptr;
|
|
|
|
|
|
|
|
TemplateParams *Next = nullptr;
|
2018-07-21 01:27:48 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
// The type class. Mangled symbols are first parsed and converted to
|
|
|
|
// this type and then converted to string.
|
|
|
|
struct Type {
|
|
|
|
virtual ~Type() {}
|
|
|
|
|
|
|
|
virtual Type *clone(ArenaAllocator &Arena) const;
|
|
|
|
|
|
|
|
// Write the "first half" of a given type. This is a static functions to
|
|
|
|
// give the code a chance to do processing that is common to a subset of
|
|
|
|
// subclasses
|
2018-08-19 02:49:48 +08:00
|
|
|
static void outputPre(OutputStream &OS, Type &Ty);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// Write the "second half" of a given type. This is a static functions to
|
|
|
|
// give the code a chance to do processing that is common to a subset of
|
|
|
|
// subclasses
|
2018-08-19 02:49:48 +08:00
|
|
|
static void outputPost(OutputStream &OS, Type &Ty);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
virtual void outputPre(OutputStream &OS);
|
|
|
|
virtual void outputPost(OutputStream &OS);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// Primitive type such as Int.
|
|
|
|
PrimTy Prim = PrimTy::Unknown;
|
|
|
|
|
|
|
|
Qualifiers Quals = Q_None;
|
|
|
|
StorageClass Storage = StorageClass::None; // storage class
|
|
|
|
};
|
|
|
|
|
|
|
|
// Represents an identifier which may be a template.
|
|
|
|
struct Name {
|
2018-08-18 00:14:05 +08:00
|
|
|
virtual ~Name() = default;
|
|
|
|
|
2018-08-02 02:32:47 +08:00
|
|
|
bool IsTemplateInstantiation = false;
|
|
|
|
bool IsOperator = false;
|
2018-08-03 01:08:03 +08:00
|
|
|
bool IsBackReference = false;
|
2018-08-17 00:17:36 +08:00
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
bool isStringLiteralOperatorInfo() const;
|
2018-08-10 23:04:56 +08:00
|
|
|
|
|
|
|
// Name read from an MangledName string.
|
|
|
|
StringView Str;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
// Template parameters. Only valid if IsTemplateInstantiation is true.
|
2018-08-01 01:16:44 +08:00
|
|
|
TemplateParams *TParams = nullptr;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// Nested BackReferences (e.g. "A::B::C") are represented as a linked list.
|
|
|
|
Name *Next = nullptr;
|
|
|
|
};
|
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
struct OperatorInfo : public Name {
|
2018-08-18 05:18:05 +08:00
|
|
|
explicit OperatorInfo(const OperatorMapEntry &Info) : Info(&Info) {
|
|
|
|
this->IsOperator = true;
|
|
|
|
}
|
|
|
|
explicit OperatorInfo(OperatorTy OpType)
|
|
|
|
: OperatorInfo(OperatorMap[(int)OpType]) {}
|
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
const OperatorMapEntry *Info = nullptr;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct StringLiteral : public OperatorInfo {
|
2018-08-18 05:18:05 +08:00
|
|
|
StringLiteral() : OperatorInfo(OperatorTy::StringLiteral) {}
|
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
PrimTy CharType;
|
|
|
|
bool IsTruncated = false;
|
|
|
|
};
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
struct RttiBaseClassDescriptor : public OperatorInfo {
|
|
|
|
RttiBaseClassDescriptor()
|
|
|
|
: OperatorInfo(OperatorTy::RttiBaseClassDescriptor) {}
|
|
|
|
|
|
|
|
uint32_t NVOffset = 0;
|
|
|
|
int32_t VBPtrOffset = 0;
|
|
|
|
uint32_t VBTableOffset = 0;
|
|
|
|
uint32_t Flags = 0;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct LocalStaticGuardVariable : public OperatorInfo {
|
|
|
|
LocalStaticGuardVariable() : OperatorInfo(OperatorTy::LocalStaticGuard) {}
|
|
|
|
|
|
|
|
uint32_t ScopeIndex = 0;
|
|
|
|
bool IsVisible = false;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct VirtualMemberPtrThunk : public OperatorInfo {
|
|
|
|
VirtualMemberPtrThunk() : OperatorInfo(OperatorTy::Vcall) {}
|
|
|
|
|
|
|
|
uint64_t OffsetInVTable = 0;
|
|
|
|
CallingConv CC = CallingConv::Cdecl;
|
|
|
|
};
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
struct PointerType : public Type {
|
|
|
|
Type *clone(ArenaAllocator &Arena) const override;
|
2018-08-19 02:49:48 +08:00
|
|
|
void outputPre(OutputStream &OS) override;
|
|
|
|
void outputPost(OutputStream &OS) override;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-31 07:02:10 +08:00
|
|
|
PointerAffinity Affinity;
|
|
|
|
|
2018-07-27 03:56:09 +08:00
|
|
|
// Represents a type X in "a pointer to X", "a reference to X",
|
|
|
|
// "an array of X", or "a function returning X".
|
|
|
|
Type *Pointee = nullptr;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct MemberPointerType : public Type {
|
|
|
|
Type *clone(ArenaAllocator &Arena) const override;
|
2018-08-19 02:49:48 +08:00
|
|
|
void outputPre(OutputStream &OS) override;
|
|
|
|
void outputPost(OutputStream &OS) override;
|
2018-07-27 03:56:09 +08:00
|
|
|
|
|
|
|
Name *MemberName = nullptr;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// Represents a type X in "a pointer to X", "a reference to X",
|
|
|
|
// "an array of X", or "a function returning X".
|
|
|
|
Type *Pointee = nullptr;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct FunctionType : public Type {
|
2018-08-18 05:18:05 +08:00
|
|
|
struct ThisAdjustor {
|
|
|
|
uint32_t StaticOffset = 0;
|
|
|
|
int32_t VBPtrOffset = 0;
|
|
|
|
int32_t VBOffsetOffset = 0;
|
|
|
|
int32_t VtordispOffset = 0;
|
|
|
|
};
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
Type *clone(ArenaAllocator &Arena) const override;
|
2018-08-19 02:49:48 +08:00
|
|
|
void outputPre(OutputStream &OS) override;
|
|
|
|
void outputPost(OutputStream &OS) override;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-27 04:33:48 +08:00
|
|
|
// True if this FunctionType instance is the Pointee of a PointerType or
|
|
|
|
// MemberPointerType.
|
|
|
|
bool IsFunctionPointer = false;
|
2018-08-18 05:18:05 +08:00
|
|
|
bool IsThunk = false;
|
2018-07-27 04:33:48 +08:00
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
Type *ReturnType = nullptr;
|
|
|
|
// If this is a reference, the type of reference.
|
|
|
|
ReferenceKind RefKind;
|
|
|
|
|
|
|
|
CallingConv CallConvention;
|
|
|
|
FuncClass FunctionClass;
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
// Valid if IsThunk is true.
|
|
|
|
ThisAdjustor *ThisAdjust = nullptr;
|
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
FunctionParams Params;
|
2018-07-21 01:27:48 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
struct UdtType : public Type {
|
|
|
|
Type *clone(ArenaAllocator &Arena) const override;
|
2018-08-19 02:49:48 +08:00
|
|
|
void outputPre(OutputStream &OS) override;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
Name *UdtName = nullptr;
|
|
|
|
};
|
|
|
|
|
2018-08-10 22:31:04 +08:00
|
|
|
struct ArrayDimension {
|
|
|
|
uint64_t Dim = 0;
|
|
|
|
ArrayDimension *Next = nullptr;
|
|
|
|
};
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
struct ArrayType : public Type {
|
|
|
|
Type *clone(ArenaAllocator &Arena) const override;
|
2018-08-19 02:49:48 +08:00
|
|
|
void outputPre(OutputStream &OS) override;
|
|
|
|
void outputPost(OutputStream &OS) override;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// Either NextDimension or ElementType will be valid.
|
2018-08-10 22:31:04 +08:00
|
|
|
ArrayDimension *Dims = nullptr;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
Type *ElementType = nullptr;
|
|
|
|
};
|
|
|
|
|
|
|
|
} // namespace
|
|
|
|
|
2018-07-27 03:56:09 +08:00
|
|
|
static bool isMemberPointer(StringView MangledName) {
|
|
|
|
switch (MangledName.popFront()) {
|
2018-07-31 07:02:10 +08:00
|
|
|
case '$':
|
|
|
|
// This is probably an rvalue reference (e.g. $$Q), and you cannot have an
|
|
|
|
// rvalue reference to a member.
|
|
|
|
return false;
|
2018-07-27 03:56:09 +08:00
|
|
|
case 'A':
|
|
|
|
// 'A' indicates a reference, and you cannot have a reference to a member
|
2018-07-31 07:02:10 +08:00
|
|
|
// function or member.
|
2018-07-27 03:56:09 +08:00
|
|
|
return false;
|
|
|
|
case 'P':
|
|
|
|
case 'Q':
|
|
|
|
case 'R':
|
|
|
|
case 'S':
|
|
|
|
// These 4 values indicate some kind of pointer, but we still don't know
|
|
|
|
// what.
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
assert(false && "Ty is not a pointer type!");
|
|
|
|
}
|
|
|
|
|
|
|
|
// If it starts with a number, then 6 indicates a non-member function
|
|
|
|
// pointer, and 8 indicates a member function pointer.
|
|
|
|
if (startsWithDigit(MangledName)) {
|
|
|
|
assert(MangledName[0] == '6' || MangledName[0] == '8');
|
|
|
|
return (MangledName[0] == '8');
|
|
|
|
}
|
|
|
|
|
|
|
|
// Remove ext qualifiers since those can appear on either type and are
|
|
|
|
// therefore not indicative.
|
|
|
|
MangledName.consumeFront('E'); // 64-bit
|
|
|
|
MangledName.consumeFront('I'); // restrict
|
|
|
|
MangledName.consumeFront('F'); // unaligned
|
|
|
|
|
|
|
|
assert(!MangledName.empty());
|
|
|
|
|
|
|
|
// The next value should be either ABCD (non-member) or QRST (member).
|
|
|
|
switch (MangledName.front()) {
|
|
|
|
case 'A':
|
|
|
|
case 'B':
|
|
|
|
case 'C':
|
|
|
|
case 'D':
|
|
|
|
return false;
|
|
|
|
case 'Q':
|
|
|
|
case 'R':
|
|
|
|
case 'S':
|
|
|
|
case 'T':
|
|
|
|
return true;
|
|
|
|
default:
|
|
|
|
assert(false);
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
static void outputCallingConvention(OutputStream &OS, CallingConv CC) {
|
|
|
|
outputSpaceIfNecessary(OS);
|
|
|
|
|
|
|
|
switch (CC) {
|
|
|
|
case CallingConv::Cdecl:
|
|
|
|
OS << "__cdecl";
|
|
|
|
break;
|
|
|
|
case CallingConv::Fastcall:
|
|
|
|
OS << "__fastcall";
|
|
|
|
break;
|
|
|
|
case CallingConv::Pascal:
|
|
|
|
OS << "__pascal";
|
|
|
|
break;
|
|
|
|
case CallingConv::Regcall:
|
|
|
|
OS << "__regcall";
|
|
|
|
break;
|
|
|
|
case CallingConv::Stdcall:
|
|
|
|
OS << "__stdcall";
|
|
|
|
break;
|
|
|
|
case CallingConv::Thiscall:
|
|
|
|
OS << "__thiscall";
|
|
|
|
break;
|
|
|
|
case CallingConv::Eabi:
|
|
|
|
OS << "__eabi";
|
|
|
|
break;
|
|
|
|
case CallingConv::Vectorcall:
|
|
|
|
OS << "__vectorcall";
|
|
|
|
break;
|
|
|
|
case CallingConv::Clrcall:
|
|
|
|
OS << "__clrcall";
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
static bool startsWithLocalScopePattern(StringView S) {
|
|
|
|
if (!S.consumeFront('?'))
|
|
|
|
return false;
|
|
|
|
if (S.size() < 2)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
size_t End = S.find('?');
|
|
|
|
if (End == StringView::npos)
|
|
|
|
return false;
|
|
|
|
StringView Candidate = S.substr(0, End);
|
|
|
|
if (Candidate.empty())
|
|
|
|
return false;
|
|
|
|
|
|
|
|
// \?[0-9]\?
|
|
|
|
// ?@? is the discriminator 0.
|
|
|
|
if (Candidate.size() == 1)
|
|
|
|
return Candidate[0] == '@' || (Candidate[0] >= '0' && Candidate[0] <= '9');
|
|
|
|
|
|
|
|
// If it's not 0-9, then it's an encoded number terminated with an @
|
|
|
|
if (Candidate.back() != '@')
|
|
|
|
return false;
|
|
|
|
Candidate = Candidate.dropBack();
|
|
|
|
|
|
|
|
// An encoded number starts with B-P and all subsequent digits are in A-P.
|
|
|
|
// Note that the reason the first digit cannot be A is two fold. First, it
|
|
|
|
// would create an ambiguity with ?A which delimits the beginning of an
|
|
|
|
// anonymous namespace. Second, A represents 0, and you don't start a multi
|
|
|
|
// digit number with a leading 0. Presumably the anonymous namespace
|
|
|
|
// ambiguity is also why single digit encoded numbers use 0-9 rather than A-J.
|
|
|
|
if (Candidate[0] < 'B' || Candidate[0] > 'P')
|
|
|
|
return false;
|
|
|
|
Candidate = Candidate.dropFront();
|
|
|
|
while (!Candidate.empty()) {
|
|
|
|
if (Candidate[0] < 'A' || Candidate[0] > 'P')
|
|
|
|
return false;
|
|
|
|
Candidate = Candidate.dropFront();
|
|
|
|
}
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
// Write a function or template parameter list.
|
2018-08-19 02:49:48 +08:00
|
|
|
static void outputParameterList(OutputStream &OS,
|
|
|
|
const FunctionParams &Params) {
|
2018-08-01 01:16:44 +08:00
|
|
|
if (!Params.Current) {
|
|
|
|
OS << "void";
|
2018-07-27 04:20:10 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
const FunctionParams *Head = &Params;
|
2018-07-21 01:27:48 +08:00
|
|
|
while (Head) {
|
2018-08-19 02:49:48 +08:00
|
|
|
Type::outputPre(OS, *Head->Current);
|
|
|
|
Type::outputPost(OS, *Head->Current);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
Head = Head->Next;
|
|
|
|
|
|
|
|
if (Head)
|
|
|
|
OS << ", ";
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
static void outputStringLiteral(OutputStream &OS, const StringLiteral &Str) {
|
|
|
|
switch (Str.CharType) {
|
2018-08-17 00:17:36 +08:00
|
|
|
case PrimTy::Wchar:
|
|
|
|
OS << "const wchar_t * {L\"";
|
|
|
|
break;
|
|
|
|
case PrimTy::Char:
|
|
|
|
OS << "const char * {\"";
|
|
|
|
break;
|
|
|
|
case PrimTy::Char16:
|
|
|
|
OS << "const char16_t * {u\"";
|
|
|
|
break;
|
|
|
|
case PrimTy::Char32:
|
|
|
|
OS << "const char32_t * {U\"";
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
LLVM_BUILTIN_UNREACHABLE;
|
|
|
|
}
|
2018-08-18 00:14:05 +08:00
|
|
|
OS << Str.Str << "\"";
|
|
|
|
if (Str.IsTruncated)
|
2018-08-17 00:17:36 +08:00
|
|
|
OS << "...";
|
|
|
|
OS << "}";
|
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
static void outputName(OutputStream &OS, const Name *TheName, const Type *Ty);
|
2018-08-03 01:08:03 +08:00
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
static void outputParameterList(OutputStream &OS,
|
|
|
|
const TemplateParams &Params) {
|
2018-08-10 22:31:04 +08:00
|
|
|
if (Params.IsEmptyParameterPack) {
|
2018-08-01 01:16:44 +08:00
|
|
|
OS << "<>";
|
2018-07-21 01:27:48 +08:00
|
|
|
return;
|
2018-08-01 01:16:44 +08:00
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
OS << "<";
|
2018-08-01 01:16:44 +08:00
|
|
|
const TemplateParams *Head = &Params;
|
|
|
|
while (Head) {
|
|
|
|
// Type can be null if this is a template template parameter,
|
|
|
|
// and Name can be null if this is a simple type.
|
|
|
|
|
2018-08-10 22:31:04 +08:00
|
|
|
if (Head->IsIntegerLiteral) {
|
|
|
|
if (Head->IntegerLiteralIsNegative)
|
|
|
|
OS << '-';
|
|
|
|
OS << Head->IntegralValue;
|
|
|
|
} else if (Head->PointerToSymbol || Head->ReferenceToSymbol) {
|
2018-08-21 03:15:35 +08:00
|
|
|
if (Head->NullptrLiteral)
|
|
|
|
OS << "nullptr";
|
|
|
|
else {
|
|
|
|
if (Head->ThunkOffsetCount > 0)
|
|
|
|
OS << "{";
|
|
|
|
else if (Head->PointerToSymbol)
|
|
|
|
OS << "&";
|
|
|
|
if (Head->ParamType)
|
|
|
|
Type::outputPre(OS, *Head->ParamType);
|
|
|
|
outputName(OS, Head->ParamName, Head->ParamType);
|
|
|
|
if (Head->ParamType)
|
|
|
|
Type::outputPost(OS, *Head->ParamType);
|
|
|
|
if (Head->ThunkOffsetCount > 0) {
|
|
|
|
for (int I = 0; I < Head->ThunkOffsetCount; ++I) {
|
|
|
|
OS << ", " << Head->ThunkOffsets[I];
|
|
|
|
}
|
|
|
|
OS << "}";
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} else if (Head->DataMemberPointer) {
|
|
|
|
OS << "{" << Head->ThunkOffsets[0];
|
|
|
|
for (int I = 1; I < Head->ThunkOffsetCount; ++I)
|
|
|
|
OS << ", " << Head->ThunkOffsets[I];
|
|
|
|
OS << "}";
|
2018-08-01 01:16:44 +08:00
|
|
|
} else if (Head->ParamType) {
|
|
|
|
// simple type.
