LadybirdBrowser/ladybird
1
1
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-09-20 17:58:18 +03:00
Code Issues Packages Projects Releases Wiki Activity
94f139c111
ladybird/Tests/AK/TestString.cpp

610 lines
18 KiB
C++
Raw Normal View History

AK: Introduce the new String, replacement for DeprecatedString DeprecatedString (formerly String) has been with us since the start, and it has served us well. However, it has a number of shortcomings that I'd like to address. Some of these issues are hard if not impossible to solve incrementally inside of DeprecatedString, so instead of doing that, let's build a new String class and then incrementally move over to it instead. Problems in DeprecatedString: - It assumes string allocation never fails. This makes it impossible to use in allocation-sensitive contexts, and is the reason we had to ban DeprecatedString from the kernel entirely. - The awkward null state. DeprecatedString can be null. It's different from the empty state, although null strings are considered empty. All code is immediately nicer when using Optional<DeprecatedString> but DeprecatedString came before Optional, which is how we ended up like this. - The encoding of the underlying data is ambiguous. For the most part, we use it as if it's always UTF-8, but there have been cases where we pass around strings in other encodings (e.g ISO8859-1) - operator[] and length() are used to iterate over DeprecatedString one byte at a time. This is done all over the codebase, and will *not* give the right results unless the string is all ASCII. How we solve these issues in the new String: - Functions that may allocate now return ErrorOr<String> so that ENOMEM errors can be passed to the caller. - String has no null state. Use Optional<String> when needed. - String is always UTF-8. This is validated when constructing a String. We may need to add a bypass for this in the future, for cases where you have a known-good string, but for now: validate all the things! - There is no operator[] or length(). You can get the underlying data with bytes(), but for iterating over code points, you should be using an UTF-8 iterator. Furthermore, it has two nifty new features: - String implements a small string optimization (SSO) for strings that can fit entirely within a pointer. This means up to 3 bytes on 32-bit platforms, and 7 bytes on 64-bit platforms. Such small strings will not be heap-allocated. - String can create substrings without making a deep copy of the substring. Instead, the superstring gets +1 refcount from the substring, and it acts like a view into the superstring. To make substrings like this, use the substring_with_shared_superstring() API. One caveat: - String does not guarantee that the underlying data is null-terminated like DeprecatedString does today. While this was nifty in a handful of places where we were calling C functions, it did stand in the way of shared-superstring substrings.
2022-12-01 15:27:43 +03:00
/*
* Copyright (c) 2022, Andreas Kling <kling@serenityos.org>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
AK: Add a String factory to create a string from a single code point
2023-01-21 20:34:01 +03:00
// This is included first on purpose. We specifically do not want LibTest to override VERIFY here so
// that we can actually test that some String factory methods cause a crash with invalid input.
#include <AK/String.h>
AK: Introduce the new String, replacement for DeprecatedString DeprecatedString (formerly String) has been with us since the start, and it has served us well. However, it has a number of shortcomings that I'd like to address. Some of these issues are hard if not impossible to solve incrementally inside of DeprecatedString, so instead of doing that, let's build a new String class and then incrementally move over to it instead. Problems in DeprecatedString: - It assumes string allocation never fails. This makes it impossible to use in allocation-sensitive contexts, and is the reason we had to ban DeprecatedString from the kernel entirely. - The awkward null state. DeprecatedString can be null. It's different from the empty state, although null strings are considered empty. All code is immediately nicer when using Optional<DeprecatedString> but DeprecatedString came before Optional, which is how we ended up like this. - The encoding of the underlying data is ambiguous. For the most part, we use it as if it's always UTF-8, but there have been cases where we pass around strings in other encodings (e.g ISO8859-1) - operator[] and length() are used to iterate over DeprecatedString one byte at a time. This is done all over the codebase, and will *not* give the right results unless the string is all ASCII. How we solve these issues in the new String: - Functions that may allocate now return ErrorOr<String> so that ENOMEM errors can be passed to the caller. - String has no null state. Use Optional<String> when needed. - String is always UTF-8. This is validated when constructing a String. We may need to add a bypass for this in the future, for cases where you have a known-good string, but for now: validate all the things! - There is no operator[] or length(). You can get the underlying data with bytes(), but for iterating over code points, you should be using an UTF-8 iterator. Furthermore, it has two nifty new features: - String implements a small string optimization (SSO) for strings that can fit entirely within a pointer. This means up to 3 bytes on 32-bit platforms, and 7 bytes on 64-bit platforms. Such small strings will not be heap-allocated. - String can create substrings without making a deep copy of the substring. Instead, the superstring gets +1 refcount from the substring, and it acts like a view into the superstring. To make substrings like this, use the substring_with_shared_superstring() API. One caveat: - String does not guarantee that the underlying data is null-terminated like DeprecatedString does today. While this was nifty in a handful of places where we were calling C functions, it did stand in the way of shared-superstring substrings.
