mirror of
https://github.com/apple/swift.git
synced 2025-12-14 20:36:38 +01:00
938e7c2676
This allows UnicodeScalars to be constructed from an integer, rather then from a string. Not only this avoids an unnecessary memory allocation (!) when creating a UnicodeScalar, this also allows the compiler to statically check that the string contains a single scalar value (in the same way the compiler checks that Character contains only a single extended grapheme cluster). rdar://17966622 Swift SVN r21198
97 lines
2.9 KiB
C++
97 lines
2.9 KiB
C++
//===--- Unicode.cpp - Unicode utilities ----------------------------------===//
|
|
//
|
|
// This source file is part of the Swift.org open source project
|
|
//
|
|
// Copyright (c) 2014 - 2015 Apple Inc. and the Swift project authors
|
|
// Licensed under Apache License v2.0 with Runtime Library Exception
|
|
//
|
|
// See http://swift.org/LICENSE.txt for license information
|
|
// See http://swift.org/CONTRIBUTORS.txt for the list of Swift project authors
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "swift/Basic/Unicode.h"
|
|
#include "llvm/Support/ConvertUTF.h"
|
|
|
|
using namespace swift;
|
|
|
|
StringRef swift::unicode::extractFirstExtendedGraphemeCluster(StringRef S) {
|
|
// Extended grapheme cluster segmentation algorithm as described in Unicode
|
|
// Standard Annex #29.
|
|
if (S.empty())
|
|
return StringRef();
|
|
|
|
const UTF8 *SourceStart = reinterpret_cast<const UTF8 *>(S.data());
|
|
|
|
const UTF8 *SourceNext = SourceStart;
|
|
UTF32 C[2];
|
|
UTF32 *TargetStart = C;
|
|
|
|
ConvertUTF8toUTF32(&SourceNext, SourceStart + S.size(), &TargetStart, C + 1,
|
|
lenientConversion);
|
|
if (TargetStart == C) {
|
|
// The source string contains an ill-formed subsequence at the end.
|
|
return S;
|
|
}
|
|
|
|
GraphemeClusterBreakProperty GCBForC0 = getGraphemeClusterBreakProperty(C[0]);
|
|
while (true) {
|
|
if (isExtendedGraphemeClusterBoundaryAfter(GCBForC0))
|
|
return S.slice(0, SourceNext - SourceStart);
|
|
|
|
size_t C1Offset = SourceNext - SourceStart;
|
|
ConvertUTF8toUTF32(&SourceNext, SourceStart + S.size(), &TargetStart, C + 2,
|
|
lenientConversion);
|
|
|
|
if (TargetStart == C + 1) {
|
|
// End of source string or the source string contains an ill-formed
|
|
// subsequence at the end.
|
|
return S.slice(0, C1Offset);
|
|
}
|
|
|
|
GraphemeClusterBreakProperty GCBForC1 =
|
|
getGraphemeClusterBreakProperty(C[1]);
|
|
if (isExtendedGraphemeClusterBoundary(GCBForC0, GCBForC1))
|
|
return S.slice(0, C1Offset);
|
|
|
|
C[0] = C[1];
|
|
TargetStart = C + 1;
|
|
GCBForC0 = GCBForC1;
|
|
}
|
|
}
|
|
|
|
static bool extractFirstUnicodeScalarImpl(StringRef S, unsigned &Scalar) {
|
|
if (S.empty())
|
|
return false;
|
|
|
|
const UTF8 *SourceStart = reinterpret_cast<const UTF8 *>(S.data());
|
|
|
|
const UTF8 *SourceNext = SourceStart;
|
|
UTF32 C;
|
|
UTF32 *TargetStart = &C;
|
|
|
|
ConvertUTF8toUTF32(&SourceNext, SourceStart + S.size(), &TargetStart, TargetStart + 1,
|
|
lenientConversion);
|
|
if (TargetStart == &C) {
|
|
// The source string contains an ill-formed subsequence at the end.
|
|
return false;
|
|
}
|
|
|
|
Scalar = C;
|
|
return size_t(SourceNext - SourceStart) == S.size();
|
|
}
|
|
|
|
bool swift::unicode::isSingleUnicodeScalar(StringRef S) {
|
|
unsigned Scalar;
|
|
return extractFirstUnicodeScalarImpl(S, Scalar);
|
|
}
|
|
|
|
unsigned swift::unicode::extractFirstUnicodeScalar(StringRef S) {
|
|
unsigned Scalar;
|
|
bool Result = extractFirstUnicodeScalarImpl(S, Scalar);
|
|
assert(Result && "string does not consist of one Unicode scalar");
|
|
(void)Result;
|
|
return Scalar;
|
|
}
|
|
|