|
2018-08-19 02:49:48 +08:00
|
|
|
Type::outputPre(OS, *Head->ParamType);
|
|
|
|
Type::outputPost(OS, *Head->ParamType);
|
2018-08-01 01:16:44 +08:00
|
|
|
} else {
|
|
|
|
// Template alias.
|
2018-08-19 02:49:48 +08:00
|
|
|
outputName(OS, Head->ParamName, Head->ParamType);
|
2018-08-01 01:16:44 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
Head = Head->Next;
|
|
|
|
|
|
|
|
if (Head)
|
|
|
|
OS << ", ";
|
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
OS << ">";
|
|
|
|
}
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
static void outputQualifiers(OutputStream &OS, Qualifiers Q) {
|
|
|
|
if (Q & Q_Const) {
|
|
|
|
outputSpaceIfNecessary(OS);
|
|
|
|
OS << "const";
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Q & Q_Volatile) {
|
|
|
|
outputSpaceIfNecessary(OS);
|
|
|
|
OS << "volatile";
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Q & Q_Restrict) {
|
|
|
|
outputSpaceIfNecessary(OS);
|
|
|
|
OS << "__restrict";
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
static void outputNameComponent(OutputStream &OS, const Name &N) {
|
|
|
|
OS << N.Str;
|
2018-08-03 01:08:03 +08:00
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
if (N.IsTemplateInstantiation && N.TParams)
|
|
|
|
outputParameterList(OS, *N.TParams);
|
2018-08-03 01:08:03 +08:00
|
|
|
}
|
|
|
|
|
2018-08-21 03:15:35 +08:00
|
|
|
static const OperatorInfo *lastComponentAsOperator(const Name *TheName) {
|
|
|
|
if (!TheName)
|
|
|
|
return nullptr;
|
|
|
|
while (TheName->Next)
|
|
|
|
TheName = TheName->Next;
|
|
|
|
if (TheName->IsOperator)
|
|
|
|
return static_cast<const OperatorInfo *>(TheName);
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
static void outputName(OutputStream &OS, const Name *TheName, const Type *Ty) {
|
2018-07-21 01:27:48 +08:00
|
|
|
if (!TheName)
|
|
|
|
return;
|
|
|
|
|
|
|
|
outputSpaceIfNecessary(OS);
|
|
|
|
|
2018-08-21 03:15:35 +08:00
|
|
|
const OperatorInfo *Operator = lastComponentAsOperator(TheName);
|
|
|
|
const VirtualMemberPtrThunk *Thunk = nullptr;
|
2018-08-21 07:59:21 +08:00
|
|
|
bool PrintLastScopeSeparator = true;
|
2018-08-21 03:15:35 +08:00
|
|
|
if (Operator) {
|
|
|
|
if (Operator->Info->Operator == OperatorTy::Vcall) {
|
|
|
|
Thunk = static_cast<const VirtualMemberPtrThunk *>(Operator);
|
|
|
|
OS << "[thunk]: ";
|
|
|
|
outputCallingConvention(OS, Thunk->CC);
|
|
|
|
OS << " ";
|
2018-08-21 07:59:21 +08:00
|
|
|
} else if (Operator->Info->Operator == OperatorTy::DynamicInitializer) {
|
|
|
|
OS << "`dynamic initializer for '";
|
|
|
|
PrintLastScopeSeparator = false;
|
|
|
|
} else if (Operator->Info->Operator ==
|
|
|
|
OperatorTy::DynamicAtexitDestructor) {
|
|
|
|
OS << "`dynamic atexit destructor for '";
|
|
|
|
PrintLastScopeSeparator = false;
|
2018-08-21 03:15:35 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-07-29 06:10:42 +08:00
|
|
|
const Name *Previous = nullptr;
|
2018-07-21 01:27:48 +08:00
|
|
|
// Print out namespaces or outer class BackReferences.
|
|
|
|
for (; TheName->Next; TheName = TheName->Next) {
|
2018-07-29 06:10:42 +08:00
|
|
|
Previous = TheName;
|
2018-08-19 02:49:48 +08:00
|
|
|
outputNameComponent(OS, *TheName);
|
2018-08-21 07:59:21 +08:00
|
|
|
if (TheName->Next != Operator || PrintLastScopeSeparator)
|
|
|
|
OS << "::";
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// Print out a regular name.
|
2018-08-02 02:32:47 +08:00
|
|
|
if (!TheName->IsOperator) {
|
2018-08-19 02:49:48 +08:00
|
|
|
outputNameComponent(OS, *TheName);
|
2018-07-21 01:27:48 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
// Print out ctor or dtor.
|
2018-08-21 03:15:35 +08:00
|
|
|
switch (Operator->Info->Operator) {
|
2018-08-18 00:14:05 +08:00
|
|
|
case OperatorTy::Dtor:
|
2018-07-29 06:10:42 +08:00
|
|
|
OS << "~";
|
2018-08-18 00:14:05 +08:00
|
|
|
LLVM_FALLTHROUGH;
|
|
|
|
case OperatorTy::Ctor:
|
2018-08-19 02:49:48 +08:00
|
|
|
outputNameComponent(OS, *Previous);
|
2018-08-18 00:14:05 +08:00
|
|
|
break;
|
|
|
|
case OperatorTy::Conversion:
|
2018-08-10 23:04:56 +08:00
|
|
|
OS << "operator";
|
|
|
|
if (TheName->IsTemplateInstantiation && TheName->TParams)
|
2018-08-19 02:49:48 +08:00
|
|
|
outputParameterList(OS, *TheName->TParams);
|
2018-08-10 23:04:56 +08:00
|
|
|
OS << " ";
|
|
|
|
if (Ty) {
|
|
|
|
const FunctionType *FTy = static_cast<const FunctionType *>(Ty);
|
2018-08-19 02:49:48 +08:00
|
|
|
Type::outputPre(OS, *FTy->ReturnType);
|
|
|
|
Type::outputPost(OS, *FTy->ReturnType);
|
2018-08-10 23:04:56 +08:00
|
|
|
} else {
|
|
|
|
OS << "<conversion>";
|
|
|
|
}
|
2018-08-18 00:14:05 +08:00
|
|
|
break;
|
|
|
|
case OperatorTy::LiteralOperator:
|
2018-08-21 03:15:35 +08:00
|
|
|
OS << Operator->Info->Name;
|
2018-08-19 02:49:48 +08:00
|
|
|
outputNameComponent(OS, *TheName);
|
2018-08-18 00:14:05 +08:00
|
|
|
break;
|
2018-08-18 05:18:05 +08:00
|
|
|
case OperatorTy::RttiBaseClassDescriptor: {
|
|
|
|
const RttiBaseClassDescriptor &BCD =
|
2018-08-21 03:15:35 +08:00
|
|
|
static_cast<const RttiBaseClassDescriptor &>(*Operator);
|
|
|
|
OS << "`" << Operator->Info->Name << " at (";
|
2018-08-18 05:18:05 +08:00
|
|
|
OS << BCD.NVOffset << ", " << BCD.VBPtrOffset << ", " << BCD.VBTableOffset
|
|
|
|
<< ", " << BCD.Flags;
|
|
|
|
OS << ")'";
|
|
|
|
break;
|
|
|
|
}
|
2018-08-21 03:15:35 +08:00
|
|
|
case OperatorTy::Vcall: {
|
|
|
|
OS << "`vcall'{";
|
|
|
|
OS << Thunk->OffsetInVTable << ", {flat}}";
|
|
|
|
break;
|
|
|
|
}
|
2018-08-21 07:59:21 +08:00
|
|
|
case OperatorTy::DynamicInitializer:
|
|
|
|
case OperatorTy::DynamicAtexitDestructor:
|
|
|
|
OS << "''";
|
|
|
|
break;
|
2018-08-21 03:15:35 +08:00
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
case OperatorTy::LocalStaticGuard: {
|
|
|
|
const LocalStaticGuardVariable &LSG =
|
2018-08-21 03:15:35 +08:00
|
|
|
static_cast<const LocalStaticGuardVariable &>(*Operator);
|
|
|
|
OS << Operator->Info->Name;
|
2018-08-18 05:18:05 +08:00
|
|
|
if (LSG.ScopeIndex > 0)
|
|
|
|
OS << "{" << LSG.ScopeIndex << "}";
|
|
|
|
break;
|
|
|
|
}
|
2018-08-18 00:14:05 +08:00
|
|
|
default:
|
2018-08-21 03:15:35 +08:00
|
|
|
OS << Operator->Info->Name;
|
|
|
|
if (Operator->IsTemplateInstantiation)
|
|
|
|
outputParameterList(OS, *Operator->TParams);
|
2018-08-18 00:14:05 +08:00
|
|
|
break;
|
2018-08-10 23:04:56 +08:00
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
static void outputSpecialOperator(OutputStream &OS, const Name *OuterName) {
|
2018-08-18 05:18:05 +08:00
|
|
|
assert(OuterName);
|
|
|
|
// The last component should be an operator.
|
2018-08-21 03:15:35 +08:00
|
|
|
const OperatorInfo *Operator = lastComponentAsOperator(OuterName);
|
2018-08-18 05:18:05 +08:00
|
|
|
|
2018-08-21 03:15:35 +08:00
|
|
|
assert(Operator->IsOperator);
|
|
|
|
const OperatorInfo &Oper = static_cast<const OperatorInfo &>(*Operator);
|
2018-08-18 05:18:05 +08:00
|
|
|
switch (Oper.Info->Operator) {
|
|
|
|
case OperatorTy::StringLiteral: {
|
|
|
|
const StringLiteral &SL = static_cast<const StringLiteral &>(Oper);
|
|
|
|
outputStringLiteral(OS, SL);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
case OperatorTy::Vcall: {
|
|
|
|
const VirtualMemberPtrThunk &Thunk =
|
|
|
|
static_cast<const VirtualMemberPtrThunk &>(Oper);
|
|
|
|
OS << "[thunk]: ";
|
|
|
|
outputCallingConvention(OS, Thunk.CC);
|
|
|
|
OS << " ";
|
|
|
|
// Print out namespaces or outer class BackReferences.
|
|
|
|
const Name *N = OuterName;
|
|
|
|
for (; N->Next; N = N->Next) {
|
2018-08-19 02:49:48 +08:00
|
|
|
outputNameComponent(OS, *N);
|
2018-08-18 05:18:05 +08:00
|
|
|
OS << "::";
|
|
|
|
}
|
|
|
|
OS << "`vcall'{";
|
|
|
|
OS << Thunk.OffsetInVTable << ", {flat}}";
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
default:
|
|
|
|
// There are no other special operator categories.
|
|
|
|
LLVM_BUILTIN_UNREACHABLE;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
namespace {
|
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
bool Name::isStringLiteralOperatorInfo() const {
|
|
|
|
if (!IsOperator)
|
|
|
|
return false;
|
|
|
|
const OperatorInfo &O = static_cast<const OperatorInfo &>(*this);
|
|
|
|
return O.Info->Operator == OperatorTy::StringLiteral;
|
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
Type *Type::clone(ArenaAllocator &Arena) const {
|
2018-07-21 02:35:06 +08:00
|
|
|
return Arena.alloc<Type>(*this);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// Write the "first half" of a given type.
|
2018-08-19 02:49:48 +08:00
|
|
|
void Type::outputPre(OutputStream &OS, Type &Ty) {
|
2018-07-21 01:27:48 +08:00
|
|
|
// Function types require custom handling of const and static so we
|
|
|
|
// handle them separately. All other types use the same decoration
|
|
|
|
// for these modifiers, so handle them here in common code.
|
|
|
|
if (Ty.Prim == PrimTy::Function) {
|
2018-08-19 02:49:48 +08:00
|
|
|
Ty.outputPre(OS);
|
2018-07-21 01:27:48 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
switch (Ty.Storage) {
|
|
|
|
case StorageClass::PrivateStatic:
|
|
|
|
case StorageClass::PublicStatic:
|
|
|
|
case StorageClass::ProtectedStatic:
|
|
|
|
OS << "static ";
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
2018-08-19 02:49:48 +08:00
|
|
|
Ty.outputPre(OS);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
outputQualifiers(OS, Ty.Quals);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// Write the "second half" of a given type.
|
2018-08-19 02:49:48 +08:00
|
|
|
void Type::outputPost(OutputStream &OS, Type &Ty) { Ty.outputPost(OS); }
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
void Type::outputPre(OutputStream &OS) {
|
2018-07-21 01:27:48 +08:00
|
|
|
switch (Prim) {
|
|
|
|
case PrimTy::Void:
|
|
|
|
OS << "void";
|
|
|
|
break;
|
|
|
|
case PrimTy::Bool:
|
|
|
|
OS << "bool";
|
|
|
|
break;
|
|
|
|
case PrimTy::Char:
|
|
|
|
OS << "char";
|
|
|
|
break;
|
|
|
|
case PrimTy::Schar:
|
|
|
|
OS << "signed char";
|
|
|
|
break;
|
|
|
|
case PrimTy::Uchar:
|
|
|
|
OS << "unsigned char";
|
|
|
|
break;
|
2018-07-31 07:02:10 +08:00
|
|
|
case PrimTy::Char16:
|
|
|
|
OS << "char16_t";
|
|
|
|
break;
|
|
|
|
case PrimTy::Char32:
|
|
|
|
OS << "char32_t";
|
|
|
|
break;
|
2018-07-21 01:27:48 +08:00
|
|
|
case PrimTy::Short:
|
|
|
|
OS << "short";
|
|
|
|
break;
|
|
|
|
case PrimTy::Ushort:
|
|
|
|
OS << "unsigned short";
|
|
|
|
break;
|
|
|
|
case PrimTy::Int:
|
|
|
|
OS << "int";
|
|
|
|
break;
|
|
|
|
case PrimTy::Uint:
|
|
|
|
OS << "unsigned int";
|
|
|
|
break;
|
|
|
|
case PrimTy::Long:
|
|
|
|
OS << "long";
|
|
|
|
break;
|
|
|
|
case PrimTy::Ulong:
|
|
|
|
OS << "unsigned long";
|
|
|
|
break;
|
|
|
|
case PrimTy::Int64:
|
|
|
|
OS << "__int64";
|
|
|
|
break;
|
|
|
|
case PrimTy::Uint64:
|
|
|
|
OS << "unsigned __int64";
|
|
|
|
break;
|
|
|
|
case PrimTy::Wchar:
|
|
|
|
OS << "wchar_t";
|
|
|
|
break;
|
|
|
|
case PrimTy::Float:
|
|
|
|
OS << "float";
|
|
|
|
break;
|
|
|
|
case PrimTy::Double:
|
|
|
|
OS << "double";
|
|
|
|
break;
|
|
|
|
case PrimTy::Ldouble:
|
|
|
|
OS << "long double";
|
|
|
|
break;
|
2018-07-31 07:02:10 +08:00
|
|
|
case PrimTy::Nullptr:
|
|
|
|
OS << "std::nullptr_t";
|
|
|
|
break;
|
2018-08-18 00:14:05 +08:00
|
|
|
case PrimTy::Vbtable:
|
|
|
|
case PrimTy::Vftable:
|
|
|
|
break;
|
2018-07-21 01:27:48 +08:00
|
|
|
default:
|
|
|
|
assert(false && "Invalid primitive type!");
|
|
|
|
}
|
|
|
|
}
|
2018-08-19 02:49:48 +08:00
|
|
|
void Type::outputPost(OutputStream &OS) {}
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
Type *PointerType::clone(ArenaAllocator &Arena) const {
|
2018-07-21 02:35:06 +08:00
|
|
|
return Arena.alloc<PointerType>(*this);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-07-27 04:33:48 +08:00
|
|
|
static void outputPointerIndicator(OutputStream &OS, PointerAffinity Affinity,
|
2018-08-19 02:49:48 +08:00
|
|
|
const Name *MemberName,
|
|
|
|
const Type *Pointee) {
|
2018-07-21 01:27:48 +08:00
|
|
|
// "[]" and "()" (for function parameters) take precedence over "*",
|
|
|
|
// so "int *x(int)" means "x is a function returning int *". We need
|
|
|
|
// parentheses to supercede the default precedence. (e.g. we want to
|
|
|
|
// emit something like "int (*x)(int)".)
|
2018-07-27 04:33:48 +08:00
|
|
|
if (Pointee->Prim == PrimTy::Function || Pointee->Prim == PrimTy::Array) {
|
2018-07-21 01:27:48 +08:00
|
|
|
OS << "(";
|
2018-07-27 04:33:48 +08:00
|
|
|
if (Pointee->Prim == PrimTy::Function) {
|
|
|
|
const FunctionType *FTy = static_cast<const FunctionType *>(Pointee);
|
|
|
|
assert(FTy->IsFunctionPointer);
|
|
|
|
outputCallingConvention(OS, FTy->CallConvention);
|
|
|
|
OS << " ";
|
|
|
|
}
|
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-27 04:33:48 +08:00
|
|
|
if (MemberName) {
|
2018-08-19 02:49:48 +08:00
|
|
|
outputName(OS, MemberName, Pointee);
|
2018-07-27 04:33:48 +08:00
|
|
|
OS << "::";
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Affinity == PointerAffinity::Pointer)
|
2018-07-21 01:27:48 +08:00
|
|
|
OS << "*";
|
2018-07-31 07:02:10 +08:00
|
|
|
else if (Affinity == PointerAffinity::Reference)
|
2018-07-21 01:27:48 +08:00
|
|
|
OS << "&";
|
2018-07-31 07:02:10 +08:00
|
|
|
else
|
|
|
|
OS << "&&";
|
2018-07-27 04:33:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
void PointerType::outputPre(OutputStream &OS) {
|
|
|
|
Type::outputPre(OS, *Pointee);
|
2018-07-27 04:33:48 +08:00
|
|
|
|
|
|
|
outputSpaceIfNecessary(OS);
|
|
|
|
|
|
|
|
if (Quals & Q_Unaligned)
|
|
|
|
OS << "__unaligned ";
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
outputPointerIndicator(OS, Affinity, nullptr, Pointee);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-21 02:07:33 +08:00
|
|
|
// FIXME: We should output this, but it requires updating lots of tests.
