note
	description: "Eiffel implementations for Unicode encoding conversion."
	legal: "See notice at end of class."
	status: "See notice at end of class."
	date: "$Date: 2020-05-20 11:14:50 +0000 (Wed, 20 May 2020) $"
	revision: "$Revision: 104299 $"

class interface
	UNICODE_CONVERSION

create {ENCODING}
	default_create
			-- Process instances of classes with no creation clause.
			-- (Default: do nothing.)
			-- (from ANY)

feature -- Access

	generating_type: TYPE [detachable UNICODE_CONVERSION]
			-- Type of current object
			-- (type of which it is a direct instance)
			-- (from ANY)
		ensure -- from ANY
			generating_type_not_void: Result /= Void

	generator: STRING_8
			-- Name of current object's generating class
			-- (base class of the type of which it is a direct instance)
			-- (from ANY)
		ensure -- from ANY
			generator_not_void: Result /= Void
			generator_not_empty: not Result.is_empty
	
feature -- Comparison

	frozen deep_equal (a: detachable ANY; b: like arg #1): BOOLEAN
			-- Are a and b either both void
			-- or attached to isomorphic object structures?
			-- (from ANY)
		ensure -- from ANY
			instance_free: class
			shallow_implies_deep: standard_equal (a, b) implies Result
			both_or_none_void: (a = Void) implies (Result = (b = Void))
			same_type: (Result and (a /= Void)) implies (b /= Void and then a.same_type (b))
			symmetric: Result implies deep_equal (b, a)

	frozen equal (a: detachable ANY; b: like arg #1): BOOLEAN
			-- Are a and b either both void or attached
			-- to objects considered equal?
			-- (from ANY)
		ensure -- from ANY
			instance_free: class
			definition: Result = (a = Void and b = Void) or else ((a /= Void and b /= Void) and then a.is_equal (b))

	frozen is_deep_equal alias "≡≡≡" (other: UNICODE_CONVERSION): BOOLEAN
			-- Are Current and other attached to isomorphic object structures?
			-- (from ANY)
		require -- from ANY
			other_not_void: other /= Void
		ensure -- from ANY
			shallow_implies_deep: standard_is_equal (other) implies Result
			same_type: Result implies same_type (other)
			symmetric: Result implies other.is_deep_equal (Current)

	is_equal (other: UNICODE_CONVERSION): BOOLEAN
			-- Is other attached to an object considered
			-- equal to current object?
			-- (from ANY)
		require -- from ANY
			other_not_void: other /= Void
		ensure -- from ANY
			symmetric: Result implies other ~ Current
			consistent: standard_is_equal (other) implies Result

	frozen standard_equal (a: detachable ANY; b: like arg #1): BOOLEAN
			-- Are a and b either both void or attached to
			-- field-by-field identical objects of the same type?
			-- Always uses default object comparison criterion.
			-- (from ANY)
		ensure -- from ANY
			instance_free: class
			definition: Result = (a = Void and b = Void) or else ((a /= Void and b /= Void) and then a.standard_is_equal (b))

	frozen standard_is_equal alias "≜" (other: UNICODE_CONVERSION): BOOLEAN
			-- Is other attached to an object of the same type
			-- as current object, and field-by-field identical to it?
			-- (from ANY)
		require -- from ANY
			other_not_void: other /= Void
		ensure -- from ANY
			same_type: Result implies same_type (other)
			symmetric: Result implies other.standard_is_equal (Current)
	
feature -- Status report

	conforms_to (other: ANY): BOOLEAN
			-- Does type of current object conform to type
			-- of other (as per Eiffel: The Language, chapter 13)?
			-- (from ANY)
		require -- from ANY
			other_not_void: other /= Void

	same_type (other: ANY): BOOLEAN
			-- Is type of current object identical to type of other?
			-- (from ANY)
		require -- from ANY
			other_not_void: other /= Void
		ensure -- from ANY
			definition: Result = (conforms_to (other) and other.conforms_to (Current))
	
feature -- Conversion

	convert_to (a_from_code_page: READABLE_STRING_8; a_from_string: READABLE_STRING_GENERAL; a_to_code_page: READABLE_STRING_8)
			-- Convert between Unicode encodings.
		require -- from ENCODING_I
			a_from_code_page_valid: is_code_page_valid (a_from_code_page)
			a_to_code_page_valid: is_code_page_valid (a_to_code_page)
			code_page_convertible: is_code_page_convertible (a_from_code_page, a_to_code_page)
			a_from_string_not_void: a_from_string /= Void
		ensure -- from ENCODING_I
			success_implies_not_void: last_conversion_successful implies last_converted_stream /= Void
			success_implies_not_void: last_conversion_successful implies last_converted_string /= Void

	multi_byte_to_pointer (a_string: READABLE_STRING_8): MANAGED_POINTER
			-- Managed pointer of a_string.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_string_not_void: a_string /= Void
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void

