mirror of
				https://github.com/RGBCube/serenity
				synced 2025-10-31 21:22:46 +00:00 
			
		
		
		
	AK: Rename Utf8CodepointIterator => Utf8CodePointIterator
This commit is contained in:
		
							parent
							
								
									628c7f094f
								
							
						
					
					
						commit
						407d6cd9e4
					
				
					 8 changed files with 37 additions and 37 deletions
				
			
		|  | @ -227,7 +227,7 @@ URL URLParser::parse(Badge<URL>, const StringView& raw_input, URL const* base_ur | |||
|     bool password_token_seen = false; | ||||
| 
 | ||||
|     Utf8View input(processed_input); | ||||
|     Utf8CodepointIterator iterator = input.begin(); | ||||
|     Utf8CodePointIterator iterator = input.begin(); | ||||
| 
 | ||||
|     auto get_remaining = [&input, &iterator] { | ||||
|         return input.substring_view(iterator - input.begin() + iterator.code_point_length_in_bytes()).as_string(); | ||||
|  |  | |||
|  | @ -36,17 +36,17 @@ const unsigned char* Utf8View::end_ptr() const | |||
|     return begin_ptr() + m_string.length(); | ||||
| } | ||||
| 
 | ||||
| Utf8CodepointIterator Utf8View::begin() const | ||||
| Utf8CodePointIterator Utf8View::begin() const | ||||
| { | ||||
|     return { begin_ptr(), m_string.length() }; | ||||
| } | ||||
| 
 | ||||
| Utf8CodepointIterator Utf8View::end() const | ||||
| Utf8CodePointIterator Utf8View::end() const | ||||
| { | ||||
|     return { end_ptr(), 0 }; | ||||
| } | ||||
| 
 | ||||
| Utf8CodepointIterator Utf8View::iterator_at_byte_offset(size_t byte_offset) const | ||||
| Utf8CodePointIterator Utf8View::iterator_at_byte_offset(size_t byte_offset) const | ||||
| { | ||||
|     size_t current_offset = 0; | ||||
|     for (auto iterator = begin(); !iterator.done(); ++iterator) { | ||||
|  | @ -57,7 +57,7 @@ Utf8CodepointIterator Utf8View::iterator_at_byte_offset(size_t byte_offset) cons | |||
|     return end(); | ||||
| } | ||||
| 
 | ||||
| size_t Utf8View::byte_offset_of(const Utf8CodepointIterator& it) const | ||||
| size_t Utf8View::byte_offset_of(const Utf8CodePointIterator& it) const | ||||
| { | ||||
|     VERIFY(it.m_ptr >= begin_ptr()); | ||||
|     VERIFY(it.m_ptr <= end_ptr()); | ||||
|  | @ -173,23 +173,23 @@ bool Utf8View::starts_with(const Utf8View& start) const | |||
|     return true; | ||||
| } | ||||
| 
 | ||||
| Utf8CodepointIterator::Utf8CodepointIterator(const unsigned char* ptr, size_t length) | ||||
| Utf8CodePointIterator::Utf8CodePointIterator(const unsigned char* ptr, size_t length) | ||||
|     : m_ptr(ptr) | ||||
|     , m_length(length) | ||||
| { | ||||
| } | ||||
| 
 | ||||
| bool Utf8CodepointIterator::operator==(const Utf8CodepointIterator& other) const | ||||
| bool Utf8CodePointIterator::operator==(const Utf8CodePointIterator& other) const | ||||
| { | ||||
|     return m_ptr == other.m_ptr && m_length == other.m_length; | ||||
| } | ||||
| 
 | ||||
| bool Utf8CodepointIterator::operator!=(const Utf8CodepointIterator& other) const | ||||
| bool Utf8CodePointIterator::operator!=(const Utf8CodePointIterator& other) const | ||||
| { | ||||
|     return !(*this == other); | ||||
| } | ||||
| 
 | ||||
| Utf8CodepointIterator& Utf8CodepointIterator::operator++() | ||||
| Utf8CodePointIterator& Utf8CodePointIterator::operator++() | ||||
| { | ||||
|     VERIFY(m_length > 0); | ||||
| 
 | ||||
|  | @ -206,7 +206,7 @@ Utf8CodepointIterator& Utf8CodepointIterator::operator++() | |||
|     return *this; | ||||
| } | ||||
| 
 | ||||
| size_t Utf8CodepointIterator::code_point_length_in_bytes() const | ||||
| size_t Utf8CodePointIterator::code_point_length_in_bytes() const | ||||
| { | ||||
|     VERIFY(m_length > 0); | ||||
|     size_t code_point_length_in_bytes = 0; | ||||
|  | @ -216,7 +216,7 @@ size_t Utf8CodepointIterator::code_point_length_in_bytes() const | |||