2022-12-01 15:27:43 +03:00
#include <LibTest/TestCase.h>
#include <AK/StringBuilder.h>
#include <AK/Try.h>
#include <AK/Utf8View.h>
#include <AK/Vector.h>
TEST_CASE(construct_empty)
{
String empty;
EXPECT(empty.is_empty());
EXPECT_EQ(empty.bytes().size(), 0u);
auto empty2 = MUST(String::from_utf8(""sv));
EXPECT(empty2.is_empty());
EXPECT_EQ(empty, empty2);
EXPECT_EQ(empty, ""sv);
}
AK: Unref old m_data in String's move assignment We were overridding the data pointer without unreffing it, causing a memory leak when assigning a String.
2022-12-08 20:30:04 +03:00
TEST_CASE(move_assignment)
{
String string1 = MUST(String::from_utf8("hello"sv));
string1 = MUST(String::from_utf8("friends!"sv));
EXPECT_EQ(string1, "friends!"sv);
}
AK: Introduce the new String, replacement for DeprecatedString DeprecatedString (formerly String) has been with us since the start, and it has served us well. However, it has a number of shortcomings that I'd like to address. Some of these issues are hard if not impossible to solve incrementally inside of DeprecatedString, so instead of doing that, let's build a new String class and then incrementally move over to it instead. Problems in DeprecatedString: - It assumes string allocation never fails. This makes it impossible to use in allocation-sensitive contexts, and is the reason we had to ban DeprecatedString from the kernel entirely. - The awkward null state. DeprecatedString can be null. It's different from the empty state, although null strings are considered empty. All code is immediately nicer when using Optional<DeprecatedString> but DeprecatedString came before Optional, which is how we ended up like this. - The encoding of the underlying data is ambiguous. For the most part, we use it as if it's always UTF-8, but there have been cases where we pass around strings in other encodings (e.g ISO8859-1) - operator[] and length() are used to iterate over DeprecatedString one byte at a time. This is done all over the codebase, and will *not* give the right results unless the string is all ASCII. How we solve these issues in the new String: - Functions that may allocate now return ErrorOr<String> so that ENOMEM errors can be passed to the caller. - String has no null state. Use Optional<String> when needed. - String is always UTF-8. This is validated when constructing a String. We may need to add a bypass for this in the future, for cases where you have a known-good string, but for now: validate all the things! - There is no operator[] or length(). You can get the underlying data with bytes(), but for iterating over code points, you should be using an UTF-8 iterator. Furthermore, it has two nifty new features: - String implements a small string optimization (SSO) for strings that can fit entirely within a pointer. This means up to 3 bytes on 32-bit platforms, and 7 bytes on 64-bit platforms. Such small strings will not be heap-allocated. - String can create substrings without making a deep copy of the substring. Instead, the superstring gets +1 refcount from the substring, and it acts like a view into the superstring. To make substrings like this, use the substring_with_shared_superstring() API. One caveat: - String does not guarantee that the underlying data is null-terminated like DeprecatedString does today. While this was nifty in a handful of places where we were calling C functions, it did stand in the way of shared-superstring substrings.
2022-12-01 15:27:43 +03:00
TEST_CASE(short_strings)
{
#ifdef AK_ARCH_64_BIT
AK: Support creating known short string literals at compile time In cases where we know a string literal will fit in the short string storage, we can do so at compile time without needing to handle error propagation. If the provided string literal is too long, a compilation error will be emitted due to the failed VERIFY statement being a non- constant expression.
2023-01-20 15:20:01 +03:00
auto string1 = MUST(String::from_utf8("abcdefg"sv));
EXPECT_EQ(string1.is_short_string(), true);
EXPECT_EQ(string1.bytes().size(), 7u);
EXPECT_EQ(string1.bytes_as_string_view(), "abcdefg"sv);
constexpr auto string2 = String::from_utf8_short_string("abcdefg"sv);
EXPECT_EQ(string2.is_short_string(), true);
EXPECT_EQ(string2.bytes().size(), 7u);
EXPECT_EQ(string2, string1);
AK: Introduce the new String, replacement for DeprecatedString DeprecatedString (formerly String) has been with us since the start, and it has served us well. However, it has a number of shortcomings that I'd like to address. Some of these issues are hard if not impossible to solve incrementally inside of DeprecatedString, so instead of doing that, let's build a new String class and then incrementally move over to it instead. Problems in DeprecatedString: - It assumes string allocation never fails. This makes it impossible to use in allocation-sensitive contexts, and is the reason we had to ban DeprecatedString from the kernel entirely. - The awkward null state. DeprecatedString can be null. It's different from the empty state, although null strings are considered empty. All code is immediately nicer when using Optional<DeprecatedString> but DeprecatedString came before Optional, which is how we ended up like this. - The encoding of the underlying data is ambiguous. For the most part, we use it as if it's always UTF-8, but there have been cases where we pass around strings in other encodings (e.g ISO8859-1) - operator[] and length() are used to iterate over DeprecatedString one byte at a time. This is done all over the codebase, and will *not* give the right results unless the string is all ASCII. How we solve these issues in the new String: - Functions that may allocate now return ErrorOr<String> so that ENOMEM errors can be passed to the caller. - String has no null state. Use Optional<String> when needed. - String is always UTF-8. This is validated when constructing a String. We may need to add a bypass for this in the future, for cases where you have a known-good string, but for now: validate all the things! - There is no operator[] or length(). You can get the underlying data with bytes(), but for iterating over code points, you should be using an UTF-8 iterator. Furthermore, it has two nifty new features: - String implements a small string optimization (SSO) for strings that can fit entirely within a pointer. This means up to 3 bytes on 32-bit platforms, and 7 bytes on 64-bit platforms. Such small strings will not be heap-allocated. - String can create substrings without making a deep copy of the substring. Instead, the superstring gets +1 refcount from the substring, and it acts like a view into the superstring. To make substrings like this, use the substring_with_shared_superstring() API. One caveat: - String does not guarantee that the underlying data is null-terminated like DeprecatedString does today. While this was nifty in a handful of places where we were calling C functions, it did stand in the way of shared-superstring substrings.
