mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 13:11:39 +01:00
ae65e281f3
to reflect the new license. We understand that people may be surprised that we're moving the header entirely to discuss the new license. We checked this carefully with the Foundation's lawyer and we believe this is the correct approach. Essentially, all code in the project is now made available by the LLVM project under our new license, so you will see that the license headers include that license only. Some of our contributors have contributed code under our old license, and accordingly, we have retained a copy of our old license notice in the top-level files in each project and repository. llvm-svn: 351636
86 lines
2.8 KiB
C++
86 lines
2.8 KiB
C++
//===-- Support/DJB.cpp ---DJB Hash -----------------------------*- 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 contains support for the DJ Bernstein hash function.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "llvm/Support/DJB.h"
|
|
#include "llvm/ADT/ArrayRef.h"
|
|
#include "llvm/Support/Compiler.h"
|
|
#include "llvm/Support/ConvertUTF.h"
|
|
#include "llvm/Support/Unicode.h"
|
|
|
|
using namespace llvm;
|
|
|
|
static UTF32 chopOneUTF32(StringRef &Buffer) {
|
|
UTF32 C;
|
|
const UTF8 *const Begin8Const =
|
|
reinterpret_cast<const UTF8 *>(Buffer.begin());
|
|
const UTF8 *Begin8 = Begin8Const;
|
|
UTF32 *Begin32 = &C;
|
|
|
|
// In lenient mode we will always end up with a "reasonable" value in C for
|
|
// non-empty input.
|
|
assert(!Buffer.empty());
|
|
ConvertUTF8toUTF32(&Begin8, reinterpret_cast<const UTF8 *>(Buffer.end()),
|
|
&Begin32, &C + 1, lenientConversion);
|
|
Buffer = Buffer.drop_front(Begin8 - Begin8Const);
|
|
return C;
|
|
}
|
|
|
|
static StringRef toUTF8(UTF32 C, MutableArrayRef<UTF8> Storage) {
|
|
const UTF32 *Begin32 = &C;
|
|
UTF8 *Begin8 = Storage.begin();
|
|
|
|
// The case-folded output should always be a valid unicode character, so use
|
|
// strict mode here.
|
|
ConversionResult CR = ConvertUTF32toUTF8(&Begin32, &C + 1, &Begin8,
|
|
Storage.end(), strictConversion);
|
|
assert(CR == conversionOK && "Case folding produced invalid char?");
|
|
(void)CR;
|
|
return StringRef(reinterpret_cast<char *>(Storage.begin()),
|
|
Begin8 - Storage.begin());
|
|
}
|
|
|
|
static UTF32 foldCharDwarf(UTF32 C) {
|
|
// DWARF v5 addition to the unicode folding rules.
|
|
// Fold "Latin Small Letter Dotless I" and "Latin Capital Letter I With Dot
|
|
// Above" into "i".
|
|
if (C == 0x130 || C == 0x131)
|
|
return 'i';
|
|
return sys::unicode::foldCharSimple(C);
|
|
}
|
|
|
|
static uint32_t caseFoldingDjbHashCharSlow(StringRef &Buffer, uint32_t H) {
|
|
UTF32 C = chopOneUTF32(Buffer);
|
|
|
|
C = foldCharDwarf(C);
|
|
|
|
std::array<UTF8, UNI_MAX_UTF8_BYTES_PER_CODE_POINT> Storage;
|
|
StringRef Folded = toUTF8(C, Storage);
|
|
return djbHash(Folded, H);
|
|
}
|
|
|
|
uint32_t llvm::caseFoldingDjbHash(StringRef Buffer, uint32_t H) {
|
|
while (!Buffer.empty()) {
|
|
unsigned char C = Buffer.front();
|
|
if (LLVM_LIKELY(C <= 0x7f)) {
|
|
// US-ASCII, encoded as one character in utf-8.
|
|
// This is by far the most common case, so handle this specially.
|
|
if (C >= 'A' && C <= 'Z')
|
|
C = 'a' + (C - 'A'); // fold uppercase into lowercase
|
|
H = (H << 5) + H + C;
|
|
Buffer = Buffer.drop_front();
|
|
continue;
|
|
}
|
|
H = caseFoldingDjbHashCharSlow(Buffer, H);
|
|
}
|
|
return H;
|
|
}
|