	pointer_to_multi_byte (a_multi_string: POINTER; a_count: INTEGER_32): STRING_8
			-- STRING_8 read from a_multi_string.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_multi_string_not_default: a_multi_string /= default_pointer
			a_count_non_negative: a_count >= 0
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void

	pointer_to_string_32 (a_w_string: POINTER; a_count: INTEGER_32): STRING_32
			-- STRING_32 read from a_w_string of a_count bytes.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_w_string_not_default: a_w_string /= default_pointer
			a_count_non_negative: a_count >= 0
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void

	pointer_to_wide_string (a_w_string: POINTER; a_count: INTEGER_32): STRING_32
			-- STRING_32 read from a_w_string of a_count bytes.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_w_string_not_default: a_w_string /= default_pointer
			a_count_non_negative: a_count >= 0
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void

	string_16_to_stream (a_string: STRING_32): STRING_8
			-- We use a_string as 2 bytes encoding string, the first two bytes are not used.
			-- in the endianness of the current platform.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_string_not_void: a_string /= Void
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void
			valid_count: Result.count = a_string.count * 2

	string_32_to_multi_byte (a_string: STRING_32): STRING_8
			-- Byte stream of a_string in endianness of the current platform.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_string_not_void: a_string /= Void
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void

	string_8_to_wide_string (a_w_string: STRING_8): STRING_32
			-- Interpret a_w_string as a sequence of 2-byte characters into a STRING_32
			-- in endianness of the current platform.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_w_string_not_void: a_w_string /= Void
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void

	string_general_to_stream (a_string: READABLE_STRING_GENERAL): STRING_8
			-- Streamize a_string.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_string_not_void: a_string /= Void
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void

	wide_string_to_pointer (a_string: READABLE_STRING_32): MANAGED_POINTER
			-- Managed pointer of a_string which is taken as
			-- 16bits string. High 16bits of characters of a_string are discarded.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_string_not_void: a_string /= Void
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void
	
feature -- Duplication

	copy (other: UNICODE_CONVERSION)
			-- Update current object using fields of object attached
			-- to other, so as to yield equal objects.
			-- (from ANY)
		require -- from ANY
			other_not_void: other /= Void
			type_identity: same_type (other)
		ensure -- from ANY
			is_equal: Current ~ other

	frozen deep_copy (other: UNICODE_CONVERSION)
			-- Effect equivalent to that of:
			--		copy (other . deep_twin)
			-- (from ANY)
		require -- from ANY
			other_not_void: other /= Void
		ensure -- from ANY
			deep_equal: deep_equal (Current, other)

	frozen deep_twin: UNICODE_CONVERSION
			-- New object structure recursively duplicated from Current.
			-- (from ANY)
		ensure -- from ANY
			deep_twin_not_void: Result /= Void
			deep_equal: deep_equal (Current, Result)

	frozen standard_copy (other: UNICODE_CONVERSION)
			-- Copy every field of other onto corresponding field
			-- of current object.
			-- (from ANY)
		require -- from ANY
			other_not_void: other /= Void
			type_identity: same_type (other)
		ensure -- from ANY
			is_standard_equal: standard_is_equal (other)

	frozen standard_twin: UNICODE_CONVERSION
			-- New object field-by-field identical to other.
			-- Always uses default copying semantics.
			-- (from ANY)
		ensure -- from ANY
			standard_twin_not_void: Result /= Void
			equal: standard_equal (Result, Current)

	frozen twin: UNICODE_CONVERSION
			-- New object equal to Current
			-- twin calls copy; to change copying/twinning semantics, redefine copy.
			-- (from ANY)
		ensure -- from ANY
			twin_not_void: Result /= Void
			is_equal: Result ~ Current
	
feature -- Basic operations

	frozen default: detachable UNICODE_CONVERSION
			-- Default value of object's type
			-- (from ANY)

	frozen default_pointer: POINTER
			-- Default value of type POINTER
			-- (Avoid the need to write p.default for
			-- some p of type POINTER.)
			-- (from ANY)
		ensure -- from ANY
			instance_free: class

	default_rescue
			-- Process exception for routines with no Rescue clause.
			-- (Default: do nothing.)
			-- (from ANY)

	frozen do_nothing
			-- Execute a null action.
			-- (from ANY)
		ensure -- from ANY
			instance_free: class
	
feature -- Endian

	Is_little_endian: BOOLEAN
			-- Is this system little endian?
			-- (from ENCODING_HELPER)
		ensure -- from ENCODING_HELPER
			instance_free: class

	string_16_switch_endian (a_str: STRING_32): STRING_32
			-- Switch endian of a_str for low bits.
			-- High bits are cleaned.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_str_not_void: a_str /= Void
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void

	string_32_switch_endian (a_str: STRING_32): STRING_32
			-- Switch endian of a_str for both high and low bits.
			-- (from ENCODING_HELPER)
		require -- from ENCODING_HELPER
			a_str_not_void: a_str /= Void
		ensure -- from ENCODING_HELPER
			instance_free: class
			result_not_void: Result /= Void
	