2022-12-01 15:27:43 +03:00
#else
AK: Support creating known short string literals at compile time In cases where we know a string literal will fit in the short string storage, we can do so at compile time without needing to handle error propagation. If the provided string literal is too long, a compilation error will be emitted due to the failed VERIFY statement being a non- constant expression.
2023-01-20 15:20:01 +03:00
auto string1 = MUST(String::from_utf8("abc"sv));
EXPECT_EQ(string1.is_short_string(), true);
EXPECT_EQ(string1.bytes().size(), 3u);
EXPECT_EQ(string1.bytes_as_string_view(), "abc"sv);
constexpr auto string2 = String::from_utf8_short_string("abc"sv);
EXPECT_EQ(string2.is_short_string(), true);
EXPECT_EQ(string2.bytes().size(), 3u);
EXPECT_EQ(string2, string1);
AK: Introduce the new String, replacement for DeprecatedString DeprecatedString (formerly String) has been with us since the start, and it has served us well. However, it has a number of shortcomings that I'd like to address. Some of these issues are hard if not impossible to solve incrementally inside of DeprecatedString, so instead of doing that, let's build a new String class and then incrementally move over to it instead. Problems in DeprecatedString: - It assumes string allocation never fails. This makes it impossible to use in allocation-sensitive contexts, and is the reason we had to ban DeprecatedString from the kernel entirely. - The awkward null state. DeprecatedString can be null. It's different from the empty state, although null strings are considered empty. All code is immediately nicer when using Optional<DeprecatedString> but DeprecatedString came before Optional, which is how we ended up like this. - The encoding of the underlying data is ambiguous. For the most part, we use it as if it's always UTF-8, but there have been cases where we pass around strings in other encodings (e.g ISO8859-1) - operator[] and length() are used to iterate over DeprecatedString one byte at a time. This is done all over the codebase, and will *not* give the right results unless the string is all ASCII. How we solve these issues in the new String: - Functions that may allocate now return ErrorOr<String> so that ENOMEM errors can be passed to the caller. - String has no null state. Use Optional<String> when needed. - String is always UTF-8. This is validated when constructing a String. We may need to add a bypass for this in the future, for cases where you have a known-good string, but for now: validate all the things! - There is no operator[] or length(). You can get the underlying data with bytes(), but for iterating over code points, you should be using an UTF-8 iterator. Furthermore, it has two nifty new features: - String implements a small string optimization (SSO) for strings that can fit entirely within a pointer. This means up to 3 bytes on 32-bit platforms, and 7 bytes on 64-bit platforms. Such small strings will not be heap-allocated. - String can create substrings without making a deep copy of the substring. Instead, the superstring gets +1 refcount from the substring, and it acts like a view into the superstring. To make substrings like this, use the substring_with_shared_superstring() API. One caveat: - String does not guarantee that the underlying data is null-terminated like DeprecatedString does today. While this was nifty in a handful of places where we were calling C functions, it did stand in the way of shared-superstring substrings.