|     return code_point_length_in_bytes; | ||||
| } | ||||
| 
 | ||||
| u32 Utf8CodepointIterator::operator*() const | ||||
| u32 Utf8CodePointIterator::operator*() const | ||||
| { | ||||
|     VERIFY(m_length > 0); | ||||
| 
 | ||||
|  | @ -240,7 +240,7 @@ u32 Utf8CodepointIterator::operator*() const | |||
|     return code_point_value_so_far; | ||||
| } | ||||
| 
 | ||||
| Optional<u32> Utf8CodepointIterator::peek(size_t offset) const | ||||
| Optional<u32> Utf8CodePointIterator::peek(size_t offset) const | ||||
| { | ||||
|     if (offset == 0) { | ||||
|         if (this->done()) | ||||
|  |  | |||
|  | @ -14,21 +14,21 @@ namespace AK { | |||
| 
 | ||||
| class Utf8View; | ||||
| 
 | ||||
| class Utf8CodepointIterator { | ||||
| class Utf8CodePointIterator { | ||||
|     friend class Utf8View; | ||||
| 
 | ||||
| public: | ||||
|     Utf8CodepointIterator() = default; | ||||
|     ~Utf8CodepointIterator() = default; | ||||
|     Utf8CodePointIterator() = default; | ||||
|     ~Utf8CodePointIterator() = default; | ||||
| 
 | ||||
|     bool operator==(const Utf8CodepointIterator&) const; | ||||
|     bool operator!=(const Utf8CodepointIterator&) const; | ||||
|     Utf8CodepointIterator& operator++(); | ||||
|     bool operator==(const Utf8CodePointIterator&) const; | ||||
|     bool operator!=(const Utf8CodePointIterator&) const; | ||||
|     Utf8CodePointIterator& operator++(); | ||||
|     u32 operator*() const; | ||||
|     // NOTE: This returns {} if the peek is at or past EOF.
 | ||||
|     Optional<u32> peek(size_t offset = 0) const; | ||||
| 
 | ||||
|     ssize_t operator-(const Utf8CodepointIterator& other) const | ||||
|     ssize_t operator-(const Utf8CodePointIterator& other) const | ||||
|     { | ||||
|         return m_ptr - other.m_ptr; | ||||
|     } | ||||
|  | @ -37,14 +37,14 @@ public: | |||
|     bool done() const { return m_length == 0; } | ||||
| 
 | ||||
| private: | ||||
|     Utf8CodepointIterator(const unsigned char*, size_t); | ||||
|     Utf8CodePointIterator(const unsigned char*, size_t); | ||||
|     const unsigned char* m_ptr { nullptr }; | ||||
|     size_t m_length; | ||||
| }; | ||||
| 
 | ||||
| class Utf8View { | ||||
| public: | ||||
|     using Iterator = Utf8CodepointIterator; | ||||
|     using Iterator = Utf8CodePointIterator; | ||||
| 
 | ||||
|     Utf8View() = default; | ||||
|     explicit Utf8View(const String&); | ||||
|  | @ -54,13 +54,13 @@ public: | |||
| 
 | ||||
|     const StringView& as_string() const { return m_string; } | ||||
| 
 | ||||
|     Utf8CodepointIterator begin() const; | ||||
|     Utf8CodepointIterator end() const; | ||||
|     Utf8CodepointIterator iterator_at_byte_offset(size_t) const; | ||||
|     Utf8CodePointIterator begin() const; | ||||
|     Utf8CodePointIterator end() const; | ||||
|     Utf8CodePointIterator iterator_at_byte_offset(size_t) const; | ||||
| 
 | ||||
|     const unsigned char* bytes() const { return begin_ptr(); } | ||||
|     size_t byte_length() const { return m_string.length(); } | ||||
|     size_t byte_offset_of(const Utf8CodepointIterator&) const; | ||||
|     size_t byte_offset_of(const Utf8CodePointIterator&) const; | ||||
| 
 | ||||
|     Utf8View substring_view(size_t byte_offset, size_t byte_length) const; | ||||
|     Utf8View substring_view(size_t byte_offset) const { return substring_view(byte_offset, byte_length() - byte_offset); } | ||||
|  | @ -70,7 +70,7 @@ public: | |||
|     bool is_empty() const { return m_string.is_empty(); } | ||||
|     bool starts_with(const Utf8View&) const; | ||||
| 
 | ||||
|     size_t iterator_offset(const Utf8CodepointIterator& it) const | ||||
|     size_t iterator_offset(const Utf8CodePointIterator& it) const | ||||