feature -- Explicit Conversion

	append_code_point_to_utf8 (a_code: NATURAL_32; a_string: STRING_8)
			-- Append a Unicode code point a_code to a UTF-8 stream.
		require
			a_string_not_void: a_string /= Void
			a_code_is_valid: a_code >= 0 and then a_code <= 1114111
		ensure
			a_string_appended: (a_code <= 127 implies a_string.count = old a_string.count + 1) and ((a_code > 127 and a_code <= 2047) implies a_string.count = old a_string.count + 2) and ((a_code > 2047 and a_code <= 65535) implies a_string.count = old a_string.count + 3) and ((a_code > 65535 and a_code <= 1114111) implies a_string.count = old a_string.count + 4)

	read_character_from_utf8 (a_position: INTEGER_32; a_read_bytes: detachable INTEGER_32_REF; a_string: READABLE_STRING_8): CHARACTER_32
			-- Read a Unicode character from UTF-8 string.
			-- a_string is in UTF-8.
			-- a_position is the starting byte point of a character.
			-- a_read_bytes is the number of bytes read.
		require
			a_string_not_void: a_string /= Void
			a_position_in_range: a_position > 0 and a_position <= a_string.count
			a_position_valid: a_string.code (a_position).to_natural_8 <= 127 or (a_string.code (a_position).to_natural_8 & 224) = 192 or (a_string.code (a_position).to_natural_8 & 240) = 224 or (a_string.code (a_position).to_natural_8 & 248) = 240 or (a_string.code (a_position).to_natural_8 & 252) = 248 or (a_string.code (a_position).to_natural_8 & 254) = 252

	utf16_to_utf32 (a_str: READABLE_STRING_32): STRING_32
			-- Convert utf16 to utf32.
		require
			a_str_not_void: a_str /= Void
		ensure
			instance_free: class
			result_not_void: Result /= Void

	utf32_to_utf16 (a_str: READABLE_STRING_32): STRING_32
			-- Convert utf32 to utf16 without data lose.
		require
			a_str_not_void: a_str /= Void
		ensure
			instance_free: class
			result_not_void: Result /= Void

	utf32_to_utf8 (a_string: READABLE_STRING_32): STRING_8
			-- Convert UTF32 to UTF8.
		require
			a_string_not_void: a_string /= Void
		ensure
			result_not_void: Result /= Void

	utf8_to_utf32 (a_string: READABLE_STRING_8): STRING_32
			-- UTF8 to UTF32 conversion, Eiffel implementation.
		require
			a_string_not_void: a_string /= Void
		ensure
			result_not_void: Result /= Void
	
feature -- Output

	Io: STD_FILES
			-- Handle to standard file setup
			-- (from ANY)
		ensure -- from ANY
			instance_free: class
			io_not_void: Result /= Void

	out: STRING_8
			-- New string containing terse printable representation
			-- of current object
			-- (from ANY)
		ensure -- from ANY
			out_not_void: Result /= Void

	print (o: detachable ANY)
			-- Write terse external representation of o
			-- on standard output.
			-- (from ANY)
		ensure -- from ANY
			instance_free: class

	frozen tagged_out: STRING_8
			-- New string containing terse printable representation
			-- of current object
			-- (from ANY)
		ensure -- from ANY
			tagged_out_not_void: Result /= Void
	
feature -- Platform

	Operating_environment: OPERATING_ENVIRONMENT
			-- Objects available from the operating system
			-- (from ANY)
		ensure -- from ANY
			instance_free: class
			operating_environment_not_void: Result /= Void
	
feature -- Query

	is_code_page_convertible (a_from_code_page, a_to_code_page: READABLE_STRING_8): BOOLEAN
			-- Is a_from_code_page convertible to a_to_code_page.

	is_code_page_valid (a_code_page: READABLE_STRING_8): BOOLEAN
			-- Is a_code_page valid?

	is_valid_as_string_16 (a_string: READABLE_STRING_GENERAL): BOOLEAN
			-- Check high 16 bit of any char in a_string is zero.

	is_valid_utf8 (a_string: READABLE_STRING_8): BOOLEAN
			-- Is a_string valid UTF-8 string?
		require
			a_string_not_void: a_string /= Void

	Last_conversion_lost_data: BOOLEAN = False
			-- Has last conversion between two encodings lost data?
	
invariant
		-- from ANY
	reflexive_equality: standard_is_equal (Current)
	reflexive_conformance: conforms_to (Current)

note
	library: "Encoding: Library of reusable components for Eiffel."
	copyright: "Copyright (c) 1984-2020, Eiffel Software and others"
	license: "Eiffel Forum License v2 (see http://www.eiffel.com/licensing/forum.txt)"
	source: "[
		Eiffel Software
		5949 Hollister Ave., Goleta, CA 93117 USA
		Telephone 805-685-1006, Fax 805-685-6869
		Website http://www.eiffel.com
		Customer support http://support.eiffel.com
	]"

end -- class UNICODE_CONVERSION

Generated by ISE EiffelStudio