|
2018-07-21 01:27:48 +08:00
|
|
|
// if (Ty.Quals & Q_Pointer64)
|
|
|
|
// OS << " __ptr64";
|
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
void PointerType::outputPost(OutputStream &OS) {
|
2018-07-21 01:27:48 +08:00
|
|
|
if (Pointee->Prim == PrimTy::Function || Pointee->Prim == PrimTy::Array)
|
|
|
|
OS << ")";
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
Type::outputPost(OS, *Pointee);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-07-27 03:56:09 +08:00
|
|
|
Type *MemberPointerType::clone(ArenaAllocator &Arena) const {
|
|
|
|
return Arena.alloc<MemberPointerType>(*this);
|
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
void MemberPointerType::outputPre(OutputStream &OS) {
|
|
|
|
Type::outputPre(OS, *Pointee);
|
2018-07-27 03:56:09 +08:00
|
|
|
|
|
|
|
outputSpaceIfNecessary(OS);
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
outputPointerIndicator(OS, PointerAffinity::Pointer, MemberName, Pointee);
|
2018-07-27 03:56:09 +08:00
|
|
|
|
|
|
|
// FIXME: We should output this, but it requires updating lots of tests.
|
|
|
|
// if (Ty.Quals & Q_Pointer64)
|
|
|
|
// OS << " __ptr64";
|
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
void MemberPointerType::outputPost(OutputStream &OS) {
|
2018-07-27 03:56:09 +08:00
|
|
|
if (Pointee->Prim == PrimTy::Function || Pointee->Prim == PrimTy::Array)
|
|
|
|
OS << ")";
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
Type::outputPost(OS, *Pointee);
|
2018-07-27 03:56:09 +08:00
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
Type *FunctionType::clone(ArenaAllocator &Arena) const {
|
2018-07-21 02:35:06 +08:00
|
|
|
return Arena.alloc<FunctionType>(*this);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
void FunctionType::outputPre(OutputStream &OS) {
|
2018-08-18 05:18:05 +08:00
|
|
|
if ((FunctionClass & StaticThisAdjust) || (FunctionClass & VirtualThisAdjust))
|
|
|
|
OS << "[thunk]: ";
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
if (!(FunctionClass & Global)) {
|
|
|
|
if (FunctionClass & Static)
|
|
|
|
OS << "static ";
|
|
|
|
}
|
2018-08-18 00:14:05 +08:00
|
|
|
if (FunctionClass & ExternC)
|
2018-08-11 05:09:05 +08:00
|
|
|
OS << "extern \"C\" ";
|
2018-08-18 00:14:05 +08:00
|
|
|
|
|
|
|
if (FunctionClass & Virtual)
|
|
|
|
OS << "virtual ";
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-27 04:20:10 +08:00
|
|
|
if (ReturnType) {
|
2018-08-19 02:49:48 +08:00
|
|
|
Type::outputPre(OS, *ReturnType);
|
2018-07-27 04:20:10 +08:00
|
|
|
OS << " ";
|
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-27 04:33:48 +08:00
|
|
|
// Function pointers print the calling convention as void (__cdecl *)(params)
|
|
|
|
// rather than void __cdecl (*)(params). So we need to let the PointerType
|
|
|
|
// class handle this.
|
|
|
|
if (!IsFunctionPointer)
|
|
|
|
outputCallingConvention(OS, CallConvention);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
void FunctionType::outputPost(OutputStream &OS) {
|
2018-08-11 05:09:05 +08:00
|
|
|
// extern "C" functions don't have a prototype.
|
|
|
|
if (FunctionClass & NoPrototype)
|
|
|
|
return;
|
|
|
|
|
2018-08-18 05:32:07 +08:00
|
|
|
if (FunctionClass & StaticThisAdjust) {
|
|
|
|
OS << "`adjustor{" << ThisAdjust->StaticOffset << "}'";
|
|
|
|
} else if (FunctionClass & VirtualThisAdjust) {
|
|
|
|
if (FunctionClass & VirtualThisAdjustEx) {
|
|
|
|
OS << "`vtordispex{" << ThisAdjust->VBPtrOffset << ", "
|
|
|
|
<< ThisAdjust->VBOffsetOffset << ", " << ThisAdjust->VtordispOffset
|
|
|
|
<< ", " << ThisAdjust->StaticOffset << "}'";
|
|
|
|
} else {
|
|
|
|
OS << "`vtordisp{" << ThisAdjust->VtordispOffset << ", "
|
|
|
|
<< ThisAdjust->StaticOffset << "}'";
|
|
|
|
}
|
2018-08-18 05:18:05 +08:00
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
OS << "(";
|
2018-08-19 02:49:48 +08:00
|
|
|
outputParameterList(OS, Params);
|
2018-07-21 01:27:48 +08:00
|
|
|
OS << ")";
|
|
|
|
if (Quals & Q_Const)
|
|
|
|
OS << " const";
|
|
|
|
if (Quals & Q_Volatile)
|
|
|
|
OS << " volatile";
|
2018-07-31 07:02:10 +08:00
|
|
|
if (Quals & Q_Restrict)
|
|
|
|
OS << " __restrict";
|
|
|
|
if (Quals & Q_Unaligned)
|
|
|
|
OS << " __unaligned";
|
|
|
|
|
|
|
|
if (RefKind == ReferenceKind::LValueRef)
|
|
|
|
OS << " &";
|
|
|
|
else if (RefKind == ReferenceKind::RValueRef)
|
|
|
|
OS << " &&";
|
2018-07-27 04:20:10 +08:00
|
|
|
|
|
|
|
if (ReturnType)
|
2018-08-19 02:49:48 +08:00
|
|
|
Type::outputPost(OS, *ReturnType);
|
2018-07-21 01:27:48 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
Type *UdtType::clone(ArenaAllocator &Arena) const {
|
2018-07-21 02:35:06 +08:00
|
|
|
return Arena.alloc<UdtType>(*this);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
void UdtType::outputPre(OutputStream &OS) {
|
2018-07-21 01:27:48 +08:00
|
|
|
switch (Prim) {
|
|
|
|
case PrimTy::Class:
|
|
|
|
OS << "class ";
|
|
|
|
break;
|
|
|
|
case PrimTy::Struct:
|
|
|
|
OS << "struct ";
|
|
|
|
break;
|
|
|
|
case PrimTy::Union:
|
|
|
|
OS << "union ";
|
|
|
|
break;
|
|
|
|
case PrimTy::Enum:
|
|
|
|
OS << "enum ";
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
assert(false && "Not a udt type!");
|
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
outputName(OS, UdtName, this);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
Type *ArrayType::clone(ArenaAllocator &Arena) const {
|
2018-07-21 02:35:06 +08:00
|
|
|
return Arena.alloc<ArrayType>(*this);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
void ArrayType::outputPre(OutputStream &OS) {
|
|
|
|
Type::outputPre(OS, *ElementType);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
void ArrayType::outputPost(OutputStream &OS) {
|
2018-08-10 22:31:04 +08:00
|
|
|
ArrayDimension *D = Dims;
|
|
|
|
while (D) {
|
|
|
|
OS << "[";
|
|
|
|
if (D->Dim > 0)
|
|
|
|
OS << D->Dim;
|
|
|
|
OS << "]";
|
|
|
|
D = D->Next;
|
|
|
|
}
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
Type::outputPost(OS, *ElementType);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
struct Symbol {
|
2018-08-02 02:32:47 +08:00
|
|
|
SymbolCategory Category;
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
Qualifiers SymbolQuals = Q_None;
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *SymbolName = nullptr;
|
|
|
|
Type *SymbolType = nullptr;
|
|
|
|
};
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
} // namespace
|
|
|
|
|
|
|
|
namespace {
|
|
|
|
|
2018-08-09 01:17:04 +08:00
|
|
|
struct BackrefContext {
|
|
|
|
static constexpr size_t Max = 10;
|
|
|
|
|
|
|
|
Type *FunctionParams[Max];
|
|
|
|
size_t FunctionParamCount = 0;
|
|
|
|
|
|
|
|
// The first 10 BackReferences in a mangled name can be back-referenced by
|
|
|
|
// special name @[0-9]. This is a storage for the first 10 BackReferences.
|
|
|
|
StringView Names[Max];
|
|
|
|
size_t NamesCount = 0;
|
|
|
|
};
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
// Demangler class takes the main role in demangling symbols.
|
|
|
|
// It has a set of functions to parse mangled symbols into Type instances.
|
|
|
|
// It also has a set of functions to cnovert Type instances to strings.
|
2018-08-19 02:49:48 +08:00
|
|
|
class Demangler {
|
2018-07-21 01:27:48 +08:00
|
|
|
public:
|
2018-07-30 00:38:02 +08:00
|
|
|
Demangler() = default;
|
2018-08-03 01:18:01 +08:00
|
|
|
virtual ~Demangler() = default;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// You are supposed to call parse() first and then check if error is true. If
|
|
|
|
// it is false, call output() to write the formatted name to the given stream.
|
2018-07-30 00:38:02 +08:00
|
|
|
Symbol *parse(StringView &MangledName);
|
2018-08-18 05:18:05 +08:00
|
|
|
Symbol *parseOperator(StringView &MangledName);
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
void output(const Symbol *S, OutputStream &OS);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// True if an error occurred.
|
|
|
|
bool Error = false;
|
|
|
|
|
2018-08-02 02:33:04 +08:00
|
|
|
void dumpBackReferences();
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
private:
|
2018-08-18 05:18:05 +08:00
|
|
|
std::pair<SymbolCategory, Type *>
|
|
|
|
demangleSymbolCategoryAndType(StringView &MangledName);
|
|
|
|
|
|
|
|
Type *demangleVariableEncoding(StringView &MangledName, StorageClass SC);
|
2018-07-30 00:38:02 +08:00
|
|
|
Type *demangleFunctionEncoding(StringView &MangledName);
|
2018-08-18 05:18:05 +08:00
|
|
|
uint64_t demangleThunkThisAdjust(StringView &MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Qualifiers demanglePointerExtQualifiers(StringView &MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// Parser functions. This is a recursive-descent parser.
|
2018-07-30 00:38:02 +08:00
|
|
|
Type *demangleType(StringView &MangledName, QualifierMangleMode QMM);
|
|
|
|
Type *demangleBasicType(StringView &MangledName);
|
|
|
|
UdtType *demangleClassType(StringView &MangledName);
|
|
|
|
PointerType *demanglePointerType(StringView &MangledName);
|
|
|
|
MemberPointerType *demangleMemberPointerType(StringView &MangledName);
|
|
|
|
FunctionType *demangleFunctionType(StringView &MangledName, bool HasThisQuals,
|
|
|
|
bool IsFunctionPointer);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
ArrayType *demangleArrayType(StringView &MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
TemplateParams *demangleTemplateParameterList(StringView &MangledName);
|
|
|
|
FunctionParams demangleFunctionParameterList(StringView &MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-10 22:31:04 +08:00
|
|
|
std::pair<uint64_t, bool> demangleNumber(StringView &MangledName);
|
2018-08-18 05:18:05 +08:00
|
|
|
uint64_t demangleUnsigned(StringView &MangledName);
|
|
|
|
int64_t demangleSigned(StringView &MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
void memorizeString(StringView s);
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
|
|
|
|
/// Allocate a copy of \p Borrowed into memory that we own.
|
|
|
|
StringView copyString(StringView Borrowed);
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *demangleFullyQualifiedTypeName(StringView &MangledName);
|
|
|
|
Name *demangleFullyQualifiedSymbolName(StringView &MangledName);
|
2018-07-29 06:10:42 +08:00
|
|
|
|
2018-08-02 02:32:47 +08:00
|
|
|
Name *demangleUnqualifiedTypeName(StringView &MangledName, bool Memorize);
|
2018-08-08 08:43:31 +08:00
|
|
|
Name *demangleUnqualifiedSymbolName(StringView &MangledName,
|
|
|
|
NameBackrefBehavior NBB);
|
2018-07-29 06:10:42 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *demangleNameScopeChain(StringView &MangledName, Name *UnqualifiedName);
|
|
|
|
Name *demangleNameScopePiece(StringView &MangledName);
|
2018-07-29 06:10:42 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *demangleBackRefName(StringView &MangledName);
|
2018-08-08 08:43:31 +08:00
|
|
|
Name *demangleTemplateInstantiationName(StringView &MangledName,
|
|
|
|
NameBackrefBehavior NBB);
|
2018-08-18 05:18:05 +08:00
|
|
|
std::pair<OperatorTy, Name *> demangleOperatorName(StringView &MangledName,
|
|
|
|
bool FullyQualified);
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *demangleSimpleName(StringView &MangledName, bool Memorize);
|
|
|
|
Name *demangleAnonymousNamespaceName(StringView &MangledName);
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
Name *demangleLocallyScopedNamePiece(StringView &MangledName);
|
2018-08-18 00:14:05 +08:00
|
|
|
StringLiteral *demangleStringLiteral(StringView &MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-31 07:02:10 +08:00
|
|
|
StringView demangleSimpleString(StringView &MangledName, bool Memorize);
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
FuncClass demangleFunctionClass(StringView &MangledName);
|
|
|
|
CallingConv demangleCallingConvention(StringView &MangledName);
|
|
|
|
StorageClass demangleVariableStorageClass(StringView &MangledName);
|
|
|
|
ReferenceKind demangleReferenceKind(StringView &MangledName);
|
|
|
|
void demangleThrowSpecification(StringView &MangledName);
|
2018-08-17 00:17:36 +08:00
|
|
|
wchar_t demangleWcharLiteral(StringView &MangledName);
|
|
|
|
uint8_t demangleCharLiteral(StringView &MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
std::pair<Qualifiers, bool> demangleQualifiers(StringView &MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// Memory allocator.
|
|
|
|
ArenaAllocator Arena;
|
|
|
|
|
2018-07-27 06:13:39 +08:00
|
|
|
// A single type uses one global back-ref table for all function params.
|
|
|
|
// This means back-refs can even go "into" other types. Examples:
|
|
|
|
//
|
|
|
|
// // Second int* is a back-ref to first.
|
|
|
|
// void foo(int *, int*);
|
|
|
|
//
|
|
|
|
// // Second int* is not a back-ref to first (first is not a function param).
|
|
|
|
// int* foo(int*);
|
|
|
|
//
|
|
|
|
// // Second int* is a back-ref to first (ALL function types share the same
|
|
|
|
// // back-ref map.
|
|
|
|
// using F = void(*)(int*);
|
|
|
|
// F G(int *);
|
2018-08-09 01:17:04 +08:00
|
|
|
BackrefContext Backrefs;
|
2018-07-21 01:27:48 +08:00
|
|
|
};
|
|
|
|
} // namespace
|
|
|
|
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
StringView Demangler::copyString(StringView Borrowed) {
|
|
|
|
char *Stable = Arena.allocUnalignedBuffer(Borrowed.size() + 1);
|
|
|
|
std::strcpy(Stable, Borrowed.begin());
|
|
|
|
|
|
|
|
return {Stable, Borrowed.size()};
|
|
|
|
}
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
Symbol *Demangler::parseOperator(StringView &MangledName) {
|
2018-07-30 00:38:02 +08:00
|
|
|
Symbol *S = Arena.alloc<Symbol>();
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
bool IsMember = false;
|
|
|
|
OperatorTy OTy;
|
|
|
|
std::tie(OTy, S->SymbolName) = demangleOperatorName(MangledName, true);
|
|
|
|
switch (OTy) {
|
|
|
|
case OperatorTy::StringLiteral:
|
|
|
|
S->Category = SymbolCategory::SpecialOperator;
|
|
|
|
break;
|
2018-08-21 03:15:35 +08:00
|
|
|
case OperatorTy::Vcall:
|
|
|
|
S->Category = SymbolCategory::UnnamedFunction;
|
|
|
|
break;
|
|
|
|
case OperatorTy::LocalStaticGuard:
|
|
|
|
S->Category = SymbolCategory::UnnamedVariable;
|
|
|
|
break;
|
2018-08-18 05:18:05 +08:00
|
|
|
case OperatorTy::Vftable: // Foo@@6B@
|
|
|
|
case OperatorTy::LocalVftable: // Foo@@6B@
|
|
|
|
case OperatorTy::RttiCompleteObjLocator: // Foo@@6B@
|
|
|
|
case OperatorTy::Vbtable: // Foo@@7B@
|
|
|
|
S->Category = SymbolCategory::UnnamedVariable;
|
|
|
|
switch (MangledName.popFront()) {
|
|
|
|
case '6':
|
|
|
|
case '7':
|
|
|
|
std::tie(S->SymbolQuals, IsMember) = demangleQualifiers(MangledName);
|
|
|
|
if (!MangledName.consumeFront('@'))
|
|
|
|
Error = true;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
Error = true;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case OperatorTy::RttiTypeDescriptor: // <type>@@8
|
|
|
|
S->Category = SymbolCategory::UnnamedVariable;
|
|
|
|
S->SymbolType = demangleType(MangledName, QualifierMangleMode::Result);
|
|
|
|
if (Error)
|
|
|
|
break;
|
|
|
|
if (!MangledName.consumeFront("@8"))
|
|
|
|
Error = true;
|
|
|
|
if (!MangledName.empty())
|
|
|
|
Error = true;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
if (!Error)
|
|
|
|
std::tie(S->Category, S->SymbolType) =
|
|
|
|
demangleSymbolCategoryAndType(MangledName);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return (Error) ? nullptr : S;
|
|
|
|
}
|
|
|
|
|
|
|
|
std::pair<SymbolCategory, Type *>
|
|
|
|
Demangler::demangleSymbolCategoryAndType(StringView &MangledName) {
|
|
|
|
// Read a variable.