|     { | ||||
|         return byte_offset_of(it); | ||||
|     } | ||||
|  | @ -103,5 +103,5 @@ private: | |||
| 
 | ||||
| } | ||||
| 
 | ||||
| using AK::Utf8CodepointIterator; | ||||
| using AK::Utf8CodePointIterator; | ||||
| using AK::Utf8View; | ||||
|  |  | |||
|  | @ -71,7 +71,7 @@ TEST_CASE(validate_invalid_ut8) | |||
| TEST_CASE(iterate_utf8) | ||||
| { | ||||
|     Utf8View view("Some weird characters \u00A9\u266A\uA755"); | ||||
|     Utf8CodepointIterator iterator = view.begin(); | ||||
|     Utf8CodePointIterator iterator = view.begin(); | ||||
| 
 | ||||
|     EXPECT(*iterator == 'S'); | ||||
|     EXPECT(iterator.peek().has_value() && iterator.peek().value() == 'S'); | ||||
|  | @ -98,7 +98,7 @@ TEST_CASE(iterate_utf8) | |||
| 
 | ||||
|     EXPECT(iterator.done()); | ||||
|     EXPECT(!iterator.peek(0).has_value()); | ||||
|     EXPECT_CRASH("Dereferencing Utf8CodepointIterator which is already done.", [&iterator] { | ||||
|     EXPECT_CRASH("Dereferencing Utf8CodePointIterator which is already done.", [&iterator] { | ||||
|         *iterator; | ||||
|         return Test::Crash::Failure::DidNotCrash; | ||||
|     }); | ||||
|  |  | |||
|  | @ -20,14 +20,14 @@ public: | |||
|     explicit StringIterator(Object& prototype, String string); | ||||
|     virtual ~StringIterator() override; | ||||
| 
 | ||||
|     Utf8CodepointIterator& iterator() { return m_iterator; } | ||||
|     Utf8CodePointIterator& iterator() { return m_iterator; } | ||||
|     bool done() const { return m_done; } | ||||
| 
 | ||||
| private: | ||||
|     friend class StringIteratorPrototype; | ||||
| 
 | ||||
|     String m_string; | ||||
|     Utf8CodepointIterator m_iterator; | ||||
|     Utf8CodePointIterator m_iterator; | ||||
|     bool m_done { false }; | ||||
| }; | ||||
| 
 | ||||
|  |  | |||
|  | @ -99,7 +99,7 @@ private: | |||
| 
 | ||||
|     String m_decoded_input; | ||||
|     Utf8View m_utf8_view; | ||||
|     AK::Utf8CodepointIterator m_utf8_iterator; | ||||
|     AK::Utf8CodepointIterator m_prev_utf8_iterator; | ||||
|     AK::Utf8CodePointIterator m_utf8_iterator; | ||||
|     AK::Utf8CodePointIterator m_prev_utf8_iterator; | ||||
| }; | ||||
| } | ||||
|  |  | |||
|  | @ -2675,7 +2675,7 @@ bool HTMLTokenizer::consumed_as_part_of_an_attribute() const | |||
|     return m_return_state == State::AttributeValueUnquoted || m_return_state == State::AttributeValueSingleQuoted || m_return_state == State::AttributeValueDoubleQuoted; | ||||
| } | ||||
| 
 | ||||
| void HTMLTokenizer::restore_to(const Utf8CodepointIterator& new_iterator) | ||||
| void HTMLTokenizer::restore_to(const Utf8CodePointIterator& new_iterator) | ||||
| { | ||||
|     if (new_iterator != m_prev_utf8_iterator) { | ||||
|         auto diff = m_prev_utf8_iterator - new_iterator; | ||||
|  |  | |||
|  | @ -146,7 +146,7 @@ private: | |||
| 
 | ||||
|     bool consumed_as_part_of_an_attribute() const; | ||||
| 
 | ||||
|     void restore_to(const Utf8CodepointIterator& new_iterator); | ||||
|     void restore_to(const Utf8CodePointIterator& new_iterator); | ||||
|     auto& nth_last_position(size_t n = 0) { return m_source_positions.at(m_source_positions.size() - 1 - n); } | ||||
| 
 | ||||
|     State m_state { State::Data }; | ||||
|  | @ -159,8 +159,8 @@ private: | |||
|     StringView m_input; | ||||
| 
 | ||||
|     Utf8View m_utf8_view; | ||||
|     Utf8CodepointIterator m_utf8_iterator; | ||||
|     Utf8CodepointIterator m_prev_utf8_iterator; | ||||
|     Utf8CodePointIterator m_utf8_iterator; | ||||
|     Utf8CodePointIterator m_prev_utf8_iterator; | ||||
| 
 | ||||
|     HTMLToken m_current_token; | ||||
| 
 | ||||
|  |  | |||
		Loading…
	
	Add table
		Add a link
		
	
		Reference in a new issue
	
	 Andreas Kling
						Andreas Kling