2022-12-01 15:27:43 +03:00
#endif
}
TEST_CASE(long_strings)
{
auto string = MUST(String::from_utf8("abcdefgh"sv));
EXPECT_EQ(string.is_short_string(), false);
EXPECT_EQ(string.bytes().size(), 8u);
EXPECT_EQ(string.bytes_as_string_view(), "abcdefgh"sv);
}
AK: Add a String factory to create a string from a single code point
2023-01-21 20:34:01 +03:00
TEST_CASE(from_code_points)
{
for (u32 code_point = 0; code_point < 0x80; ++code_point) {
auto string = String::from_code_point(code_point);
auto ch = static_cast<char>(code_point);
StringView view { &ch, 1 };
EXPECT_EQ(string, view);
}
auto string = String::from_code_point(0x10ffff);
EXPECT_EQ(string, "\xF4\x8F\xBF\xBF"sv);
EXPECT_CRASH("Creating a string from an invalid code point", [] {
String::from_code_point(0xffffffff);
return Test::Crash::Failure::DidNotCrash;
});
}
AK: Introduce the new String, replacement for DeprecatedString DeprecatedString (formerly String) has been with us since the start, and it has served us well. However, it has a number of shortcomings that I'd like to address. Some of these issues are hard if not impossible to solve incrementally inside of DeprecatedString, so instead of doing that, let's build a new String class and then incrementally move over to it instead. Problems in DeprecatedString: - It assumes string allocation never fails. This makes it impossible to use in allocation-sensitive contexts, and is the reason we had to ban DeprecatedString from the kernel entirely. - The awkward null state. DeprecatedString can be null. It's different from the empty state, although null strings are considered empty. All code is immediately nicer when using Optional<DeprecatedString> but DeprecatedString came before Optional, which is how we ended up like this. - The encoding of the underlying data is ambiguous. For the most part, we use it as if it's always UTF-8, but there have been cases where we pass around strings in other encodings (e.g ISO8859-1) - operator[] and length() are used to iterate over DeprecatedString one byte at a time. This is done all over the codebase, and will *not* give the right results unless the string is all ASCII. How we solve these issues in the new String: - Functions that may allocate now return ErrorOr<String> so that ENOMEM errors can be passed to the caller. - String has no null state. Use Optional<String> when needed. - String is always UTF-8. This is validated when constructing a String. We may need to add a bypass for this in the future, for cases where you have a known-good string, but for now: validate all the things! - There is no operator[] or length(). You can get the underlying data with bytes(), but for iterating over code points, you should be using an UTF-8 iterator. Furthermore, it has two nifty new features: - String implements a small string optimization (SSO) for strings that can fit entirely within a pointer. This means up to 3 bytes on 32-bit platforms, and 7 bytes on 64-bit platforms. Such small strings will not be heap-allocated. - String can create substrings without making a deep copy of the substring. Instead, the superstring gets +1 refcount from the substring, and it acts like a view into the superstring. To make substrings like this, use the substring_with_shared_superstring() API. One caveat: - String does not guarantee that the underlying data is null-terminated like DeprecatedString does today. While this was nifty in a handful of places where we were calling C functions, it did stand in the way of shared-superstring substrings.
2022-12-01 15:27:43 +03:00
TEST_CASE(substring)
{
auto superstring = MUST(String::from_utf8("Hello I am a long string"sv));
auto short_substring = MUST(superstring.substring_from_byte_offset(0, 5));
EXPECT_EQ(short_substring, "Hello"sv);
auto long_substring = MUST(superstring.substring_from_byte_offset(0, 10));
EXPECT_EQ(long_substring, "Hello I am"sv);
}
TEST_CASE(code_points)
{
auto string = MUST(String::from_utf8("🦬🪒"sv));
Vector<u32> code_points;
for (auto code_point : string.code_points())
code_points.append(code_point);
EXPECT_EQ(code_points[0], 0x1f9acu);
EXPECT_EQ(code_points[1], 0x1fa92u);
}
TEST_CASE(string_builder)
{
StringBuilder builder;
builder.append_code_point(0x1f9acu);
builder.append_code_point(0x1fa92u);
auto string = MUST(builder.to_string());
EXPECT_EQ(string, "🦬🪒"sv);
EXPECT_EQ(string.bytes().size(), 8u);
}
TEST_CASE(ak_format)
{
auto foo = MUST(String::formatted("Hello {}", MUST(String::from_utf8("friends"sv))));
EXPECT_EQ(foo, "Hello friends"sv);
}
TEST_CASE(replace)
{
{
auto haystack = MUST(String::from_utf8("Hello enemies"sv));
auto result = MUST(haystack.replace("enemies"sv, "friends"sv, ReplaceMode::All));
EXPECT_EQ(result, "Hello friends"sv);
}
{
auto base_title = MUST(String::from_utf8("anon@courage:~"sv));
auto result = MUST(base_title.replace("[*]"sv, "(*)"sv, ReplaceMode::FirstOnly));
EXPECT_EQ(result, "anon@courage:~"sv);
}
}
AK+LibUnicode: Provide Unicode-aware String case transformations Since AK can't refer to LibUnicode directly, the strategy here is that if you need case transformations, you can link LibUnicode and receive them. If you try to use either of these methods without linking it, then you'll of course get a linker error (note we don't do any fallbacks to e.g. ASCII case transformations). If you don't need these methods, you don't have to link LibUnicode.
2023-01-09 00:33:30 +03:00
AK: Add a somewhat naive implementation of String::reverse This will reverse the String's code points (i.e. not just its bytes), but is not aware of grapheme clusters.