|
|
|
|
switch (MangledName.front()) {
|
|
|
|
case '0':
|
|
|
|
case '1':
|
|
|
|
case '2':
|
|
|
|
case '3':
|
|
|
|
case '4':
|
|
|
|
return std::make_pair(
|
|
|
|
SymbolCategory::NamedVariable,
|
|
|
|
demangleVariableEncoding(MangledName,
|
|
|
|
demangleVariableStorageClass(MangledName)));
|
|
|
|
case '8':
|
|
|
|
MangledName.consumeFront('8');
|
|
|
|
return std::pair<SymbolCategory, Type *>(SymbolCategory::UnnamedVariable,
|
|
|
|
nullptr);
|
|
|
|
}
|
|
|
|
return std::make_pair(SymbolCategory::NamedFunction,
|
|
|
|
demangleFunctionEncoding(MangledName));
|
|
|
|
}
|
|
|
|
|
|
|
|
// Parser entry point.
|
|
|
|
Symbol *Demangler::parse(StringView &MangledName) {
|
2018-08-17 00:17:17 +08:00
|
|
|
// We can't demangle MD5 names, just output them as-is.
|
2018-08-18 05:18:05 +08:00
|
|
|
// Also, MSVC-style mangled symbols must start with '?'.
|
|
|
|
if (MangledName.startsWith("??@") || !MangledName.startsWith('?')) {
|
|
|
|
Symbol *S = Arena.alloc<Symbol>();
|
2018-08-17 00:17:17 +08:00
|
|
|
S->Category = SymbolCategory::Unknown;
|
|
|
|
S->SymbolName = Arena.alloc<Name>();
|
|
|
|
S->SymbolName->Str = MangledName;
|
2018-08-17 00:17:36 +08:00
|
|
|
S->SymbolType = nullptr;
|
2018-08-17 00:17:17 +08:00
|
|
|
MangledName = StringView();
|
|
|
|
return S;
|
|
|
|
}
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
MangledName.consumeFront('?');
|
|
|
|
|
|
|
|
// ?$ is a template instantiation, but all other names that start with ? are
|
|
|
|
// operators / special names.
|
|
|
|
if (MangledName.startsWith('?') && !MangledName.startsWith("?$"))
|
|
|
|
return parseOperator(MangledName);
|
2018-08-17 00:17:36 +08:00
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
Symbol *S = Arena.alloc<Symbol>();
|
|
|
|
// What follows is a main symbol name. This may include namespaces or class
|
|
|
|
// back references.
|
2018-07-30 00:38:02 +08:00
|
|
|
S->SymbolName = demangleFullyQualifiedSymbolName(MangledName);
|
2018-08-02 02:32:28 +08:00
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
2018-08-18 00:14:05 +08:00
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
std::tie(S->Category, S->SymbolType) =
|
|
|
|
demangleSymbolCategoryAndType(MangledName);
|
2018-08-02 02:32:47 +08:00
|
|
|
|
2018-08-02 02:32:28 +08:00
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
return S;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// <type-encoding> ::= <storage-class> <variable-type>
|
|
|
|
// <storage-class> ::= 0 # private static member
|
|
|
|
// ::= 1 # protected static member
|
|
|
|
// ::= 2 # public static member
|
|
|
|
// ::= 3 # global
|
|
|
|
// ::= 4 # static local
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
Type *Demangler::demangleVariableEncoding(StringView &MangledName,
|
|
|
|
StorageClass SC) {
|
2018-07-30 00:38:02 +08:00
|
|
|
Type *Ty = demangleType(MangledName, QualifierMangleMode::Drop);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
Ty->Storage = SC;
|
|
|
|
|
|
|
|
// <variable-type> ::= <type> <cvr-qualifiers>
|
|
|
|
// ::= <type> <pointee-cvr-qualifiers> # pointers, references
|
|
|
|
switch (Ty->Prim) {
|
|
|
|
case PrimTy::Ptr:
|
2018-07-27 03:56:09 +08:00
|
|
|
case PrimTy::MemberPtr: {
|
2018-07-21 01:27:48 +08:00
|
|
|
Qualifiers ExtraChildQuals = Q_None;
|
2018-07-30 00:38:02 +08:00
|
|
|
Ty->Quals =
|
|
|
|
Qualifiers(Ty->Quals | demanglePointerExtQualifiers(MangledName));
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-27 03:56:09 +08:00
|
|
|
bool IsMember = false;
|
2018-07-30 00:38:02 +08:00
|
|
|
std::tie(ExtraChildQuals, IsMember) = demangleQualifiers(MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-27 03:56:09 +08:00
|
|
|
if (Ty->Prim == PrimTy::MemberPtr) {
|
|
|
|
assert(IsMember);
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *BackRefName = demangleFullyQualifiedTypeName(MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
(void)BackRefName;
|
2018-07-27 03:56:09 +08:00
|
|
|
MemberPointerType *MPTy = static_cast<MemberPointerType *>(Ty);
|
|
|
|
MPTy->Pointee->Quals = Qualifiers(MPTy->Pointee->Quals | ExtraChildQuals);
|
|
|
|
} else {
|
|
|
|
PointerType *PTy = static_cast<PointerType *>(Ty);
|
|
|
|
PTy->Pointee->Quals = Qualifiers(PTy->Pointee->Quals | ExtraChildQuals);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
default:
|
2018-07-30 00:38:02 +08:00
|
|
|
Ty->Quals = demangleQualifiers(MangledName).first;
|
2018-07-21 01:27:48 +08:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return Ty;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Sometimes numbers are encoded in mangled symbols. For example,
|
|
|
|
// "int (*x)[20]" is a valid C type (x is a pointer to an array of
|
|
|
|
// length 20), so we need some way to embed numbers as part of symbols.
|
|
|
|
// This function parses it.
|
|
|
|
//
|
|
|
|
// <number> ::= [?] <non-negative integer>
|
|
|
|
//
|
|
|
|
// <non-negative integer> ::= <decimal digit> # when 1 <= Number <= 10
|
|
|
|
// ::= <hex digit>+ @ # when Numbrer == 0 or >= 10
|
|
|
|
//
|
|
|
|
// <hex-digit> ::= [A-P] # A = 0, B = 1, ...
|
2018-08-10 22:31:04 +08:00
|
|
|
std::pair<uint64_t, bool> Demangler::demangleNumber(StringView &MangledName) {
|
|
|
|
bool IsNegative = MangledName.consumeFront('?');
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
if (startsWithDigit(MangledName)) {
|
2018-08-10 22:31:04 +08:00
|
|
|
uint64_t Ret = MangledName[0] - '0' + 1;
|
2018-07-21 01:27:48 +08:00
|
|
|
MangledName = MangledName.dropFront(1);
|
2018-08-10 22:31:04 +08:00
|
|
|
return {Ret, IsNegative};
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-10 22:31:04 +08:00
|
|
|
uint64_t Ret = 0;
|
2018-07-21 01:27:48 +08:00
|
|
|
for (size_t i = 0; i < MangledName.size(); ++i) {
|
|
|
|
char C = MangledName[i];
|
|
|
|
if (C == '@') {
|
|
|
|
MangledName = MangledName.dropFront(i + 1);
|
2018-08-10 22:31:04 +08:00
|
|
|
return {Ret, IsNegative};
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
if ('A' <= C && C <= 'P') {
|
|
|
|
Ret = (Ret << 4) + (C - 'A');
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
Error = true;
|
2018-08-10 22:31:04 +08:00
|
|
|
return {0ULL, false};
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
uint64_t Demangler::demangleUnsigned(StringView &MangledName) {
|
|
|
|
bool IsNegative = false;
|
|
|
|
uint64_t Number = 0;
|
|
|
|
std::tie(Number, IsNegative) = demangleNumber(MangledName);
|
|
|
|
if (IsNegative)
|
|
|
|
Error = true;
|
|
|
|
return Number;
|
|
|
|
}
|
|
|
|
|
|
|
|
int64_t Demangler::demangleSigned(StringView &MangledName) {
|
|
|
|
bool IsNegative = false;
|
|
|
|
uint64_t Number = 0;
|
|
|
|
std::tie(Number, IsNegative) = demangleNumber(MangledName);
|
|
|
|
if (Number > INT64_MAX)
|
|
|
|
Error = true;
|
|
|
|
int64_t I = static_cast<int64_t>(Number);
|
|
|
|
return IsNegative ? -I : I;
|
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
// First 10 strings can be referenced by special BackReferences ?0, ?1, ..., ?9.
|
|
|
|
// Memorize it.
|
|
|
|
void Demangler::memorizeString(StringView S) {
|
2018-08-09 01:17:04 +08:00
|
|
|
if (Backrefs.NamesCount >= BackrefContext::Max)
|
2018-07-21 01:27:48 +08:00
|
|
|
return;
|
2018-08-09 01:17:04 +08:00
|
|
|
for (size_t i = 0; i < Backrefs.NamesCount; ++i)
|
|
|
|
if (S == Backrefs.Names[i])
|
2018-07-21 01:27:48 +08:00
|
|
|
return;
|
2018-08-09 01:17:04 +08:00
|
|
|
Backrefs.Names[Backrefs.NamesCount++] = S;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *Demangler::demangleBackRefName(StringView &MangledName) {
|
2018-07-29 06:10:42 +08:00
|
|
|
assert(startsWithDigit(MangledName));
|
2018-08-19 02:49:48 +08:00
|
|
|
|
|
|
|
size_t I = MangledName[0] - '0';
|
|
|
|
if (I >= Backrefs.NamesCount) {
|
|
|
|
Error = true;
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
|
2018-08-03 01:08:03 +08:00
|
|
|
MangledName = MangledName.dropFront();
|
2018-08-19 02:49:48 +08:00
|
|
|
Name *Node = Arena.alloc<Name>();
|
|
|
|
Node->Str = Backrefs.Names[I];
|
2018-07-29 06:10:42 +08:00
|
|
|
return Node;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-08 08:43:31 +08:00
|
|
|
Name *Demangler::demangleTemplateInstantiationName(StringView &MangledName,
|
|
|
|
NameBackrefBehavior NBB) {
|
2018-07-29 06:10:42 +08:00
|
|
|
assert(MangledName.startsWith("?$"));
|
|
|
|
MangledName.consumeFront("?$");
|
|
|
|
|
2018-08-09 01:17:04 +08:00
|
|
|
BackrefContext OuterContext;
|
|
|
|
std::swap(OuterContext, Backrefs);
|
|
|
|
|
2018-08-19 02:49:48 +08:00
|
|
|
Name *Node = demangleUnqualifiedSymbolName(MangledName, NBB_Simple);
|
2018-08-09 01:17:04 +08:00
|
|
|
if (!Error)
|
|
|
|
Node->TParams = demangleTemplateParameterList(MangledName);
|
2018-08-02 02:32:28 +08:00
|
|
|
|
2018-08-09 01:17:04 +08:00
|
|
|
std::swap(OuterContext, Backrefs);
|
2018-08-02 02:32:28 +08:00
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
|
2018-08-02 02:32:47 +08:00
|
|
|
Node->IsTemplateInstantiation = true;
|
|
|
|
|
2018-08-08 08:43:31 +08:00
|
|
|
if (NBB & NBB_Template) {
|
|
|
|
// Render this class template name into a string buffer so that we can
|
|
|
|
// memorize it for the purpose of back-referencing.
|
|
|
|
OutputStream OS = OutputStream::create(nullptr, nullptr, 1024);
|
2018-08-19 02:49:48 +08:00
|
|
|
outputName(OS, Node, nullptr);
|
2018-08-08 08:43:31 +08:00
|
|
|
OS << '\0';
|
|
|
|
char *Name = OS.getBuffer();
|
|
|
|
|
|
|
|
StringView Owned = copyString(Name);
|
|
|
|
memorizeString(Owned);
|
|
|
|
std::free(Name);
|
|
|
|
}
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
|
2018-07-29 06:10:42 +08:00
|
|
|
return Node;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
std::pair<OperatorTy, Name *>
|
|
|
|
Demangler::demangleOperatorName(StringView &MangledName, bool FullyQualified) {
|
2018-07-29 06:10:42 +08:00
|
|
|
assert(MangledName.startsWith('?'));
|
|
|
|
MangledName.consumeFront('?');
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
const OperatorMapEntry *Entry = nullptr;
|
|
|
|
for (const auto &MapEntry : OperatorMap) {
|
|
|
|
if (!MangledName.consumeFront(MapEntry.Prefix))
|
|
|
|
continue;
|
|
|
|
Entry = &MapEntry;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (!Entry) {
|
2018-07-29 06:10:42 +08:00
|
|
|
Error = true;
|
2018-08-18 05:18:05 +08:00
|
|
|
return std::make_pair(OperatorTy::Unknown, nullptr);
|
2018-08-18 00:14:05 +08:00
|
|
|
}
|
2018-07-29 06:10:42 +08:00
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
Name *N = nullptr;
|
2018-08-18 00:14:05 +08:00
|
|
|
switch (Entry->Operator) {
|
2018-08-18 05:18:05 +08:00
|
|
|
case OperatorTy::Vftable: // Foo@@6B@
|
|
|
|
case OperatorTy::LocalVftable: // Foo@@6B@
|
|
|
|
case OperatorTy::RttiCompleteObjLocator: // Foo@@6B@
|
|
|
|
case OperatorTy::Vbtable: { // Foo@@7B@
|
|
|
|
OperatorInfo *Oper = Arena.alloc<OperatorInfo>(*Entry);
|
|
|
|
N = (FullyQualified) ? demangleNameScopeChain(MangledName, Oper) : Oper;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
case OperatorTy::StringLiteral:
|
2018-08-18 05:18:05 +08:00
|
|
|
N = demangleStringLiteral(MangledName);
|
2018-08-18 00:14:05 +08:00
|
|
|
break;
|
|
|
|
case OperatorTy::LiteralOperator:
|
2018-08-18 05:18:05 +08:00
|
|
|
N = Arena.alloc<OperatorInfo>(*Entry);
|
|
|
|
N->Str = demangleSimpleString(MangledName, false);
|
|
|
|
if (!MangledName.consumeFront('@'))
|
|
|
|
Error = true;
|
|
|
|
break;
|
|
|
|
case OperatorTy::RttiBaseClassDescriptor: {
|
|
|
|
RttiBaseClassDescriptor *Temp = Arena.alloc<RttiBaseClassDescriptor>();
|
|
|
|
Temp->NVOffset = demangleUnsigned(MangledName);
|
|
|
|
Temp->VBPtrOffset = demangleSigned(MangledName);
|
|
|
|
Temp->VBTableOffset = demangleUnsigned(MangledName);
|
|
|
|
Temp->Flags = demangleUnsigned(MangledName);
|
|
|
|
N = (FullyQualified) ? demangleNameScopeChain(MangledName, Temp) : Temp;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
case OperatorTy::Vcall: {
|
|
|
|
VirtualMemberPtrThunk *Temp = Arena.alloc<VirtualMemberPtrThunk>();
|
|
|
|
N = demangleNameScopeChain(MangledName, Temp);
|
|
|
|
if (Error)
|
|
|
|
break;
|
|
|
|
if (!MangledName.consumeFront("$B"))
|
|
|
|
Error = true;
|
|
|
|
Temp->OffsetInVTable = demangleUnsigned(MangledName);
|
|
|
|
if (!MangledName.consumeFront('A'))
|
|
|
|
Error = true;
|
|
|
|
Temp->CC = demangleCallingConvention(MangledName);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
case OperatorTy::RttiTypeDescriptor:
|
|
|
|
// This one is just followed by a type, not a name scope.
|
|
|
|
N = Arena.alloc<OperatorInfo>(*Entry);
|
|
|
|
break;
|
|
|
|
case OperatorTy::LocalStaticGuard: {
|
|
|
|
LocalStaticGuardVariable *Temp = Arena.alloc<LocalStaticGuardVariable>();
|
|
|
|
N = (FullyQualified) ? demangleNameScopeChain(MangledName, Temp) : Temp;
|
|
|
|
if (MangledName.consumeFront("4IA"))
|
|
|
|
Temp->IsVisible = false;
|
|
|
|
else if (MangledName.consumeFront("5"))
|
|
|
|
Temp->IsVisible = true;
|
|
|
|
else
|
|
|
|
Error = true;
|
|
|
|
if (!MangledName.empty())
|
|
|
|
Temp->ScopeIndex = demangleUnsigned(MangledName);
|
2018-08-18 00:14:05 +08:00
|
|
|
break;
|
2018-08-18 05:18:05 +08:00
|
|
|
}
|
2018-08-18 00:14:05 +08:00
|
|
|
default:
|
2018-08-18 05:18:05 +08:00
|
|
|
N = Arena.alloc<OperatorInfo>(*Entry);
|
|
|
|
N = (FullyQualified) ? demangleNameScopeChain(MangledName, N) : N;
|
|
|
|
break;
|
2018-08-10 23:04:56 +08:00
|
|
|
}
|
2018-08-17 00:17:36 +08:00
|
|
|
if (Error)
|
2018-08-18 05:18:05 +08:00
|
|
|
return std::make_pair(OperatorTy::Unknown, nullptr);
|
2018-08-17 00:17:36 +08:00
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
return std::make_pair(Entry->Operator, N);
|
2018-07-29 06:10:42 +08:00
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *Demangler::demangleSimpleName(StringView &MangledName, bool Memorize) {
|
2018-07-31 07:02:10 +08:00
|
|
|
StringView S = demangleSimpleString(MangledName, Memorize);
|
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
|
|
|
|
2018-07-29 06:10:42 +08:00
|
|
|
Name *Node = Arena.alloc<Name>();
|
2018-07-31 07:02:10 +08:00
|
|
|
Node->Str = S;
|
|
|
|
return Node;
|
|
|
|
}
|
|
|
|
|
2018-08-17 00:17:36 +08:00
|
|
|
static bool isRebasedHexDigit(char C) { return (C >= 'A' && C <= 'P'); }
|
|
|
|
|
|
|
|
static uint8_t rebasedHexDigitToNumber(char C) {
|
|
|
|
assert(isRebasedHexDigit(C));
|
|
|
|
return (C <= 'J') ? (C - 'A') : (10 + C - 'K');
|
|
|
|
}
|
|
|
|
|
|
|
|
uint8_t Demangler::demangleCharLiteral(StringView &MangledName) {
|
|
|
|
if (!MangledName.startsWith('?'))
