RustDemangle.cpp | Explore in Territory

//===--- RustDemangle.cpp ---------------------------------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file defines a demangler for Rust v0 mangled symbols as specified in
// https://rust-lang.github.io/rfcs/2603-rust-symbol-name-mangling-v0.html
//
//===----------------------------------------------------------------------===//

#include "llvm/Demangle/Demangle.h"
#include "llvm/Demangle/StringViewExtras.h"
#include "llvm/Demangle/Utility.h"

#include <algorithm>
#include <cassert>
#include <cstdint>
#include <cstring>
#include <limits>
#include <string_view>

usingnamespacellvm;

OutputBuffer;
ScopedOverride;
starts_with;

namespace {

struct Identifier { … };

enum class BasicType { … };

enum class IsInType { … };

enum class LeaveGenericsOpen { … };

class Demangler { … };

} // namespace

char *llvm::rustDemangle(std::string_view MangledName) { … }

Demangler::Demangler(size_t MaxRecursionLevel)
    : … { … }

static inline bool isDigit(const char C) { … }

static inline bool isHexDigit(const char C) { … }

static inline bool isLower(const char C) { … }

static inline bool isUpper(const char C) { … }

/// Returns true if C is a valid mangled character: <0-9a-zA-Z_>.
static inline bool isValid(const char C) { … }

// Demangles Rust v0 mangled symbol. Returns true when successful, and false
// otherwise. The demangled symbol is stored in Output field. It is
// responsibility of the caller to free the memory behind the output stream.
//
// <symbol-name> = "_R" <path> [<instantiating-crate>]
bool Demangler::demangle(std::string_view Mangled) { … }

// Demangles a path. InType indicates whether a path is inside a type. When
// LeaveOpen is true, a closing `>` after generic arguments is omitted from the
// output. Return value indicates whether generics arguments have been left
// open.
//
// <path> = "C" <identifier>               // crate root
//        | "M" <impl-path> <type>         // <T> (inherent impl)
//        | "X" <impl-path> <type> <path>  // <T as Trait> (trait impl)
//        | "Y" <type> <path>              // <T as Trait> (trait definition)
//        | "N" <ns> <path> <identifier>   // ...::ident (nested path)
//        | "I" <path> {<generic-arg>} "E" // ...<T, U> (generic args)
//        | <backref>
// <identifier> = [<disambiguator>] <undisambiguated-identifier>
// <ns> = "C"      // closure
//      | "S"      // shim
//      | <A-Z>    // other special namespaces
//      | <a-z>    // internal namespaces
bool Demangler::demanglePath(IsInType InType, LeaveGenericsOpen LeaveOpen) { … }

// <impl-path> = [<disambiguator>] <path>
// <disambiguator> = "s" <base-62-number>
void Demangler::demangleImplPath(IsInType InType) { … }

// <generic-arg> = <lifetime>
//               | <type>
//               | "K" <const>
// <lifetime> = "L" <base-62-number>
void Demangler::demangleGenericArg() { … }

// <basic-type> = "a"      // i8
//              | "b"      // bool
//              | "c"      // char
//              | "d"      // f64
//              | "e"      // str
//              | "f"      // f32
//              | "h"      // u8
//              | "i"      // isize
//              | "j"      // usize
//              | "l"      // i32
//              | "m"      // u32
//              | "n"      // i128
//              | "o"      // u128
//              | "s"      // i16
//              | "t"      // u16
//              | "u"      // ()
//              | "v"      // ...
//              | "x"      // i64
//              | "y"      // u64
//              | "z"      // !
//              | "p"      // placeholder (e.g. for generic params), shown as _
static bool parseBasicType(char C, BasicType &Type) { … }

void Demangler::printBasicType(BasicType Type) { … }

// <type> = | <basic-type>
//          | <path>                      // named type
//          | "A" <type> <const>          // [T; N]
//          | "S" <type>                  // [T]
//          | "T" {<type>} "E"            // (T1, T2, T3, ...)
//          | "R" [<lifetime>] <type>     // &T
//          | "Q" [<lifetime>] <type>     // &mut T
//          | "P" <type>                  // *const T
//          | "O" <type>                  // *mut T
//          | "F" <fn-sig>                // fn(...) -> ...
//          | "D" <dyn-bounds> <lifetime> // dyn Trait<Assoc = X> + Send + 'a
//          | <backref>                   // backref
void Demangler::demangleType() { … }