2023-01-13 19:34:00 +03:00
TEST_CASE(reverse)
{
auto test_reverse = [](auto test, auto expected) {
auto string = MUST(String::from_utf8(test));
auto result = MUST(string.reverse());
EXPECT_EQ(result, expected);
};
test_reverse(""sv, ""sv);
test_reverse("a"sv, "a"sv);
test_reverse("ab"sv, "ba"sv);
test_reverse("ab cd ef"sv, "fe dc ba"sv);
test_reverse("😀"sv, "😀"sv);
test_reverse("ab😀cd"sv, "dc😀ba"sv);
}
AK+LibUnicode: Provide Unicode-aware String case transformations Since AK can't refer to LibUnicode directly, the strategy here is that if you need case transformations, you can link LibUnicode and receive them. If you try to use either of these methods without linking it, then you'll of course get a linker error (note we don't do any fallbacks to e.g. ASCII case transformations). If you don't need these methods, you don't have to link LibUnicode.
2023-01-09 00:33:30 +03:00
TEST_CASE(to_lowercase)
{
{
auto string = MUST(String::from_utf8("Aa"sv));
auto result = MUST(string.to_lowercase());
EXPECT_EQ(result, "aa"sv);
}
{
auto string = MUST(String::from_utf8("Ωω"sv));
auto result = MUST(string.to_lowercase());
EXPECT_EQ(result, "ωω"sv);
}
{
auto string = MUST(String::from_utf8("İi̇"sv));
auto result = MUST(string.to_lowercase());
EXPECT_EQ(result, "i̇i̇"sv);
}
}
TEST_CASE(to_uppercase)
{
{
auto string = MUST(String::from_utf8("Aa"sv));
auto result = MUST(string.to_uppercase());
EXPECT_EQ(result, "AA"sv);
}
{
auto string = MUST(String::from_utf8("Ωω"sv));
auto result = MUST(string.to_uppercase());
EXPECT_EQ(result, "ΩΩ"sv);
}
{
auto string = MUST(String::from_utf8("ʼn"sv));
auto result = MUST(string.to_uppercase());
EXPECT_EQ(result, "ʼN"sv);
}
}
AK: Add String::is_one_of for variadic string comparison
2023-01-14 17:59:18 +03:00
AK+LibUnicode: Provide Unicode-aware String titlecase transformation
2023-01-16 19:28:27 +03:00
TEST_CASE(to_titlecase)
{
{
auto string = MUST(String::from_utf8("foo bar baz"sv));
auto result = MUST(string.to_titlecase());
EXPECT_EQ(result, "Foo Bar Baz"sv);
}
{
auto string = MUST(String::from_utf8("foo \n \r bar \t baz"sv));
auto result = MUST(string.to_titlecase());
EXPECT_EQ(result, "Foo \n \r Bar \t Baz"sv);
}
{
auto string = MUST(String::from_utf8("f\"oo\" b'ar'"sv));
auto result = MUST(string.to_titlecase());
EXPECT_EQ(result, "F\"Oo\" B'Ar'"sv);
}
{
auto string = MUST(String::from_utf8("123dollars"sv));
auto result = MUST(string.to_titlecase());
EXPECT_EQ(result, "123Dollars"sv);
}
}
AK+LibUnicode: Provide Unicode-aware caseless String matching The Unicode spec defines much more complicated caseless matching algorithms in its Collation spec. This implements the "basic" case folding comparison.