|
|
|
|
return MangledName.popFront();
|
|
|
|
|
|
|
|
MangledName = MangledName.dropFront();
|
|
|
|
if (MangledName.empty())
|
|
|
|
goto CharLiteralError;
|
|
|
|
|
|
|
|
if (MangledName.consumeFront('$')) {
|
|
|
|
// Two hex digits
|
|
|
|
if (MangledName.size() < 2)
|
|
|
|
goto CharLiteralError;
|
|
|
|
StringView Nibbles = MangledName.substr(0, 2);
|
|
|
|
if (!isRebasedHexDigit(Nibbles[0]) || !isRebasedHexDigit(Nibbles[1]))
|
|
|
|
goto CharLiteralError;
|
|
|
|
// Don't append the null terminator.
|
|
|
|
uint8_t C1 = rebasedHexDigitToNumber(Nibbles[0]);
|
|
|
|
uint8_t C2 = rebasedHexDigitToNumber(Nibbles[1]);
|
|
|
|
MangledName = MangledName.dropFront(2);
|
|
|
|
return (C1 << 4) | C2;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (startsWithDigit(MangledName)) {
|
|
|
|
const char *Lookup = ",/\\:. \n\t'-";
|
|
|
|
char C = Lookup[MangledName[0] - '0'];
|
|
|
|
MangledName = MangledName.dropFront();
|
|
|
|
return C;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (MangledName[0] >= 'a' && MangledName[0] <= 'z') {
|
|
|
|
char Lookup[26] = {'\xE1', '\xE2', '\xE3', '\xE4', '\xE5', '\xE6', '\xE7',
|
|
|
|
'\xE8', '\xE9', '\xEA', '\xEB', '\xEC', '\xED', '\xEE',
|
|
|
|
'\xEF', '\xF0', '\xF1', '\xF2', '\xF3', '\xF4', '\xF5',
|
|
|
|
'\xF6', '\xF7', '\xF8', '\xF9', '\xFA'};
|
|
|
|
char C = Lookup[MangledName[0] - 'a'];
|
|
|
|
MangledName = MangledName.dropFront();
|
|
|
|
return C;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (MangledName[0] >= 'A' && MangledName[0] <= 'Z') {
|
|
|
|
char Lookup[26] = {'\xC1', '\xC2', '\xC3', '\xC4', '\xC5', '\xC6', '\xC7',
|
|
|
|
'\xC8', '\xC9', '\xCA', '\xCB', '\xCC', '\xCD', '\xCE',
|
|
|
|
'\xCF', '\xD0', '\xD1', '\xD2', '\xD3', '\xD4', '\xD5',
|
|
|
|
'\xD6', '\xD7', '\xD8', '\xD9', '\xDA'};
|
|
|
|
char C = Lookup[MangledName[0] - 'A'];
|
|
|
|
MangledName = MangledName.dropFront();
|
|
|
|
return C;
|
|
|
|
}
|
|
|
|
|
|
|
|
CharLiteralError:
|
|
|
|
Error = true;
|
|
|
|
return '\0';
|
|
|
|
}
|
|
|
|
|
|
|
|
wchar_t Demangler::demangleWcharLiteral(StringView &MangledName) {
|
2018-08-17 00:30:27 +08:00
|
|
|
uint8_t C1, C2;
|
|
|
|
|
|
|
|
C1 = demangleCharLiteral(MangledName);
|
2018-08-17 00:17:36 +08:00
|
|
|
if (Error)
|
|
|
|
goto WCharLiteralError;
|
2018-08-17 00:30:27 +08:00
|
|
|
C2 = demangleCharLiteral(MangledName);
|
2018-08-17 00:17:36 +08:00
|
|
|
if (Error)
|
|
|
|
goto WCharLiteralError;
|
|
|
|
|
|
|
|
return ((wchar_t)C1 << 8) | (wchar_t)C2;
|
|
|
|
|
|
|
|
WCharLiteralError:
|
|
|
|
Error = true;
|
|
|
|
return L'\0';
|
|
|
|
}
|
|
|
|
|
|
|
|
static void writeHexDigit(char *Buffer, uint8_t Digit) {
|
|
|
|
assert(Digit <= 15);
|
|
|
|
*Buffer = (Digit < 10) ? ('0' + Digit) : ('A' + Digit - 10);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void outputHex(OutputStream &OS, unsigned C) {
|
|
|
|
if (C == 0) {
|
|
|
|
OS << "\\x00";
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
// It's easier to do the math if we can work from right to left, but we need
|
|
|
|
// to print the numbers from left to right. So render this into a temporary
|
|
|
|
// buffer first, then output the temporary buffer. Each byte is of the form
|
|
|
|
// \xAB, which means that each byte needs 4 characters. Since there are at
|
|
|
|
// most 4 bytes, we need a 4*4+1 = 17 character temporary buffer.
|
|
|
|
char TempBuffer[17];
|
|
|
|
|
|
|
|
::memset(TempBuffer, 0, sizeof(TempBuffer));
|
|
|
|
constexpr int MaxPos = 15;
|
|
|
|
|
|
|
|
int Pos = MaxPos - 1;
|
|
|
|
while (C != 0) {
|
|
|
|
for (int I = 0; I < 2; ++I) {
|
|
|
|
writeHexDigit(&TempBuffer[Pos--], C % 16);
|
|
|
|
C /= 16;
|
|
|
|
}
|
|
|
|
TempBuffer[Pos--] = 'x';
|
|
|
|
TempBuffer[Pos--] = '\\';
|
|
|
|
assert(Pos >= 0);
|
|
|
|
}
|
|
|
|
OS << StringView(&TempBuffer[Pos + 1]);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void outputEscapedChar(OutputStream &OS, unsigned C) {
|
|
|
|
switch (C) {
|
|
|
|
case '\'': // single quote
|
|
|
|
OS << "\\\'";
|
|
|
|
return;
|
|
|
|
case '\"': // double quote
|
|
|
|
OS << "\\\"";
|
|
|
|
return;
|
|
|
|
case '\\': // backslash
|
|
|
|
OS << "\\\\";
|
|
|
|
return;
|
|
|
|
case '\a': // bell
|
|
|
|
OS << "\\a";
|
|
|
|
return;
|
|
|
|
case '\b': // backspace
|
|
|
|
OS << "\\b";
|
|
|
|
return;
|
|
|
|
case '\f': // form feed
|
|
|
|
OS << "\\f";
|
|
|
|
return;
|
|
|
|
case '\n': // new line
|
|
|
|
OS << "\\n";
|
|
|
|
return;
|
|
|
|
case '\r': // carriage return
|
|
|
|
OS << "\\r";
|
|
|
|
return;
|
|
|
|
case '\t': // tab
|
|
|
|
OS << "\\t";
|
|
|
|
return;
|
|
|
|
case '\v': // vertical tab
|
|
|
|
OS << "\\v";
|
|
|
|
return;
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (C > 0x1F && C < 0x7F) {
|
|
|
|
// Standard ascii char.
|
|
|
|
OS << (char)C;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
outputHex(OS, C);
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned countTrailingNullBytes(const uint8_t *StringBytes, int Length) {
|
|
|
|
const uint8_t *End = StringBytes + Length - 1;
|
2018-08-18 00:14:05 +08:00
|
|
|
unsigned Count = 0;
|
2018-08-17 00:17:36 +08:00
|
|
|
while (Length > 0 && *End == 0) {
|
|
|
|
--Length;
|
|
|
|
--End;
|
2018-08-18 00:14:05 +08:00
|
|
|
++Count;
|
2018-08-17 00:17:36 +08:00
|
|
|
}
|
2018-08-18 00:14:05 +08:00
|
|
|
return Count;
|
2018-08-17 00:17:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
unsigned countEmbeddedNulls(const uint8_t *StringBytes, unsigned Length) {
|
|
|
|
unsigned Result = 0;
|
|
|
|
for (unsigned I = 0; I < Length; ++I) {
|
|
|
|
if (*StringBytes++ == 0)
|
|
|
|
++Result;
|
|
|
|
}
|
|
|
|
return Result;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned guessCharByteSize(const uint8_t *StringBytes, unsigned NumChars,
|
|
|
|
unsigned NumBytes) {
|
|
|
|
assert(NumBytes > 0);
|
|
|
|
|
|
|
|
// If the number of bytes is odd, this is guaranteed to be a char string.
|
|
|
|
if (NumBytes % 2 == 1)
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
// All strings can encode at most 32 bytes of data. If it's less than that,
|
|
|
|
// then we encoded the entire string. In this case we check for a 1-byte,
|
|
|
|
// 2-byte, or 4-byte null terminator.
|
|
|
|
if (NumBytes < 32) {
|
|
|
|
unsigned TrailingNulls = countTrailingNullBytes(StringBytes, NumChars);
|
|
|
|
if (TrailingNulls >= 4)
|
|
|
|
return 4;
|
|
|
|
if (TrailingNulls >= 2)
|
|
|
|
return 2;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
// The whole string was not able to be encoded. Try to look at embedded null
|
|
|
|
// terminators to guess. The heuristic is that we count all embedded null
|
|
|
|
// terminators. If more than 2/3 are null, it's a char32. If more than 1/3
|
|
|
|
// are null, it's a char16. Otherwise it's a char8. This obviously isn't
|
|
|
|
// perfect and is biased towards languages that have ascii alphabets, but this
|
|
|
|
// was always going to be best effort since the encoding is lossy.
|
|
|
|
unsigned Nulls = countEmbeddedNulls(StringBytes, NumChars);
|
|
|
|
if (Nulls >= 2 * NumChars / 3)
|
|
|
|
return 4;
|
|
|
|
if (Nulls >= NumChars / 3)
|
|
|
|
return 2;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned decodeMultiByteChar(const uint8_t *StringBytes,
|
|
|
|
unsigned CharIndex, unsigned CharBytes) {
|
|
|
|
assert(CharBytes == 1 || CharBytes == 2 || CharBytes == 4);
|
|
|
|
unsigned Offset = CharIndex * CharBytes;
|
|
|
|
unsigned Result = 0;
|
|
|
|
StringBytes = StringBytes + Offset;
|
|
|
|
for (unsigned I = 0; I < CharBytes; ++I) {
|
|
|
|
unsigned C = static_cast<unsigned>(StringBytes[I]);
|
|
|
|
Result |= C << (8 * I);
|
|
|
|
}
|
|
|
|
return Result;
|
|
|
|
}
|
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
StringLiteral *Demangler::demangleStringLiteral(StringView &MangledName) {
|
2018-08-17 00:30:27 +08:00
|
|
|
// This function uses goto, so declare all variables up front.
|
2018-08-17 00:17:36 +08:00
|
|
|
OutputStream OS;
|
|
|
|
StringView CRC;
|
2018-08-17 00:30:27 +08:00
|
|
|
uint64_t StringByteSize;
|
|
|
|
bool IsWcharT = false;
|
|
|
|
bool IsNegative = false;
|
|
|
|
size_t CrcEndPos = 0;
|
|
|
|
char *ResultBuffer = nullptr;
|
|
|
|
|
2018-08-18 00:14:05 +08:00
|
|
|
StringLiteral *Result = Arena.alloc<StringLiteral>();
|
2018-08-17 00:17:36 +08:00
|
|
|
|
|
|
|
// Prefix indicating the beginning of a string literal
|
2018-08-18 00:14:05 +08:00
|
|
|
if (!MangledName.consumeFront("@_"))
|
|
|
|
goto StringLiteralError;
|
2018-08-17 00:17:36 +08:00
|
|
|
if (MangledName.empty())
|
|
|
|
goto StringLiteralError;
|
|
|
|
|
|
|
|
// Char Type (regular or wchar_t)
|
|
|
|
switch (MangledName.popFront()) {
|
|
|
|
case '1':
|
|
|
|
IsWcharT = true;
|
|
|
|
LLVM_FALLTHROUGH;
|
|
|
|
case '0':
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
goto StringLiteralError;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Encoded Length
|
|
|
|
std::tie(StringByteSize, IsNegative) = demangleNumber(MangledName);
|
|
|
|
if (Error || IsNegative)
|
|
|
|
goto StringLiteralError;
|
|
|
|
|
|
|
|
// CRC 32 (always 8 characters plus a terminator)
|
2018-08-17 00:30:27 +08:00
|
|
|
CrcEndPos = MangledName.find('@');
|
2018-08-17 00:17:36 +08:00
|
|
|
if (CrcEndPos == StringView::npos)
|
|
|
|
goto StringLiteralError;
|
|
|
|
CRC = MangledName.substr(0, CrcEndPos);
|
|
|
|
MangledName = MangledName.dropFront(CrcEndPos + 1);
|
|
|
|
if (MangledName.empty())
|
|
|
|
goto StringLiteralError;
|
|
|
|
|
|
|
|
OS = OutputStream::create(nullptr, nullptr, 1024);
|
|
|
|
if (IsWcharT) {
|
2018-08-18 00:14:05 +08:00
|
|
|
Result->CharType = PrimTy::Wchar;
|
2018-08-17 00:17:36 +08:00
|
|
|
if (StringByteSize > 64)
|
2018-08-18 00:14:05 +08:00
|
|
|
Result->IsTruncated = true;
|
2018-08-17 00:17:36 +08:00
|
|
|
|
|
|
|
while (!MangledName.consumeFront('@')) {
|
|
|
|
assert(StringByteSize >= 2);
|
|
|
|
wchar_t W = demangleWcharLiteral(MangledName);
|
2018-08-18 00:14:05 +08:00
|
|
|
if (StringByteSize != 2 || Result->IsTruncated)
|
2018-08-17 00:17:36 +08:00
|
|
|
outputEscapedChar(OS, W);
|
|
|
|
StringByteSize -= 2;
|
|
|
|
if (Error)
|
|
|
|
goto StringLiteralError;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
if (StringByteSize > 32)
|
2018-08-18 00:14:05 +08:00
|
|
|
Result->IsTruncated = true;
|
2018-08-17 00:17:36 +08:00
|
|
|
|
|
|
|
constexpr unsigned MaxStringByteLength = 32;
|
|
|
|
uint8_t StringBytes[MaxStringByteLength];
|
|
|
|
|
|
|
|
unsigned BytesDecoded = 0;
|
|
|
|
while (!MangledName.consumeFront('@')) {
|
|
|
|
assert(StringByteSize >= 1);
|
|
|
|
StringBytes[BytesDecoded++] = demangleCharLiteral(MangledName);
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned CharBytes =
|
|
|
|
guessCharByteSize(StringBytes, BytesDecoded, StringByteSize);
|
|
|
|
assert(StringByteSize % CharBytes == 0);
|
|
|
|
switch (CharBytes) {
|
|
|
|
case 1:
|
2018-08-18 00:14:05 +08:00
|
|
|
Result->CharType = PrimTy::Char;
|
2018-08-17 00:17:36 +08:00
|
|
|
break;
|
|
|
|
case 2:
|
2018-08-18 00:14:05 +08:00
|
|
|
Result->CharType = PrimTy::Char16;
|
2018-08-17 00:17:36 +08:00
|
|
|
break;
|
|
|
|
case 4:
|
2018-08-18 00:14:05 +08:00
|
|
|
Result->CharType = PrimTy::Char32;
|
2018-08-17 00:17:36 +08:00
|
|
|
break;
|
|
|
|
default:
|
|
|
|
LLVM_BUILTIN_UNREACHABLE;
|
|
|
|
}
|
|
|
|
const unsigned NumChars = BytesDecoded / CharBytes;
|
|
|
|
for (unsigned CharIndex = 0; CharIndex < NumChars; ++CharIndex) {
|
|
|
|
unsigned NextChar =
|
|
|
|
decodeMultiByteChar(StringBytes, CharIndex, CharBytes);
|
2018-08-18 00:14:05 +08:00
|
|
|
if (CharIndex + 1 < NumChars || Result->IsTruncated)
|
2018-08-17 00:17:36 +08:00
|
|
|
outputEscapedChar(OS, NextChar);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
OS << '\0';
|
2018-08-17 00:30:27 +08:00
|
|
|
ResultBuffer = OS.getBuffer();
|
2018-08-17 00:17:36 +08:00
|
|
|
Result->Str = copyString(ResultBuffer);
|
2018-08-17 01:48:32 +08:00
|
|
|
std::free(ResultBuffer);
|
2018-08-17 00:17:36 +08:00
|
|
|
return Result;
|
|
|
|
|
|
|
|
StringLiteralError:
|
|
|
|
Error = true;
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
|
2018-07-31 07:02:10 +08:00
|
|
|
StringView Demangler::demangleSimpleString(StringView &MangledName,
|
|
|
|
bool Memorize) {
|
|
|
|
StringView S;
|
2018-07-29 06:10:42 +08:00
|
|
|
for (size_t i = 0; i < MangledName.size(); ++i) {
|
|
|
|
if (MangledName[i] != '@')
|
|
|
|
continue;
|
2018-07-31 07:02:10 +08:00
|
|
|
S = MangledName.substr(0, i);
|
2018-07-29 06:10:42 +08:00
|
|
|
MangledName = MangledName.dropFront(i + 1);
|
|
|
|
|
|
|
|
if (Memorize)
|
2018-07-31 07:02:10 +08:00
|
|
|
memorizeString(S);
|
|
|
|
return S;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
Error = true;
|
2018-07-31 07:02:10 +08:00
|
|
|
return {};
|
2018-07-29 06:10:42 +08:00
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *Demangler::demangleAnonymousNamespaceName(StringView &MangledName) {
|
2018-07-29 06:10:42 +08:00
|
|
|
assert(MangledName.startsWith("?A"));
|
|
|
|
MangledName.consumeFront("?A");
|
|
|
|
|
|
|
|
Name *Node = Arena.alloc<Name>();
|
|
|
|
Node->Str = "`anonymous namespace'";
|
2018-08-21 07:58:35 +08:00
|
|
|
size_t EndPos = MangledName.find('@');
|
|
|
|
if (EndPos == StringView::npos) {
|
|
|
|
Error = true;
|
|
|
|
return nullptr;
|
|
|
|
}
|
2018-08-21 07:58:58 +08:00
|
|
|
StringView NamespaceKey = MangledName.substr(0, EndPos);
|
|
|
|
memorizeString(NamespaceKey);
|
2018-08-21 07:58:35 +08:00
|
|
|
MangledName = MangledName.substr(EndPos + 1);
|
|
|
|
return Node;
|
2018-07-29 06:10:42 +08:00
|
|
|
}
|
|
|
|
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
Name *Demangler::demangleLocallyScopedNamePiece(StringView &MangledName) {
|
|
|
|
assert(startsWithLocalScopePattern(MangledName));
|
|
|
|
|
|
|
|
Name *Node = Arena.alloc<Name>();
|
|
|
|
MangledName.consumeFront('?');
|
2018-08-10 22:31:04 +08:00
|
|
|
auto Number = demangleNumber(MangledName);
|
|
|
|
assert(!Number.second);
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
|
|
|
|
// One ? to terminate the number
|
|
|
|
MangledName.consumeFront('?');
|
|
|
|
|
|
|
|
assert(!Error);
|
|
|
|
Symbol *Scope = parse(MangledName);
|
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
|
|
|
|
|
|
|
// Render the parent symbol's name into a buffer.
|
|
|
|
OutputStream OS = OutputStream::create(nullptr, nullptr, 1024);
|
|
|
|
OS << '`';
|
|
|
|
output(Scope, OS);
|
|
|
|
OS << '\'';
|
2018-08-10 22:31:04 +08:00
|
|
|
OS << "::`" << Number.first << "'";
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
OS << '\0';
|
|
|
|
char *Result = OS.getBuffer();
|
|
|
|
Node->Str = copyString(Result);
|
|
|
|
std::free(Result);
|
|
|
|
return Node;
|
|
|
|
}
|
|
|
|
|
2018-07-29 06:10:42 +08:00
|
|
|
// Parses a type name in the form of A@B@C@@ which represents C::B::A.
