pgrondek/polybar-dwm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Make utf8_to_ucs4 take a string reference

Browse Source
This commit is contained in:
patrick96 2023-05-10 16:16:47 +02:00 committed by Patrick Ziegler
parent 5e5a0a7c4d
commit 5b1fae4fc1
4 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
include/cairo/context.hpp
View File

@ -165,7 +165,7 @@ namespace cairo {
string utf8 = t.contents; string utf8 = t.contents;
string_util::unicode_charlist chars; string_util::unicode_charlist chars;
bool success = string_util::utf8_to_ucs4(utf8.c_str(), chars); bool success = string_util::utf8_to_ucs4(utf8, chars);
if (!success) { if (!success) {
m_log.warn("Dropping invalid UTF8 text '%s'", utf8); m_log.warn("Dropping invalid UTF8 text '%s'", utf8);

2
include/utils/string.hpp
View File

@ -87,7 +87,7 @@ string utf8_truncate(string&& value, size_t len);
/** /**
* @brief Create a UCS-4 codepoint from a utf-8 encoded string * @brief Create a UCS-4 codepoint from a utf-8 encoded string
*/ */
[[nodiscard]] bool utf8_to_ucs4(const char* src, unicode_charlist& result_list); [[nodiscard]] bool utf8_to_ucs4(const string& src, unicode_charlist& result_list);
/** /**
* @brief Convert a UCS-4 codepoint to a utf-8 encoded string * @brief Convert a UCS-4 codepoint to a utf-8 encoded string

6
src/utils/string.cpp
View File

@ -280,10 +280,10 @@ static pair<int, uint32_t> utf8_get_len(uint8_t leading) {
* *
* @return Whether the string is completely valid utf8 * @return Whether the string is completely valid utf8
*/ */
bool utf8_to_ucs4(const char* src, unicode_charlist& result_list) { bool utf8_to_ucs4(const string& src, unicode_charlist& result_list) {
assert(src); result_list.reserve(src.size());
bool has_errors = false; bool has_errors = false;
const auto* begin = reinterpret_cast<const uint8_t*>(src); const auto* begin = reinterpret_cast<const uint8_t*>(src.c_str());
const auto* current = begin; const auto* current = begin;
while (*current) { while (*current) {

8
tests/unit_tests/utils/string.cpp
View File

@ -188,7 +188,7 @@ TEST_P(Utf8ToUCS4AsciiTest, correctness) {
string_util::unicode_charlist result_list{}; string_util::unicode_charlist result_list{};
string str = GetParam(); string str = GetParam();
bool success = string_util::utf8_to_ucs4(str.c_str(), result_list); bool success = string_util::utf8_to_ucs4(str, result_list);
ASSERT_TRUE(success); ASSERT_TRUE(success);
ASSERT_EQ(str.size(), result_list.size()); ASSERT_EQ(str.size(), result_list.size());
@ -229,7 +229,7 @@ TEST_P(Utf8ToUCS4SingleTest, correctness) {
string_util::unicode_charlist result_list{}; string_util::unicode_charlist result_list{};
const auto [str, codepoint] = GetParam(); const auto [str, codepoint] = GetParam();
bool success = string_util::utf8_to_ucs4(str.c_str(), result_list); bool success = string_util::utf8_to_ucs4(str, result_list);
ASSERT_TRUE(success); ASSERT_TRUE(success);
ASSERT_EQ(1, result_list.size()); ASSERT_EQ(1, result_list.size());
@ -251,7 +251,7 @@ const vector<string> utf8_to_ucs4_invalid_list = {
"\xe0", // 3 byte code point with only leading byte "\xe0", // 3 byte code point with only leading byte
"\xf0", // 4 byte code point with only leading byte "\xf0", // 4 byte code point with only leading byte
"\xf0\x80\x80", // 4 byte code point with only 3 bytes "\xf0\x80\x80", // 4 byte code point with only 3 bytes
"\xe0\x70\x80", // 3 byte code point, 2nd byte has no continuation prefix "\xe0\xf0\x80", // 3 byte code point, 2nd byte has no continuation prefix
}; };
INSTANTIATE_TEST_SUITE_P(Inst, Utf8ToUCS4InvalidTest, testing::ValuesIn(utf8_to_ucs4_invalid_list)); INSTANTIATE_TEST_SUITE_P(Inst, Utf8ToUCS4InvalidTest, testing::ValuesIn(utf8_to_ucs4_invalid_list));
@ -262,7 +262,7 @@ INSTANTIATE_TEST_SUITE_P(Inst, Utf8ToUCS4InvalidTest, testing::ValuesIn(utf8_to_
TEST_P(Utf8ToUCS4InvalidTest, correctness) { TEST_P(Utf8ToUCS4InvalidTest, correctness) {
string_util::unicode_charlist result_list{}; string_util::unicode_charlist result_list{};
const auto str = GetParam(); const auto str = GetParam();
bool success = string_util::utf8_to_ucs4(str.c_str(), result_list); bool success = string_util::utf8_to_ucs4(str, result_list);
EXPECT_FALSE(success); EXPECT_FALSE(success);
EXPECT_EQ(0, result_list.size()); EXPECT_EQ(0, result_list.size());
} }