2023-01-17 19:30:10 +03:00
TEST_CASE(equals_ignoring_case)
{
{
String string1 {};
String string2 {};
EXPECT(MUST(string1.equals_ignoring_case(string2)));
}
{
auto string1 = MUST(String::from_utf8("abcd"sv));
auto string2 = MUST(String::from_utf8("ABCD"sv));
auto string3 = MUST(String::from_utf8("AbCd"sv));
auto string4 = MUST(String::from_utf8("dcba"sv));
EXPECT(MUST(string1.equals_ignoring_case(string2)));
EXPECT(MUST(string1.equals_ignoring_case(string3)));
EXPECT(!MUST(string1.equals_ignoring_case(string4)));
EXPECT(MUST(string2.equals_ignoring_case(string1)));
EXPECT(MUST(string2.equals_ignoring_case(string3)));
EXPECT(!MUST(string2.equals_ignoring_case(string4)));
EXPECT(MUST(string3.equals_ignoring_case(string1)));
EXPECT(MUST(string3.equals_ignoring_case(string2)));
EXPECT(!MUST(string3.equals_ignoring_case(string4)));
}
{
auto string1 = MUST(String::from_utf8("\u00DF"sv)); // LATIN SMALL LETTER SHARP S
auto string2 = MUST(String::from_utf8("SS"sv));
auto string3 = MUST(String::from_utf8("Ss"sv));
auto string4 = MUST(String::from_utf8("ss"sv));
auto string5 = MUST(String::from_utf8("S"sv));
auto string6 = MUST(String::from_utf8("s"sv));
EXPECT(MUST(string1.equals_ignoring_case(string2)));
EXPECT(MUST(string1.equals_ignoring_case(string3)));
EXPECT(MUST(string1.equals_ignoring_case(string4)));
EXPECT(!MUST(string1.equals_ignoring_case(string5)));
EXPECT(!MUST(string1.equals_ignoring_case(string6)));
EXPECT(MUST(string2.equals_ignoring_case(string1)));
EXPECT(MUST(string2.equals_ignoring_case(string3)));
EXPECT(MUST(string2.equals_ignoring_case(string4)));
EXPECT(!MUST(string2.equals_ignoring_case(string5)));
EXPECT(!MUST(string2.equals_ignoring_case(string6)));
EXPECT(MUST(string3.equals_ignoring_case(string1)));
EXPECT(MUST(string3.equals_ignoring_case(string2)));
EXPECT(MUST(string3.equals_ignoring_case(string4)));
EXPECT(!MUST(string3.equals_ignoring_case(string5)));
EXPECT(!MUST(string3.equals_ignoring_case(string6)));
EXPECT(MUST(string4.equals_ignoring_case(string1)));
EXPECT(MUST(string4.equals_ignoring_case(string2)));
EXPECT(MUST(string4.equals_ignoring_case(string3)));
EXPECT(!MUST(string4.equals_ignoring_case(string5)));
EXPECT(!MUST(string4.equals_ignoring_case(string6)));
}
}
AK: Add String::is_one_of for variadic string comparison
2023-01-14 17:59:18 +03:00
TEST_CASE(is_one_of)
{
auto foo = MUST(String::from_utf8("foo"sv));
auto bar = MUST(String::from_utf8("bar"sv));
EXPECT(foo.is_one_of(foo));
EXPECT(foo.is_one_of(foo, bar));
EXPECT(foo.is_one_of(bar, foo));
EXPECT(!foo.is_one_of(bar));
EXPECT(!bar.is_one_of("foo"sv));
EXPECT(bar.is_one_of("foo"sv, "bar"sv));
EXPECT(bar.is_one_of("bar"sv, "foo"sv));
EXPECT(bar.is_one_of("bar"sv));
}
AK: Add `split()` for `String`
2023-01-16 19:12:53 +03:00
TEST_CASE(split)
{
{
auto test = MUST(String::from_utf8("foo bar baz"sv));
auto parts = MUST(test.split(' '));
EXPECT_EQ(parts.size(), 3u);
EXPECT_EQ(parts[0], "foo");
EXPECT_EQ(parts[1], "bar");
EXPECT_EQ(parts[2], "baz");
}
{
auto test = MUST(String::from_utf8("ωΣ2ωΣω"sv));
auto parts = MUST(test.split(0x03A3u));
EXPECT_EQ(parts.size(), 3u);
EXPECT_EQ(parts[0], "ω"sv);
EXPECT_EQ(parts[1], "2ω"sv);
EXPECT_EQ(parts[2], "ω"sv);
}
}
AK: Add a method to find the byte offset of a code point
2023-01-22 17:24:12 +03:00
TEST_CASE(find_byte_offset)
{
{
String string {};
AK: Add an overload of String::find_byte_offset for StringView
2023-01-27 18:17:34 +03:00
auto index1 = string.find_byte_offset(0);
EXPECT(!index1.has_value());
auto index2 = string.find_byte_offset(""sv);
EXPECT(!index2.has_value());
AK: Add a method to find the byte offset of a code point
2023-01-22 17:24:12 +03:00
}
{
auto string = MUST(String::from_utf8("foo"sv));
auto index1 = string.find_byte_offset('f');
EXPECT_EQ(index1, 0u);
auto index2 = string.find_byte_offset('o');