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *Demangler::demangleFullyQualifiedTypeName(StringView &MangledName) {
|
2018-08-02 02:32:47 +08:00
|
|
|
Name *TypeName = demangleUnqualifiedTypeName(MangledName, true);
|
2018-08-02 02:32:28 +08:00
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
2018-07-29 06:10:42 +08:00
|
|
|
assert(TypeName);
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *QualName = demangleNameScopeChain(MangledName, TypeName);
|
2018-08-02 02:32:28 +08:00
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
2018-07-29 06:10:42 +08:00
|
|
|
assert(QualName);
|
|
|
|
return QualName;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Parses a symbol name in the form of A@B@C@@ which represents C::B::A.
|
|
|
|
// Symbol names have slightly different rules regarding what can appear
|
|
|
|
// so we separate out the implementations for flexibility.
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *Demangler::demangleFullyQualifiedSymbolName(StringView &MangledName) {
|
2018-08-08 08:43:31 +08:00
|
|
|
// This is the final component of a symbol name (i.e. the leftmost component
|
|
|
|
// of a mangled name. Since the only possible template instantiation that
|
|
|
|
// can appear in this context is a function template, and since those are
|
|
|
|
// not saved for the purposes of name backreferences, only backref simple
|
|
|
|
// names.
|
|
|
|
Name *SymbolName = demangleUnqualifiedSymbolName(MangledName, NBB_Simple);
|
2018-08-02 02:32:28 +08:00
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
2018-08-18 00:14:05 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *QualName = demangleNameScopeChain(MangledName, SymbolName);
|
2018-08-02 02:32:28 +08:00
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
2018-07-29 06:10:42 +08:00
|
|
|
assert(QualName);
|
|
|
|
return QualName;
|
|
|
|
}
|
|
|
|
|
2018-08-02 02:32:47 +08:00
|
|
|
Name *Demangler::demangleUnqualifiedTypeName(StringView &MangledName,
|
|
|
|
bool Memorize) {
|
2018-07-29 06:10:42 +08:00
|
|
|
// An inner-most name can be a back-reference, because a fully-qualified name
|
|
|
|
// (e.g. Scope + Inner) can contain other fully qualified names inside of
|
|
|
|
// them (for example template parameters), and these nested parameters can
|
|
|
|
// refer to previously mangled types.
|
|
|
|
if (startsWithDigit(MangledName))
|
2018-07-30 00:38:02 +08:00
|
|
|
return demangleBackRefName(MangledName);
|
2018-07-29 06:10:42 +08:00
|
|
|
|
|
|
|
if (MangledName.startsWith("?$"))
|
2018-08-08 08:43:31 +08:00
|
|
|
return demangleTemplateInstantiationName(MangledName, NBB_Template);
|
2018-07-29 06:10:42 +08:00
|
|
|
|
2018-08-02 02:32:47 +08:00
|
|
|
return demangleSimpleName(MangledName, Memorize);
|
2018-07-29 06:10:42 +08:00
|
|
|
}
|
|
|
|
|
2018-08-02 02:32:47 +08:00
|
|
|
Name *Demangler::demangleUnqualifiedSymbolName(StringView &MangledName,
|
2018-08-08 08:43:31 +08:00
|
|
|
NameBackrefBehavior NBB) {
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
if (startsWithDigit(MangledName))
|
|
|
|
return demangleBackRefName(MangledName);
|
|
|
|
if (MangledName.startsWith("?$"))
|
2018-08-08 08:43:31 +08:00
|
|
|
return demangleTemplateInstantiationName(MangledName, NBB);
|
2018-07-29 06:10:42 +08:00
|
|
|
if (MangledName.startsWith('?'))
|
2018-08-18 05:18:05 +08:00
|
|
|
return demangleOperatorName(MangledName, false).second;
|
2018-08-08 08:43:31 +08:00
|
|
|
return demangleSimpleName(MangledName, (NBB & NBB_Simple) != 0);
|
2018-07-29 06:10:42 +08:00
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *Demangler::demangleNameScopePiece(StringView &MangledName) {
|
2018-07-29 06:10:42 +08:00
|
|
|
if (startsWithDigit(MangledName))
|
2018-07-30 00:38:02 +08:00
|
|
|
return demangleBackRefName(MangledName);
|
2018-07-29 06:10:42 +08:00
|
|
|
|
|
|
|
if (MangledName.startsWith("?$"))
|
2018-08-08 08:43:31 +08:00
|
|
|
return demangleTemplateInstantiationName(MangledName, NBB_Template);
|
2018-07-29 06:10:42 +08:00
|
|
|
|
|
|
|
if (MangledName.startsWith("?A"))
|
2018-07-30 00:38:02 +08:00
|
|
|
return demangleAnonymousNamespaceName(MangledName);
|
2018-07-29 06:10:42 +08:00
|
|
|
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
if (startsWithLocalScopePattern(MangledName))
|
|
|
|
return demangleLocallyScopedNamePiece(MangledName);
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
return demangleSimpleName(MangledName, true);
|
2018-07-29 06:10:42 +08:00
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *Demangler::demangleNameScopeChain(StringView &MangledName,
|
|
|
|
Name *UnqualifiedName) {
|
2018-07-29 06:10:42 +08:00
|
|
|
Name *Head = UnqualifiedName;
|
|
|
|
|
|
|
|
while (!MangledName.consumeFront("@")) {
|
|
|
|
if (MangledName.empty()) {
|
|
|
|
Error = true;
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
assert(!Error);
|
2018-07-30 00:38:02 +08:00
|
|
|
Name *Elem = demangleNameScopePiece(MangledName);
|
2018-07-29 06:10:42 +08:00
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
|
|
|
|
|
|
|
Elem->Next = Head;
|
|
|
|
Head = Elem;
|
|
|
|
}
|
|
|
|
return Head;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
FuncClass Demangler::demangleFunctionClass(StringView &MangledName) {
|
2018-07-21 01:27:48 +08:00
|
|
|
SwapAndRestore<StringView> RestoreOnError(MangledName, MangledName);
|
|
|
|
RestoreOnError.shouldRestore(false);
|
|
|
|
|
|
|
|
switch (MangledName.popFront()) {
|
2018-08-11 05:09:05 +08:00
|
|
|
case '9':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(ExternC | NoPrototype);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'A':
|
|
|
|
return Private;
|
|
|
|
case 'B':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Private | Far);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'C':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Private | Static);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'D':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Private | Static);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'E':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Private | Virtual);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'F':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Private | Virtual);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'I':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Protected);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'J':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Protected | Far);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'K':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Protected | Static);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'L':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Protected | Static | Far);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'M':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Protected | Virtual);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'N':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Protected | Virtual | Far);
|
|
|
|
case 'O':
|
|
|
|
return FuncClass(Protected | Virtual | StaticThisAdjust);
|
|
|
|
case 'P':
|
|
|
|
return FuncClass(Protected | Virtual | StaticThisAdjust | Far);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'Q':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Public);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'R':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Public | Far);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'S':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Public | Static);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'T':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Public | Static | Far);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'U':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Public | Virtual);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'V':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Public | Virtual | Far);
|
|
|
|
case 'W':
|
|
|
|
return FuncClass(Public | Virtual | StaticThisAdjust);
|
|
|
|
case 'X':
|
|
|
|
return FuncClass(Public | Virtual | StaticThisAdjust | Far);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'Y':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Global);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'Z':
|
2018-08-18 05:18:05 +08:00
|
|
|
return FuncClass(Global | Far);
|
|
|
|
case '$': {
|
|
|
|
FuncClass VFlag = VirtualThisAdjust;
|
|
|
|
if (MangledName.consumeFront('R'))
|
|
|
|
VFlag = FuncClass(VFlag | VirtualThisAdjustEx);
|
|
|
|
|
|
|
|
switch (MangledName.popFront()) {
|
|
|
|
case '0':
|
|
|
|
return FuncClass(Private | Virtual | VFlag);
|
|
|
|
case '1':
|
|
|
|
return FuncClass(Private | Virtual | VFlag | Far);
|
|
|
|
case '2':
|
|
|
|
return FuncClass(Protected | Virtual | VFlag);
|
|
|
|
case '3':
|
|
|
|
return FuncClass(Protected | Virtual | VFlag | Far);
|
|
|
|
case '4':
|
|
|
|
return FuncClass(Public | Virtual | VFlag);
|
|
|
|
case '5':
|
|
|
|
return FuncClass(Public | Virtual | VFlag | Far);
|
|
|
|
}
|
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
Error = true;
|
|
|
|
RestoreOnError.shouldRestore(true);
|
2018-07-27 04:20:10 +08:00
|
|
|
return Public;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
CallingConv Demangler::demangleCallingConvention(StringView &MangledName) {
|
2018-07-21 01:27:48 +08:00
|
|
|
switch (MangledName.popFront()) {
|
|
|
|
case 'A':
|
|
|
|
case 'B':
|
|
|
|
return CallingConv::Cdecl;
|
|
|
|
case 'C':
|
|
|
|
case 'D':
|
|
|
|
return CallingConv::Pascal;
|
|
|
|
case 'E':
|
|
|
|
case 'F':
|
|
|
|
return CallingConv::Thiscall;
|
|
|
|
case 'G':
|
|
|
|
case 'H':
|
|
|
|
return CallingConv::Stdcall;
|
|
|
|
case 'I':
|
|
|
|
case 'J':
|
|
|
|
return CallingConv::Fastcall;
|
|
|
|
case 'M':
|
|
|
|
case 'N':
|
|
|
|
return CallingConv::Clrcall;
|
|
|
|
case 'O':
|
|
|
|
case 'P':
|
|
|
|
return CallingConv::Eabi;
|
|
|
|
case 'Q':
|
|
|
|
return CallingConv::Vectorcall;
|
|
|
|
}
|
|
|
|
|
|
|
|
return CallingConv::None;
|
2018-07-21 02:43:42 +08:00
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
StorageClass Demangler::demangleVariableStorageClass(StringView &MangledName) {
|
2018-07-21 01:27:48 +08:00
|
|
|
assert(std::isdigit(MangledName.front()));
|
|
|
|
|
|
|
|
switch (MangledName.popFront()) {
|
|
|
|
case '0':
|
|
|
|
return StorageClass::PrivateStatic;
|
|
|
|
case '1':
|
|
|
|
return StorageClass::ProtectedStatic;
|
|
|
|
case '2':
|
|
|
|
return StorageClass::PublicStatic;
|
|
|
|
case '3':
|
|
|
|
return StorageClass::Global;
|
|
|
|
case '4':
|
|
|
|
return StorageClass::FunctionLocalStatic;
|
|
|
|
}
|
|
|
|
Error = true;
|
|
|
|
return StorageClass::None;
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
std::pair<Qualifiers, bool>
|
|
|
|
Demangler::demangleQualifiers(StringView &MangledName) {
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
switch (MangledName.popFront()) {
|
2018-07-27 03:56:09 +08:00
|
|
|
// Member qualifiers
|
|
|
|
case 'Q':
|
|
|
|
return std::make_pair(Q_None, true);
|
|
|
|
case 'R':
|
|
|
|
return std::make_pair(Q_Const, true);
|
|
|
|
case 'S':
|
|
|
|
return std::make_pair(Q_Volatile, true);
|
|
|
|
case 'T':
|
|
|
|
return std::make_pair(Qualifiers(Q_Const | Q_Volatile), true);
|
|
|
|
// Non-Member qualifiers
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'A':
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Q_None, false);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'B':
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Q_Const, false);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'C':
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Q_Volatile, false);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'D':
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Qualifiers(Q_Const | Q_Volatile), false);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
Error = true;
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Q_None, false);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-07-31 07:02:10 +08:00
|
|
|
static bool isTagType(StringView S) {
|
|
|
|
switch (S.front()) {
|
|
|
|
case 'T': // union
|
|
|
|
case 'U': // struct
|
|
|
|
case 'V': // class
|
|
|
|
case 'W': // enum
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool isPointerType(StringView S) {
|
|
|
|
if (S.startsWith("$$Q")) // foo &&
|
|
|
|
return true;
|
|
|
|
|
|
|
|
switch (S.front()) {
|
|
|
|
case 'A': // foo &
|
|
|
|
case 'P': // foo *
|
|
|
|
case 'Q': // foo *const
|
|
|
|
case 'R': // foo *volatile
|
|
|
|
case 'S': // foo *const volatile
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool isArrayType(StringView S) { return S[0] == 'Y'; }
|
|
|
|
|
|
|
|
static bool isFunctionType(StringView S) {
|
|
|
|
return S.startsWith("$$A8@@") || S.startsWith("$$A6");
|
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
// <variable-type> ::= <type> <cvr-qualifiers>
|
|
|
|
// ::= <type> <pointee-cvr-qualifiers> # pointers, references
|
2018-07-30 00:38:02 +08:00
|
|
|
Type *Demangler::demangleType(StringView &MangledName,
|
|
|
|
QualifierMangleMode QMM) {
|
2018-07-21 01:27:48 +08:00
|
|
|
Qualifiers Quals = Q_None;
|
2018-07-27 03:56:09 +08:00
|
|
|
bool IsMember = false;
|
|
|
|
bool IsMemberKnown = false;
|
|
|
|
if (QMM == QualifierMangleMode::Mangle) {
|
2018-07-30 00:38:02 +08:00
|
|
|
std::tie(Quals, IsMember) = demangleQualifiers(MangledName);
|
2018-07-27 03:56:09 +08:00
|
|
|
IsMemberKnown = true;
|
|
|
|
} else if (QMM == QualifierMangleMode::Result) {
|
|
|
|
if (MangledName.consumeFront('?')) {
|
2018-07-30 00:38:02 +08:00
|
|
|
std::tie(Quals, IsMember) = demangleQualifiers(MangledName);
|
2018-07-27 03:56:09 +08:00
|
|
|
IsMemberKnown = true;
|
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
Type *Ty = nullptr;
|
2018-07-31 07:02:10 +08:00
|
|
|
if (isTagType(MangledName))
|
2018-07-30 00:38:02 +08:00
|
|
|
Ty = demangleClassType(MangledName);
|
2018-07-31 07:02:10 +08:00
|
|
|
else if (isPointerType(MangledName)) {
|
2018-07-27 03:56:09 +08:00
|
|
|
if (!IsMemberKnown)
|
|
|
|
IsMember = isMemberPointer(MangledName);
|
2018-07-31 07:02:10 +08:00
|
|
|
|
2018-07-27 03:56:09 +08:00
|
|
|
if (IsMember)
|
2018-07-30 00:38:02 +08:00
|
|
|
Ty = demangleMemberPointerType(MangledName);
|
2018-07-27 03:56:09 +08:00
|
|
|
else
|
2018-07-30 00:38:02 +08:00
|
|
|
Ty = demanglePointerType(MangledName);
|
2018-07-31 07:02:10 +08:00
|
|
|
} else if (isArrayType(MangledName))
|
2018-07-30 00:38:02 +08:00
|
|
|
Ty = demangleArrayType(MangledName);
|
2018-07-31 07:02:10 +08:00
|
|
|
else if (isFunctionType(MangledName)) {
|
|
|
|
if (MangledName.consumeFront("$$A8@@"))
|
|
|
|
Ty = demangleFunctionType(MangledName, true, false);
|
|
|
|
else {
|
|
|
|
assert(MangledName.startsWith("$$A6"));
|
|
|
|
MangledName.consumeFront("$$A6");
|
|
|
|
Ty = demangleFunctionType(MangledName, false, false);
|
|
|
|
}
|
|
|
|
} else {
|
2018-07-30 00:38:02 +08:00
|
|
|
Ty = demangleBasicType(MangledName);
|
2018-07-31 07:02:10 +08:00
|
|
|
assert(Ty && !Error);
|
|
|
|
if (!Ty || Error)
|
|
|
|
return Ty;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
2018-07-31 07:02:10 +08:00
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
Ty->Quals = Qualifiers(Ty->Quals | Quals);
|
|
|
|
return Ty;
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
ReferenceKind Demangler::demangleReferenceKind(StringView &MangledName) {
|
2018-07-21 01:27:48 +08:00
|
|
|
if (MangledName.consumeFront('G'))
|
|
|
|
return ReferenceKind::LValueRef;
|
|
|
|
else if (MangledName.consumeFront('H'))
|
|
|
|
return ReferenceKind::RValueRef;
|
|
|
|
return ReferenceKind::None;
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
void Demangler::demangleThrowSpecification(StringView &MangledName) {
|
2018-07-27 04:20:10 +08:00
|
|
|
if (MangledName.consumeFront('Z'))
|
|
|
|
return;
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-27 04:20:10 +08:00
|
|
|
Error = true;
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
FunctionType *Demangler::demangleFunctionType(StringView &MangledName,
|
|
|
|
bool HasThisQuals,
|
2018-07-27 04:33:48 +08:00
|
|
|
bool IsFunctionPointer) {
|
2018-07-27 04:20:10 +08:00
|
|
|
FunctionType *FTy = Arena.alloc<FunctionType>();
|
2018-07-21 01:27:48 +08:00
|
|
|
FTy->Prim = PrimTy::Function;
|
2018-07-27 04:33:48 +08:00
|
|
|
FTy->IsFunctionPointer = IsFunctionPointer;
|
2018-07-27 04:20:10 +08:00
|
|
|
|
|
|
|
if (HasThisQuals) {
|
2018-07-30 00:38:02 +08:00
|
|
|
FTy->Quals = demanglePointerExtQualifiers(MangledName);
|
|
|
|
FTy->RefKind = demangleReferenceKind(MangledName);
|
|
|
|
FTy->Quals = Qualifiers(FTy->Quals | demangleQualifiers(MangledName).first);
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// Fields that appear on both member and non-member functions.
