mirror of
https://github.com/apple/swift.git
synced 2025-12-14 20:36:38 +01:00
4814e00fda
algorithm The implementation uses a specialized trie that has not been tuned to the table data. I tried guessing parameter values that should work well, but did not do any performance measurements. There is no efficient way to initialize arrays with static data in Swift. The required tables are being generated as C++ code in the runtime library. rdar://16013860 Swift SVN r19340
73 lines
2.1 KiB
C++
73 lines
2.1 KiB
C++
%# -*- mode: C++ -*-
|
|
|
|
%# Ignore the following admonition; it applies to the resulting .cpp file only
|
|
//// Automatically Generated From UnicodeExtendedGraphemeClusters.cpp.gyb.
|
|
//// Do Not Edit Directly!
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
%{
|
|
|
|
from GYBUnicodeDataUtils import *
|
|
|
|
grapheme_cluster_break_tests = \
|
|
get_grapheme_cluster_break_tests_as_UTF8(unicodeGraphemeBreakTestFile)
|
|
|
|
}%
|
|
|
|
#include "swift/Basic/Unicode.h"
|
|
#include "gtest/gtest.h"
|
|
#include <vector>
|
|
|
|
using namespace swift;
|
|
using namespace swift::unicode;
|
|
|
|
static std::vector<unsigned> FindGraphemeClusterBoundaries(StringRef Str) {
|
|
std::vector<unsigned> Result;
|
|
Result.push_back(0);
|
|
|
|
unsigned Pos = 0;
|
|
while (Pos != Str.size()) {
|
|
Pos += extractFirstExtendedGraphemeCluster(Str.substr(Pos)).size();
|
|
Result.push_back(Pos);
|
|
}
|
|
|
|
return Result;
|
|
}
|
|
|
|
TEST(ExtractExtendedGraphemeCluster, TestsFromUnicodeSpec) {
|
|
% for subject_string,expected_boundaries in grapheme_cluster_break_tests:
|
|
EXPECT_EQ((std::vector<unsigned>{ ${', '.join([ str(x) for x in expected_boundaries ])} }),
|
|
FindGraphemeClusterBoundaries("${subject_string}"));
|
|
% end
|
|
}
|
|
|
|
TEST(ExtractExtendedGraphemeCluster, ExtraTests) {
|
|
//
|
|
// Sequences with one continuation byte missing
|
|
//
|
|
|
|
EXPECT_EQ((std::vector<unsigned>{ 0, 1 }),
|
|
FindGraphemeClusterBoundaries("\xc2"));
|
|
|
|
//
|
|
// Isolated surrogates
|
|
//
|
|
|
|
EXPECT_EQ((std::vector<unsigned>{ 0, 1, 2, 3 }),
|
|
FindGraphemeClusterBoundaries("\xed\xa0\x80"));
|
|
EXPECT_EQ((std::vector<unsigned>{ 0, 4, 5, 6, 11 }),
|
|
FindGraphemeClusterBoundaries(
|
|
"\xf3\xa0\x84\x80" "\xed\xa0\x80" "\xf3\xa0\x84\x80"));
|
|
}
|
|
|