EXPECT_EQ(index2, 1u);
auto index3 = string.find_byte_offset('o', *index2 + 1);
EXPECT_EQ(index3, 2u);
auto index4 = string.find_byte_offset('b');
EXPECT(!index4.has_value());
}
AK: Add an overload of String::find_byte_offset for StringView
2023-01-27 18:17:34 +03:00
{
auto string = MUST(String::from_utf8("foo"sv));
auto index1 = string.find_byte_offset("fo"sv);
EXPECT_EQ(index1, 0u);
auto index2 = string.find_byte_offset("oo"sv);
EXPECT_EQ(index2, 1u);
auto index3 = string.find_byte_offset("o"sv, *index2 + 1);
EXPECT_EQ(index3, 2u);
auto index4 = string.find_byte_offset("fooo"sv);
EXPECT(!index4.has_value());
}
AK: Add a method to find the byte offset of a code point
2023-01-22 17:24:12 +03:00
{
auto string = MUST(String::from_utf8("ωΣωΣω"sv));
auto index1 = string.find_byte_offset(0x03C9U);
EXPECT_EQ(index1, 0u);
auto index2 = string.find_byte_offset(0x03A3u);
EXPECT_EQ(index2, 2u);
auto index3 = string.find_byte_offset(0x03C9U, 2);
EXPECT_EQ(index3, 4u);
auto index4 = string.find_byte_offset(0x03A3u, 4);
EXPECT_EQ(index4, 6u);
auto index5 = string.find_byte_offset(0x03C9U, 6);
EXPECT_EQ(index5, 8u);
}
AK: Add an overload of String::find_byte_offset for StringView
2023-01-27 18:17:34 +03:00
{
auto string = MUST(String::from_utf8("ωΣωΣω"sv));
auto index1 = string.find_byte_offset("ω"sv);
EXPECT_EQ(index1, 0u);
auto index2 = string.find_byte_offset("Σ"sv);
EXPECT_EQ(index2, 2u);
auto index3 = string.find_byte_offset("ω"sv, 2);
EXPECT_EQ(index3, 4u);
auto index4 = string.find_byte_offset("Σ"sv, 4);
EXPECT_EQ(index4, 6u);
auto index5 = string.find_byte_offset("ω"sv, 6);
EXPECT_EQ(index5, 8u);
}
AK: Add a method to find the byte offset of a code point
2023-01-22 17:24:12 +03:00
}
AK: Add a method to create a String with a repeated code point
2023-01-22 18:17:48 +03:00
TEST_CASE(repeated)
{
{
auto string1 = MUST(String::repeated('a', 0));
EXPECT(string1.is_short_string());
EXPECT(string1.is_empty());
auto string2 = MUST(String::repeated(0x03C9U, 0));
EXPECT(string2.is_short_string());
EXPECT(string2.is_empty());
auto string3 = MUST(String::repeated(0x10300, 0));
EXPECT(string3.is_short_string());
EXPECT(string3.is_empty());
}
{
auto string1 = MUST(String::repeated('a', 1));
EXPECT(string1.is_short_string());
EXPECT_EQ(string1.bytes_as_string_view().length(), 1u);
EXPECT_EQ(string1, "a"sv);
auto string2 = MUST(String::repeated(0x03C9U, 1));
EXPECT(string2.is_short_string());
EXPECT_EQ(string2.bytes_as_string_view().length(), 2u);
EXPECT_EQ(string2, "ω"sv);
auto string3 = MUST(String::repeated(0x10300, 1));
#ifdef AK_ARCH_64_BIT
EXPECT(string3.is_short_string());
#else
EXPECT(!string3.is_short_string());
#endif
EXPECT_EQ(string3.bytes_as_string_view().length(), 4u);
EXPECT_EQ(string3, "𐌀"sv);
}
{
auto string1 = MUST(String::repeated('a', 3));
EXPECT(string1.is_short_string());
EXPECT_EQ(string1.bytes_as_string_view().length(), 3u);
EXPECT_EQ(string1, "aaa"sv);
auto string2 = MUST(String::repeated(0x03C9U, 3));
#ifdef AK_ARCH_64_BIT
EXPECT(string2.is_short_string());
#else
EXPECT(!string2.is_short_string());
#endif
EXPECT_EQ(string2.bytes_as_string_view().length(), 6u);
EXPECT_EQ(string2, "ωωω"sv);
auto string3 = MUST(String::repeated(0x10300, 3));
EXPECT(!string3.is_short_string());
EXPECT_EQ(string3.bytes_as_string_view().length(), 12u);
EXPECT_EQ(string3, "𐌀𐌀𐌀"sv);
}
{
auto string1 = MUST(String::repeated('a', 10));
EXPECT(!string1.is_short_string());
EXPECT_EQ(string1.bytes_as_string_view().length(), 10u);
EXPECT_EQ(string1, "aaaaaaaaaa"sv);
auto string2 = MUST(String::repeated(0x03C9U, 10));
EXPECT(!string2.is_short_string());
EXPECT_EQ(string2.bytes_as_string_view().length(), 20u);
EXPECT_EQ(string2, "ωωωωωωωωωω"sv);
auto string3 = MUST(String::repeated(0x10300, 10));
EXPECT(!string3.is_short_string());
EXPECT_EQ(string3.bytes_as_string_view().length(), 40u);