|
2018-07-30 00:38:02 +08:00
|
|
|
FTy->CallConvention = demangleCallingConvention(MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
// <return-type> ::= <type>
|
|
|
|
// ::= @ # structors (they have no declared return type)
|
|
|
|
bool IsStructor = MangledName.consumeFront('@');
|
|
|
|
if (!IsStructor)
|
2018-07-30 00:38:02 +08:00
|
|
|
FTy->ReturnType = demangleType(MangledName, QualifierMangleMode::Result);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
FTy->Params = demangleFunctionParameterList(MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
demangleThrowSpecification(MangledName);
|
2018-07-27 04:20:10 +08:00
|
|
|
|
|
|
|
return FTy;
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Type *Demangler::demangleFunctionEncoding(StringView &MangledName) {
|
2018-08-18 05:18:05 +08:00
|
|
|
FuncClass ExtraFlags = FuncClass::None;
|
|
|
|
if (MangledName.consumeFront("$$J0"))
|
|
|
|
ExtraFlags = FuncClass::ExternC;
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
FuncClass FC = demangleFunctionClass(MangledName);
|
2018-08-18 05:18:05 +08:00
|
|
|
FC = FuncClass(ExtraFlags | FC);
|
|
|
|
|
|
|
|
FunctionType::ThisAdjustor *Adjustor = nullptr;
|
|
|
|
if (FC & FuncClass::StaticThisAdjust) {
|
|
|
|
Adjustor = Arena.alloc<FunctionType::ThisAdjustor>();
|
|
|
|
Adjustor->StaticOffset = demangleSigned(MangledName);
|
|
|
|
} else if (FC & FuncClass::VirtualThisAdjust) {
|
|
|
|
Adjustor = Arena.alloc<FunctionType::ThisAdjustor>();
|
|
|
|
if (FC & FuncClass::VirtualThisAdjustEx) {
|
|
|
|
Adjustor->VBPtrOffset = demangleSigned(MangledName);
|
|
|
|
Adjustor->VBOffsetOffset = demangleSigned(MangledName);
|
|
|
|
}
|
|
|
|
Adjustor->VtordispOffset = demangleSigned(MangledName);
|
|
|
|
Adjustor->StaticOffset = demangleSigned(MangledName);
|
|
|
|
}
|
|
|
|
|
2018-08-11 05:09:05 +08:00
|
|
|
FunctionType *FTy = nullptr;
|
|
|
|
if (FC & NoPrototype) {
|
|
|
|
// This is an extern "C" function whose full signature hasn't been mangled.
|
|
|
|
// This happens when we need to mangle a local symbol inside of an extern
|
|
|
|
// "C" function.
|
|
|
|
FTy = Arena.alloc<FunctionType>();
|
|
|
|
} else {
|
|
|
|
bool HasThisQuals = !(FC & (Global | Static));
|
|
|
|
FTy = demangleFunctionType(MangledName, HasThisQuals, false);
|
|
|
|
}
|
2018-08-18 05:18:05 +08:00
|
|
|
FTy->ThisAdjust = Adjustor;
|
2018-07-27 04:20:10 +08:00
|
|
|
FTy->FunctionClass = FC;
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
return FTy;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Reads a primitive type.
|
2018-07-30 00:38:02 +08:00
|
|
|
Type *Demangler::demangleBasicType(StringView &MangledName) {
|
2018-07-21 02:35:06 +08:00
|
|
|
Type *Ty = Arena.alloc<Type>();
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-31 07:02:10 +08:00
|
|
|
if (MangledName.consumeFront("$$T")) {
|
|
|
|
Ty->Prim = PrimTy::Nullptr;
|
|
|
|
return Ty;
|
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
switch (MangledName.popFront()) {
|
|
|
|
case 'X':
|
|
|
|
Ty->Prim = PrimTy::Void;
|
|
|
|
break;
|
|
|
|
case 'D':
|
|
|
|
Ty->Prim = PrimTy::Char;
|
|
|
|
break;
|
|
|
|
case 'C':
|
|
|
|
Ty->Prim = PrimTy::Schar;
|
|
|
|
break;
|
|
|
|
case 'E':
|
|
|
|
Ty->Prim = PrimTy::Uchar;
|
|
|
|
break;
|
|
|
|
case 'F':
|
|
|
|
Ty->Prim = PrimTy::Short;
|
|
|
|
break;
|
|
|
|
case 'G':
|
|
|
|
Ty->Prim = PrimTy::Ushort;
|
|
|
|
break;
|
|
|
|
case 'H':
|
|
|
|
Ty->Prim = PrimTy::Int;
|
|
|
|
break;
|
|
|
|
case 'I':
|
|
|
|
Ty->Prim = PrimTy::Uint;
|
|
|
|
break;
|
|
|
|
case 'J':
|
|
|
|
Ty->Prim = PrimTy::Long;
|
|
|
|
break;
|
|
|
|
case 'K':
|
|
|
|
Ty->Prim = PrimTy::Ulong;
|
|
|
|
break;
|
|
|
|
case 'M':
|
|
|
|
Ty->Prim = PrimTy::Float;
|
|
|
|
break;
|
|
|
|
case 'N':
|
|
|
|
Ty->Prim = PrimTy::Double;
|
|
|
|
break;
|
|
|
|
case 'O':
|
|
|
|
Ty->Prim = PrimTy::Ldouble;
|
|
|
|
break;
|
|
|
|
case '_': {
|
2018-07-21 02:07:33 +08:00
|
|
|
if (MangledName.empty()) {
|
|
|
|
Error = true;
|
|
|
|
return nullptr;
|
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
switch (MangledName.popFront()) {
|
|
|
|
case 'N':
|
|
|
|
Ty->Prim = PrimTy::Bool;
|
|
|
|
break;
|
|
|
|
case 'J':
|
|
|
|
Ty->Prim = PrimTy::Int64;
|
|
|
|
break;
|
|
|
|
case 'K':
|
|
|
|
Ty->Prim = PrimTy::Uint64;
|
|
|
|
break;
|
|
|
|
case 'W':
|
|
|
|
Ty->Prim = PrimTy::Wchar;
|
|
|
|
break;
|
2018-07-31 07:02:10 +08:00
|
|
|
case 'S':
|
|
|
|
Ty->Prim = PrimTy::Char16;
|
|
|
|
break;
|
|
|
|
case 'U':
|
|
|
|
Ty->Prim = PrimTy::Char32;
|
|
|
|
break;
|
2018-07-21 02:07:33 +08:00
|
|
|
default:
|
2018-07-31 07:02:10 +08:00
|
|
|
Error = true;
|
|
|
|
return nullptr;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
break;
|
|
|
|
}
|
2018-07-31 07:02:10 +08:00
|
|
|
default:
|
|
|
|
Error = true;
|
|
|
|
return nullptr;
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
return Ty;
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
UdtType *Demangler::demangleClassType(StringView &MangledName) {
|
2018-07-21 02:35:06 +08:00
|
|
|
UdtType *UTy = Arena.alloc<UdtType>();
|
2018-07-21 01:27:48 +08:00
|
|
|
|
|
|
|
switch (MangledName.popFront()) {
|
|
|
|
case 'T':
|
|
|
|
UTy->Prim = PrimTy::Union;
|
|
|
|
break;
|
|
|
|
case 'U':
|
|
|
|
UTy->Prim = PrimTy::Struct;
|
|
|
|
break;
|
|
|
|
case 'V':
|
|
|
|
UTy->Prim = PrimTy::Class;
|
|
|
|
break;
|
|
|
|
case 'W':
|
|
|
|
if (MangledName.popFront() != '4') {
|
|
|
|
Error = true;
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
UTy->Prim = PrimTy::Enum;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
assert(false);
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
UTy->UdtName = demangleFullyQualifiedTypeName(MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
return UTy;
|
|
|
|
}
|
|
|
|
|
2018-07-27 03:56:09 +08:00
|
|
|
static std::pair<Qualifiers, PointerAffinity>
|
|
|
|
demanglePointerCVQualifiers(StringView &MangledName) {
|
2018-07-31 07:02:10 +08:00
|
|
|
if (MangledName.consumeFront("$$Q"))
|
|
|
|
return std::make_pair(Q_None, PointerAffinity::RValueReference);
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
switch (MangledName.popFront()) {
|
|
|
|
case 'A':
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Q_None, PointerAffinity::Reference);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'P':
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Q_None, PointerAffinity::Pointer);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'Q':
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Q_Const, PointerAffinity::Pointer);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'R':
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Q_Volatile, PointerAffinity::Pointer);
|
2018-07-21 01:27:48 +08:00
|
|
|
case 'S':
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Qualifiers(Q_Const | Q_Volatile),
|
|
|
|
PointerAffinity::Pointer);
|
2018-07-21 01:27:48 +08:00
|
|
|
default:
|
|
|
|
assert(false && "Ty is not a pointer type!");
|
|
|
|
}
|
2018-07-27 03:56:09 +08:00
|
|
|
return std::make_pair(Q_None, PointerAffinity::Pointer);
|
|
|
|
}
|
|
|
|
|
|
|
|
// <pointer-type> ::= E? <pointer-cvr-qualifiers> <ext-qualifiers> <type>
|
|
|
|
// # the E is required for 64-bit non-static pointers
|
2018-07-30 00:38:02 +08:00
|
|
|
PointerType *Demangler::demanglePointerType(StringView &MangledName) {
|
2018-07-27 03:56:09 +08:00
|
|
|
PointerType *Pointer = Arena.alloc<PointerType>();
|
|
|
|
|
2018-07-31 07:02:10 +08:00
|
|
|
std::tie(Pointer->Quals, Pointer->Affinity) =
|
|
|
|
demanglePointerCVQualifiers(MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-31 07:02:10 +08:00
|
|
|
Pointer->Prim = PrimTy::Ptr;
|
2018-07-21 01:27:48 +08:00
|
|
|
if (MangledName.consumeFront("6")) {
|
2018-07-30 00:38:02 +08:00
|
|
|
Pointer->Pointee = demangleFunctionType(MangledName, false, true);
|
2018-07-21 01:27:48 +08:00
|
|
|
return Pointer;
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Qualifiers ExtQuals = demanglePointerExtQualifiers(MangledName);
|
2018-07-21 01:27:48 +08:00
|
|
|
Pointer->Quals = Qualifiers(Pointer->Quals | ExtQuals);
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Pointer->Pointee = demangleType(MangledName, QualifierMangleMode::Mangle);
|
2018-07-21 01:27:48 +08:00
|
|
|
return Pointer;
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
MemberPointerType *
|
|
|
|
Demangler::demangleMemberPointerType(StringView &MangledName) {
|
2018-07-27 03:56:09 +08:00
|
|
|
MemberPointerType *Pointer = Arena.alloc<MemberPointerType>();
|
|
|
|
Pointer->Prim = PrimTy::MemberPtr;
|
|
|
|
|
|
|
|
PointerAffinity Affinity;
|
|
|
|
std::tie(Pointer->Quals, Affinity) = demanglePointerCVQualifiers(MangledName);
|
|
|
|
assert(Affinity == PointerAffinity::Pointer);
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Qualifiers ExtQuals = demanglePointerExtQualifiers(MangledName);
|
2018-07-27 03:56:09 +08:00
|
|
|
Pointer->Quals = Qualifiers(Pointer->Quals | ExtQuals);
|
|
|
|
|
2018-07-27 04:20:10 +08:00
|
|
|
if (MangledName.consumeFront("8")) {
|
2018-07-30 00:38:02 +08:00
|
|
|
Pointer->MemberName = demangleFullyQualifiedSymbolName(MangledName);
|
|
|
|
Pointer->Pointee = demangleFunctionType(MangledName, true, true);
|
2018-07-27 04:20:10 +08:00
|
|
|
} else {
|
|
|
|
Qualifiers PointeeQuals = Q_None;
|
|
|
|
bool IsMember = false;
|
2018-07-30 00:38:02 +08:00
|
|
|
std::tie(PointeeQuals, IsMember) = demangleQualifiers(MangledName);
|
2018-07-27 04:20:10 +08:00
|
|
|
assert(IsMember);
|
2018-07-30 00:38:02 +08:00
|
|
|
Pointer->MemberName = demangleFullyQualifiedSymbolName(MangledName);
|
2018-07-27 04:20:10 +08:00
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Pointer->Pointee = demangleType(MangledName, QualifierMangleMode::Drop);
|
2018-07-27 04:20:10 +08:00
|
|
|
Pointer->Pointee->Quals = PointeeQuals;
|
|
|
|
}
|
2018-07-27 03:56:09 +08:00
|
|
|
|
|
|
|
return Pointer;
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
Qualifiers Demangler::demanglePointerExtQualifiers(StringView &MangledName) {
|
2018-07-21 01:27:48 +08:00
|
|
|
Qualifiers Quals = Q_None;
|
|
|
|
if (MangledName.consumeFront('E'))
|
|
|
|
Quals = Qualifiers(Quals | Q_Pointer64);
|
|
|
|
if (MangledName.consumeFront('I'))
|
|
|
|
Quals = Qualifiers(Quals | Q_Restrict);
|
|
|
|
if (MangledName.consumeFront('F'))
|
|
|
|
Quals = Qualifiers(Quals | Q_Unaligned);
|
|
|
|
|
|
|
|
return Quals;
|
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
ArrayType *Demangler::demangleArrayType(StringView &MangledName) {
|
2018-07-21 01:27:48 +08:00
|
|
|
assert(MangledName.front() == 'Y');
|
|
|
|
MangledName.popFront();
|
|
|
|
|
2018-08-10 22:31:04 +08:00
|
|
|
uint64_t Rank = 0;
|
|
|
|
bool IsNegative = false;
|
|
|
|
std::tie(Rank, IsNegative) = demangleNumber(MangledName);
|
|
|
|
if (IsNegative || Rank == 0) {
|
2018-07-21 01:27:48 +08:00
|
|
|
Error = true;
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
|
2018-07-21 02:35:06 +08:00
|
|
|
ArrayType *ATy = Arena.alloc<ArrayType>();
|
2018-08-10 22:31:04 +08:00
|
|
|
ATy->Prim = PrimTy::Array;
|
|
|
|
ATy->Dims = Arena.alloc<ArrayDimension>();
|
|
|
|
ArrayDimension *Dim = ATy->Dims;
|
|
|
|
for (uint64_t I = 0; I < Rank; ++I) {
|
|
|
|
std::tie(Dim->Dim, IsNegative) = demangleNumber(MangledName);
|
|
|
|
if (IsNegative) {
|
|
|
|
Error = true;
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
if (I + 1 < Rank) {
|
|
|
|
Dim->Next = Arena.alloc<ArrayDimension>();
|
|
|
|
Dim = Dim->Next;
|
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (MangledName.consumeFront("$$C")) {
|
2018-08-15 02:54:28 +08:00
|
|
|
bool IsMember = false;
|
|
|
|
std::tie(ATy->Quals, IsMember) = demangleQualifiers(MangledName);
|
|
|
|
if (IsMember) {
|
2018-07-21 01:27:48 +08:00
|
|
|
Error = true;
|
2018-08-15 02:54:28 +08:00
|
|
|
return nullptr;
|
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
ATy->ElementType = demangleType(MangledName, QualifierMangleMode::Drop);
|
2018-07-21 01:27:48 +08:00
|
|
|
return ATy;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Reads a function or a template parameters.
|
2018-08-01 01:16:44 +08:00
|
|
|
FunctionParams
|
|
|
|
Demangler::demangleFunctionParameterList(StringView &MangledName) {
|
2018-07-27 04:20:10 +08:00
|
|
|
// Empty parameter list.