// <fn-sig> := [<binder>] ["U"] ["K" <abi>] {<type>} "E" <type>
// <abi> = "C"
//       | <undisambiguated-identifier>
void Demangler::demangleFnSig() { … }

// <dyn-bounds> = [<binder>] {<dyn-trait>} "E"
void Demangler::demangleDynBounds() { … }

// <dyn-trait> = <path> {<dyn-trait-assoc-binding>}
// <dyn-trait-assoc-binding> = "p" <undisambiguated-identifier> <type>
void Demangler::demangleDynTrait() { … }

// Demangles optional binder and updates the number of bound lifetimes.
//
// <binder> = "G" <base-62-number>
void Demangler::demangleOptionalBinder() { … }

// <const> = <basic-type> <const-data>
//         | "p"                          // placeholder
//         | <backref>
void Demangler::demangleConst() { … }

// <const-data> = ["n"] <hex-number>
void Demangler::demangleConstInt() { … }

// <const-data> = "0_" // false
//              | "1_" // true
void Demangler::demangleConstBool() { … }

/// Returns true if CodePoint represents a printable ASCII character.
static bool isAsciiPrintable(uint64_t CodePoint) { … }

// <const-data> = <hex-number>
void Demangler::demangleConstChar() { … }

// <undisambiguated-identifier> = ["u"] <decimal-number> ["_"] <bytes>
Identifier Demangler::parseIdentifier() { … }

// Parses optional base 62 number. The presence of a number is determined using
// Tag. Returns 0 when tag is absent and parsed value + 1 otherwise
//
// This function is intended for parsing disambiguators and binders which when
// not present have their value interpreted as 0, and otherwise as decoded
// value + 1. For example for binders, value for "G_" is 1, for "G0_" value is
// 2. When "G" is absent value is 0.
uint64_t Demangler::parseOptionalBase62Number(char Tag) { … }

// Parses base 62 number with <0-9a-zA-Z> as digits. Number is terminated by
// "_". All values are offset by 1, so that "_" encodes 0, "0_" encodes 1,
// "1_" encodes 2, etc.
//
// <base-62-number> = {<0-9a-zA-Z>} "_"
uint64_t Demangler::parseBase62Number() { … }

// Parses a decimal number that had been encoded without any leading zeros.
//
// <decimal-number> = "0"
//                  | <1-9> {<0-9>}
uint64_t Demangler::parseDecimalNumber() { … }

// Parses a hexadecimal number with <0-9a-f> as a digits. Returns the parsed
// value and stores hex digits in HexDigits. The return value is unspecified if
// HexDigits.size() > 16.
//
// <hex-number> = "0_"
//              | <1-9a-f> {<0-9a-f>} "_"
uint64_t Demangler::parseHexNumber(std::string_view &HexDigits) { … }

void Demangler::print(char C) { … }

void Demangler::print(std::string_view S) { … }

void Demangler::printDecimalNumber(uint64_t N) { … }

// Prints a lifetime. An index 0 always represents an erased lifetime. Indices
// starting from 1, are De Bruijn indices, referring to higher-ranked lifetimes
// bound by one of the enclosing binders.
void Demangler::printLifetime(uint64_t Index) { … }

static inline bool decodePunycodeDigit(char C, size_t &Value) { … }

static void removeNullBytes(OutputBuffer &Output, size_t StartIdx) { … }

// Encodes code point as UTF-8 and stores results in Output. Returns false if
// CodePoint is not a valid unicode scalar value.
static inline bool encodeUTF8(size_t CodePoint, char *Output) { … }

// Decodes string encoded using punycode and appends results to Output.
// Returns true if decoding was successful.
static bool decodePunycode(std::string_view Input, OutputBuffer &Output) { … }

void Demangler::printIdentifier(Identifier Ident) { … }

char Demangler::look() const { … }

char Demangler::consume() { … }

bool Demangler::consumeIf(char Prefix) { … }

/// Computes A + B. When computation wraps around sets the error and returns
/// false. Otherwise assigns the result to A and returns true.
bool Demangler::addAssign(uint64_t &A, uint64_t B) { … }

/// Computes A * B. When computation wraps around sets the error and returns
/// false. Otherwise assigns the result to A and returns true.
bool Demangler::mulAssign(uint64_t &A, uint64_t B) { … }
llvm/llvm/lib/Demangle/RustDemangle.cpp