EXPECT_EQ(string3, "𐌀𐌀𐌀𐌀𐌀𐌀𐌀𐌀𐌀𐌀"sv);
}
EXPECT_CRASH("Creating a string from an invalid code point", [] {
(void)String::repeated(0xffffffff, 1);
return Test::Crash::Failure::DidNotCrash;
});
}
AK: Add String::join
2023-01-27 22:06:05 +03:00
TEST_CASE(join)
{
auto string1 = MUST(String::join(',', Vector<i32> {}));
EXPECT(string1.is_empty());
auto string2 = MUST(String::join(',', Array { 1 }));
EXPECT_EQ(string2, "1"sv);
auto string3 = MUST(String::join(':', Array { 1 }, "[{}]"sv));
EXPECT_EQ(string3, "[1]"sv);
auto string4 = MUST(String::join(',', Array { 1, 2, 3 }));
EXPECT_EQ(string4, "1,2,3"sv);
auto string5 = MUST(String::join(',', Array { 1, 2, 3 }, "[{}]"sv));
EXPECT_EQ(string5, "[1],[2],[3]"sv);
auto string6 = MUST(String::join(String::from_utf8_short_string("!!!"sv), Array { "foo"sv, "bar"sv, "baz"sv }));
EXPECT_EQ(string6, "foo!!!bar!!!baz"sv);
auto string7 = MUST(String::join(" - "sv, Array { 1, 16, 256, 4096 }, "[{:#04x}]"sv));
EXPECT_EQ(string7, "[0x0001] - [0x0010] - [0x0100] - [0x1000]"sv);
}
AK: Add String::trim
2023-01-27 22:37:40 +03:00
TEST_CASE(trim)
{
{
String string {};
auto result = MUST(string.trim(" "sv, TrimMode::Both));
EXPECT(result.is_empty());
result = MUST(string.trim(" "sv, TrimMode::Left));
EXPECT(result.is_empty());
result = MUST(string.trim(" "sv, TrimMode::Right));
EXPECT(result.is_empty());
}
{
auto string = MUST(String::from_utf8("word"sv));
auto result = MUST(string.trim(" "sv, TrimMode::Both));
EXPECT_EQ(result, "word"sv);
result = MUST(string.trim(" "sv, TrimMode::Left));
EXPECT_EQ(result, "word"sv);
result = MUST(string.trim(" "sv, TrimMode::Right));
EXPECT_EQ(result, "word"sv);
}
{
auto string = MUST(String::from_utf8(" word"sv));
auto result = MUST(string.trim(" "sv, TrimMode::Both));
EXPECT_EQ(result, "word"sv);
result = MUST(string.trim(" "sv, TrimMode::Left));
EXPECT_EQ(result, "word"sv);
result = MUST(string.trim(" "sv, TrimMode::Right));
EXPECT_EQ(result, " word"sv);
}
{
auto string = MUST(String::from_utf8("word "sv));
auto result = MUST(string.trim(" "sv, TrimMode::Both));
EXPECT_EQ(result, "word"sv);
result = MUST(string.trim(" "sv, TrimMode::Left));
EXPECT_EQ(result, "word "sv);
result = MUST(string.trim(" "sv, TrimMode::Right));
EXPECT_EQ(result, "word"sv);
}
{
auto string = MUST(String::from_utf8(" word "sv));
auto result = MUST(string.trim(" "sv, TrimMode::Both));
EXPECT_EQ(result, "word"sv);
result = MUST(string.trim(" "sv, TrimMode::Left));
EXPECT_EQ(result, "word "sv);
result = MUST(string.trim(" "sv, TrimMode::Right));
EXPECT_EQ(result, " word"sv);
}
{
auto string = MUST(String::from_utf8(" word "sv));
auto result = MUST(string.trim("\t"sv, TrimMode::Both));
EXPECT_EQ(result, " word "sv);
result = MUST(string.trim("\t"sv, TrimMode::Left));
EXPECT_EQ(result, " word "sv);
result = MUST(string.trim("\t"sv, TrimMode::Right));
EXPECT_EQ(result, " word "sv);
}
{
auto string = MUST(String::from_utf8("ωΣωΣω"sv));
auto result = MUST(string.trim("ω"sv, TrimMode::Both));
EXPECT_EQ(result, "ΣωΣ"sv);
result = MUST(string.trim("ω"sv, TrimMode::Left));
EXPECT_EQ(result, "ΣωΣω"sv);
result = MUST(string.trim("ω"sv, TrimMode::Right));
EXPECT_EQ(result, "ωΣωΣ"sv);
}
{
auto string = MUST(String::from_utf8("ωΣωΣω"sv));
auto result = MUST(string.trim("ωΣ"sv, TrimMode::Both));
EXPECT(result.is_empty());
result = MUST(string.trim("ωΣ"sv, TrimMode::Left));
EXPECT(result.is_empty());
result = MUST(string.trim("ωΣ"sv, TrimMode::Right));
EXPECT(result.is_empty());
}
{
auto string = MUST(String::from_utf8("ωΣωΣω"sv));
auto result = MUST(string.trim("Σω"sv, TrimMode::Both));
EXPECT(result.is_empty());
result = MUST(string.trim("Σω"sv, TrimMode::Left));
EXPECT(result.is_empty());
result = MUST(string.trim("Σω"sv, TrimMode::Right));
EXPECT(result.is_empty());
}
}
Reference in New Issue Copy Permalink