|
|
|
|
if (MangledName.consumeFront('X'))
|
|
|
|
return {};
|
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
FunctionParams *Head;
|
|
|
|
FunctionParams **Current = &Head;
|
2018-07-21 01:27:48 +08:00
|
|
|
while (!Error && !MangledName.startsWith('@') &&
|
|
|
|
!MangledName.startsWith('Z')) {
|
2018-07-27 06:13:39 +08:00
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
if (startsWithDigit(MangledName)) {
|
2018-07-27 06:24:01 +08:00
|
|
|
size_t N = MangledName[0] - '0';
|
2018-08-09 01:17:04 +08:00
|
|
|
if (N >= Backrefs.FunctionParamCount) {
|
2018-07-21 01:27:48 +08:00
|
|
|
Error = true;
|
|
|
|
return {};
|
|
|
|
}
|
|
|
|
MangledName = MangledName.dropFront();
|
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
*Current = Arena.alloc<FunctionParams>();
|
2018-08-09 01:17:04 +08:00
|
|
|
(*Current)->Current = Backrefs.FunctionParams[N]->clone(Arena);
|
2018-07-21 01:27:48 +08:00
|
|
|
Current = &(*Current)->Next;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2018-07-27 06:13:39 +08:00
|
|
|
size_t OldSize = MangledName.size();
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
*Current = Arena.alloc<FunctionParams>();
|
2018-07-30 00:38:02 +08:00
|
|
|
(*Current)->Current = demangleType(MangledName, QualifierMangleMode::Drop);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-07-27 06:13:39 +08:00
|
|
|
size_t CharsConsumed = OldSize - MangledName.size();
|
|
|
|
assert(CharsConsumed != 0);
|
|
|
|
|
|
|
|
// Single-letter types are ignored for backreferences because memorizing
|
|
|
|
// them doesn't save anything.
|
2018-08-09 01:17:04 +08:00
|
|
|
if (Backrefs.FunctionParamCount <= 9 && CharsConsumed > 1)
|
|
|
|
Backrefs.FunctionParams[Backrefs.FunctionParamCount++] =
|
|
|
|
(*Current)->Current;
|
2018-07-27 06:13:39 +08:00
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
Current = &(*Current)->Next;
|
|
|
|
}
|
|
|
|
|
2018-07-27 04:20:10 +08:00
|
|
|
if (Error)
|
|
|
|
return {};
|
|
|
|
|
|
|
|
// A non-empty parameter list is terminated by either 'Z' (variadic) parameter
|
|
|
|
// list or '@' (non variadic). Careful not to consume "@Z", as in that case
|
|
|
|
// the following Z could be a throw specifier.
|
|
|
|
if (MangledName.consumeFront('@'))
|
|
|
|
return *Head;
|
|
|
|
|
|
|
|
if (MangledName.consumeFront('Z')) {
|
|
|
|
Head->IsVariadic = true;
|
|
|
|
return *Head;
|
|
|
|
}
|
|
|
|
|
|
|
|
Error = true;
|
|
|
|
return {};
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
TemplateParams *
|
|
|
|
Demangler::demangleTemplateParameterList(StringView &MangledName) {
|
|
|
|
TemplateParams *Head;
|
|
|
|
TemplateParams **Current = &Head;
|
2018-07-27 06:13:39 +08:00
|
|
|
while (!Error && !MangledName.startsWith('@')) {
|
|
|
|
// Template parameter lists don't participate in back-referencing.
|
2018-08-01 01:16:44 +08:00
|
|
|
*Current = Arena.alloc<TemplateParams>();
|
2018-07-31 07:02:10 +08:00
|
|
|
|
2018-08-21 03:15:35 +08:00
|
|
|
TemplateParams &TP = **Current;
|
|
|
|
|
2018-07-31 07:02:10 +08:00
|
|
|
// Empty parameter pack.
|
|
|
|
if (MangledName.consumeFront("$S") || MangledName.consumeFront("$$V") ||
|
|
|
|
MangledName.consumeFront("$$$V")) {
|
2018-08-21 03:15:35 +08:00
|
|
|
TP.IsEmptyParameterPack = true;
|
2018-08-02 02:32:28 +08:00
|
|
|
break;
|
2018-07-31 07:02:10 +08:00
|
|
|
}
|
|
|
|
|
2018-08-01 01:16:44 +08:00
|
|
|
if (MangledName.consumeFront("$$Y")) {
|
2018-08-10 22:31:04 +08:00
|
|
|
// Template alias
|
2018-08-21 03:15:35 +08:00
|
|
|
TP.IsTemplateTemplate = true;
|
|
|
|
TP.IsAliasTemplate = true;
|
|
|
|
TP.ParamName = demangleFullyQualifiedTypeName(MangledName);
|
2018-08-10 22:31:04 +08:00
|
|
|
} else if (MangledName.consumeFront("$$B")) {
|
|
|
|
// Array
|
2018-08-21 03:15:35 +08:00
|
|
|
TP.ParamType = demangleType(MangledName, QualifierMangleMode::Drop);
|
2018-08-11 03:57:36 +08:00
|
|
|
} else if (MangledName.consumeFront("$$C")) {
|
|
|
|
// Type has qualifiers.
|
2018-08-21 03:15:35 +08:00
|
|
|
TP.ParamType = demangleType(MangledName, QualifierMangleMode::Mangle);
|
|
|
|
} else if (MangledName.startsWith("$1") || MangledName.startsWith("$H") ||
|
|
|
|
MangledName.startsWith("$I") || MangledName.startsWith("$J")) {
|
|
|
|
MangledName = MangledName.dropFront();
|
|
|
|
// 1 - single inheritance <name>
|
|
|
|
// H - multiple inheritance <name> <number>
|
|
|
|
// I - virtual inheritance <name> <number> <number> <number>
|
|
|
|
// J - unspecified inheritance <name> <number> <number> <number>
|
|
|
|
char InheritanceSpecifier = MangledName.popFront();
|
|
|
|
// Pointer to member
|
|
|
|
Symbol *S = MangledName.startsWith('?') ? parse(MangledName) : nullptr;
|
|
|
|
switch (InheritanceSpecifier) {
|
|
|
|
case 'J':
|
|
|
|
TP.ThunkOffsets[TP.ThunkOffsetCount++] = demangleSigned(MangledName);
|
|
|
|
LLVM_FALLTHROUGH;
|
|
|
|
case 'I':
|
|
|
|
TP.ThunkOffsets[TP.ThunkOffsetCount++] = demangleSigned(MangledName);
|
|
|
|
LLVM_FALLTHROUGH;
|
|
|
|
case 'H':
|
|
|
|
TP.ThunkOffsets[TP.ThunkOffsetCount++] = demangleSigned(MangledName);
|
|
|
|
LLVM_FALLTHROUGH;
|
|
|
|
case '1':
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
Error = true;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
TP.PointerToSymbol = true;
|
|
|
|
if (S) {
|
|
|
|
TP.ParamName = S->SymbolName;
|
|
|
|
TP.ParamType = S->SymbolType;
|
|
|
|
} else
|
|
|
|
TP.NullptrLiteral = true;
|
2018-08-10 22:31:04 +08:00
|
|
|
} else if (MangledName.startsWith("$E?")) {
|
|
|
|
MangledName.consumeFront("$E");
|
|
|
|
// Reference to symbol
|
|
|
|
Symbol *S = parse(MangledName);
|
2018-08-21 03:15:35 +08:00
|
|
|
TP.ParamName = S->SymbolName;
|
|
|
|
TP.ParamType = S->SymbolType;
|
|
|
|
TP.ReferenceToSymbol = true;
|
|
|
|
} else if (MangledName.startsWith("$F") || MangledName.startsWith("$G")) {
|
|
|
|
// Data member pointer.
|
|
|
|
MangledName = MangledName.dropFront();
|
|
|
|
char InheritanceSpecifier = MangledName.popFront();
|
|
|
|
|
|
|
|
switch (InheritanceSpecifier) {
|
|
|
|
case 'G':
|
|
|
|
TP.ThunkOffsets[TP.ThunkOffsetCount++] = demangleSigned(MangledName);
|
|
|
|
LLVM_FALLTHROUGH;
|
|
|
|
case 'F':
|
|
|
|
TP.ThunkOffsets[TP.ThunkOffsetCount++] = demangleSigned(MangledName);
|
|
|
|
TP.ThunkOffsets[TP.ThunkOffsetCount++] = demangleSigned(MangledName);
|
|
|
|
LLVM_FALLTHROUGH;
|
|
|
|
case '0':
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
Error = true;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
TP.DataMemberPointer = true;
|
|
|
|
|
2018-08-10 22:31:04 +08:00
|
|
|
} else if (MangledName.consumeFront("$0")) {
|
|
|
|
// Integral non-type template parameter
|
|
|
|
bool IsNegative = false;
|
|
|
|
uint64_t Value = 0;
|
|
|
|
std::tie(Value, IsNegative) = demangleNumber(MangledName);
|
|
|
|
|
2018-08-21 03:15:35 +08:00
|
|
|
TP.IsIntegerLiteral = true;
|
|
|
|
TP.IntegerLiteralIsNegative = IsNegative;
|
|
|
|
TP.IntegralValue = Value;
|
2018-08-01 01:16:44 +08:00
|
|
|
} else {
|
2018-08-21 03:15:35 +08:00
|
|
|
TP.ParamType = demangleType(MangledName, QualifierMangleMode::Drop);
|
2018-08-01 01:16:44 +08:00
|
|
|
}
|
2018-08-02 02:32:28 +08:00
|
|
|
if (Error)
|
|
|
|
return nullptr;
|
2018-07-27 06:13:39 +08:00
|
|
|
|
2018-08-21 03:15:35 +08:00
|
|
|
Current = &TP.Next;
|
2018-07-27 06:13:39 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (Error)
|
2018-08-02 02:32:28 +08:00
|
|
|
return nullptr;
|
2018-07-27 06:13:39 +08:00
|
|
|
|
|
|
|
// Template parameter lists cannot be variadic, so it can only be terminated
|
|
|
|
// by @.
|
|
|
|
if (MangledName.consumeFront('@'))
|
2018-07-31 07:02:10 +08:00
|
|
|
return Head;
|
2018-07-27 06:13:39 +08:00
|
|
|
Error = true;
|
2018-08-02 02:32:28 +08:00
|
|
|
return nullptr;
|
2018-07-27 06:13:39 +08:00
|
|
|
}
|
|
|
|
|
2018-07-30 00:38:02 +08:00
|
|
|
void Demangler::output(const Symbol *S, OutputStream &OS) {
|
2018-08-17 00:17:17 +08:00
|
|
|
if (S->Category == SymbolCategory::Unknown) {
|
2018-08-19 02:49:48 +08:00
|
|
|
outputName(OS, S->SymbolName, S->SymbolType);
|
2018-08-17 00:17:17 +08:00
|
|
|
return;
|
|
|
|
}
|
2018-08-17 00:17:36 +08:00
|
|
|
|
2018-08-18 05:18:05 +08:00
|
|
|
if (S->Category == SymbolCategory::SpecialOperator) {
|
2018-08-19 02:49:48 +08:00
|
|
|
outputSpecialOperator(OS, S->SymbolName);
|
2018-08-18 05:18:05 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
// Converts an AST to a string.
|
|
|
|
//
|
|
|
|
// Converting an AST representing a C++ type to a string is tricky due
|
|
|
|
// to the bad grammar of the C++ declaration inherited from C. You have
|
|
|
|
// to construct a string from inside to outside. For example, if a type
|
|
|
|
// X is a pointer to a function returning int, the order you create a
|
|
|
|
// string becomes something like this:
|
|
|
|
//
|
|
|
|
// (1) X is a pointer: *X
|
|
|
|
// (2) (1) is a function returning int: int (*X)()
|
|
|
|
//
|
|
|
|
// So you cannot construct a result just by appending strings to a result.
|
|
|
|
//
|
|
|
|
// To deal with this, we split the function into two. outputPre() writes
|
|
|
|
// the "first half" of type declaration, and outputPost() writes the
|
|
|
|
// "second half". For example, outputPre() writes a return type for a
|
|
|
|
// function and outputPost() writes an parameter list.
|
2018-08-18 00:14:05 +08:00
|
|
|
if (S->SymbolType) {
|
2018-08-19 02:49:48 +08:00
|
|
|
Type::outputPre(OS, *S->SymbolType);
|
|
|
|
outputName(OS, S->SymbolName, S->SymbolType);
|
|
|
|
Type::outputPost(OS, *S->SymbolType);
|
2018-08-18 05:18:05 +08:00
|
|
|
} else {
|
|
|
|
outputQualifiers(OS, S->SymbolQuals);
|
2018-08-19 02:49:48 +08:00
|
|
|
outputName(OS, S->SymbolName, nullptr);
|
2018-08-18 05:18:05 +08:00
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
}
|
|
|
|
|
2018-08-02 02:33:04 +08:00
|
|
|
void Demangler::dumpBackReferences() {
|
2018-08-02 02:44:12 +08:00
|
|
|
std::printf("%d function parameter backreferences\n",
|
2018-08-09 01:17:04 +08:00
|
|
|
(int)Backrefs.FunctionParamCount);
|
2018-08-02 02:33:04 +08:00
|
|
|
|
|
|
|
// Create an output stream so we can render each type.
|
|
|
|
OutputStream OS = OutputStream::create(nullptr, 0, 1024);
|
2018-08-09 01:17:04 +08:00
|
|
|
for (size_t I = 0; I < Backrefs.FunctionParamCount; ++I) {
|
2018-08-02 02:33:04 +08:00
|
|
|
OS.setCurrentPosition(0);
|
|
|
|
|
2018-08-09 01:17:04 +08:00
|
|
|
Type *T = Backrefs.FunctionParams[I];
|
2018-08-19 02:49:48 +08:00
|
|
|
Type::outputPre(OS, *T);
|
|
|
|
Type::outputPost(OS, *T);
|
2018-08-02 02:33:04 +08:00
|
|
|
|
2018-08-03 01:08:24 +08:00
|
|
|
std::printf(" [%d] - %.*s\n", (int)I, (int)OS.getCurrentPosition(),
|
2018-08-02 02:44:12 +08:00
|
|
|
OS.getBuffer());
|
2018-08-02 02:33:04 +08:00
|
|
|
}
|
|
|
|
std::free(OS.getBuffer());
|
|
|
|
|
2018-08-09 01:17:04 +08:00
|
|
|
if (Backrefs.FunctionParamCount > 0)
|
2018-08-02 02:44:12 +08:00
|
|
|
std::printf("\n");
|
2018-08-09 01:17:04 +08:00
|
|
|
std::printf("%d name backreferences\n", (int)Backrefs.NamesCount);
|
|
|
|
for (size_t I = 0; I < Backrefs.NamesCount; ++I) {
|
|
|
|
std::printf(" [%d] - %.*s\n", (int)I, (int)Backrefs.Names[I].size(),
|
|
|
|
Backrefs.Names[I].begin());
|
2018-08-02 02:33:04 +08:00
|
|
|
}
|
2018-08-09 01:17:04 +08:00
|
|
|
if (Backrefs.NamesCount > 0)
|
2018-08-02 02:44:12 +08:00
|
|
|
std::printf("\n");
|
2018-08-02 02:33:04 +08:00
|
|
|
}
|
|
|
|
|
2018-07-21 01:27:48 +08:00
|
|
|
char *llvm::microsoftDemangle(const char *MangledName, char *Buf, size_t *N,
|
2018-08-02 02:33:04 +08:00
|
|
|
int *Status, MSDemangleFlags Flags) {
|
2018-07-30 00:38:02 +08:00
|
|
|
Demangler D;
|
|
|
|
StringView Name{MangledName};
|
|
|
|
Symbol *S = D.parse(Name);
|
2018-07-21 01:27:48 +08:00
|
|
|
|
2018-08-02 02:33:04 +08:00
|
|
|
if (Flags & MSDF_DumpBackrefs)
|
|
|
|
D.dumpBackReferences();
|
2018-08-02 02:32:28 +08:00
|
|
|
OutputStream OS = OutputStream::create(Buf, N, 1024);
|
|
|
|
if (D.Error) {
|
|
|
|
OS << MangledName;
|
2018-07-21 01:27:48 +08:00
|
|
|
*Status = llvm::demangle_invalid_mangled_name;
|
2018-08-02 02:32:28 +08:00
|
|
|
} else {
|
|
|
|
D.output(S, OS);
|
2018-07-21 01:27:48 +08:00
|
|
|
*Status = llvm::demangle_success;
|
2018-08-02 02:32:28 +08:00
|
|
|
}
|
2018-07-21 01:27:48 +08:00
|
|
|
|
[MS Demangler] Demangle symbols in function scopes.
There are a couple of issues you run into when you start getting into
more complex names, especially with regards to function local statics.
When you've got something like:
int x() {
static int n = 0;
return n;
}
Then this needs to demangle to something like
int `int __cdecl x()'::`1'::n
The nested mangled symbols (e.g. `int __cdecl x()` in the above
example) also share state with regards to back-referencing, so
we need to be able to re-use the demangler in the middle of
demangling a symbol while sharing back-ref state.
To make matters more complicated, there are a lot of ambiguities
when demangling a symbol's qualified name, because a function local
scope pattern (usually something like `?1??name?`) looks suspiciously
like many other possible things that can occur, such as `?1` meaning
the second back-ref and disambiguating these cases is rather
interesting. The `?1?` in a local scope pattern is actually a special
case of the more general pattern of `? + <encoded number> + ?`, where
"encoded number" can itself have embedded `@` symbols, which is a
common delimeter in mangled names. So we have to take care during the
disambiguation, which is the reason for the overly complicated
`isLocalScopePattern` function in this patch.
I've added some pretty obnoxious tests to exercise all of this, which
exposed several other problems related to back-referencing, so those
are fixed here as well. Finally, I've uncommented some tests that were
previously marked as `FIXME`, since now these work.
Differential Revision: https://reviews.llvm.org/D49965
llvm-svn: 338226
2018-07-30 11:12:34 +08:00
|
|
|
OS << '\0';
|
2018-07-21 01:27:48 +08:00
|
|
|
return OS.getBuffer();
|
|
|
|
}
|