Merge pull request #40999 from bruvzg/ctl_string_to_utf32

[Complex Test Layouts] Refactor `String` to use UTF-32 encoding.

2 files changed, 63 insertions, 4 deletions

diff --git a/doc/classes/PackedByteArray.xml b/doc/classes/PackedByteArray.xml
index 08f8558881..b1c4e54854 100644
--- a/doc/classes/PackedByteArray.xml
+++ b/doc/classes/PackedByteArray.xml
@@ -68,14 +68,28 @@
 			<return type="String">
 			</return>
 			<description>
-				Returns a copy of the array's contents as [String]. Fast alternative to [method get_string_from_utf8] if the content is ASCII-only. Unlike the UTF-8 function this function maps every byte to a character in the array. Multibyte sequences will not be interpreted correctly. For parsing user input always use [method get_string_from_utf8].
+				Converts ASCII/Latin-1 encoded array to [String]. Fast alternative to [method get_string_from_utf8] if the content is ASCII/Latin-1 only. Unlike the UTF-8 function this function maps every byte to a character in the array. Multibyte sequences will not be interpreted correctly. For parsing user input always use [method get_string_from_utf8].
+			</description>
+		</method>
+		<method name="get_string_from_utf16">
+			<return type="String">
+			</return>
+			<description>
+				Converts UTF-16 encoded array to [String]. If the BOM is missing, system endianness is assumed. Returns empty string if source array is not vaild UTF-16 string.
+			</description>
+		</method>
+		<method name="get_string_from_utf32">
+			<return type="String">
+			</return>
+			<description>
+				Converts UTF-32 encoded array to [String]. System endianness is assumed. Returns empty string if source array is not vaild UTF-32 string.
 			</description>
 		</method>
 		<method name="get_string_from_utf8">
 			<return type="String">
 			</return>
 			<description>
-				Returns a copy of the array's contents as [String]. Slower than [method get_string_from_ascii] but supports UTF-8 encoded data. Use this function if you are unsure about the source of the data. For user input this function should always be preferred.
+				Converts UTF-8 encoded array to [String]. Slower than [method get_string_from_ascii] but supports UTF-8 encoded data. Use this function if you are unsure about the source of the data. For user input this function should always be preferred. Returns empty string if source array is not vaild UTF-8 string.
 			</description>
 		</method>
 		<method name="has">
diff --git a/doc/classes/String.xml b/doc/classes/String.xml
index e134ae03e0..40fff25fc4 100644
--- a/doc/classes/String.xml
+++ b/doc/classes/String.xml
@@ -654,6 +654,17 @@
 				Returns the string's amount of characters.
 			</description>
 		</method>
+		<method name="lpad">
+			<return type="String">
+			</return>
+			<argument index="0" name="min_length" type="int">
+			</argument>
+			<argument index="1" name="character" type="String" default="&quot; &quot;">
+			</argument>
+			<description>
+				Formats a string to be at least [code]min_length[/code] long by adding [code]character[/code]s to the left of the string.
+			</description>
+		</method>
 		<method name="lstrip">
 			<return type="String">
 			</return>
@@ -695,6 +706,15 @@
 				Returns the MD5 hash of the string as a string.
 			</description>
 		</method>
+		<method name="naturalnocasecmp_to">
+			<return type="int">
+			</return>
+			<argument index="0" name="to" type="String">
+			</argument>
+			<description>
+				Performs a case-insensitive natural order comparison to another string. Returns [code]-1[/code] if less than, [code]+1[/code] if greater than, or [code]0[/code] if equal.
+			</description>
+		</method>
 		<method name="nocasecmp_to">
 			<return type="int">
 			</return>
@@ -816,6 +836,17 @@
 				Returns the right side of the string from a given position.
 			</description>
 		</method>
+		<method name="rpad">
+			<return type="String">
+			</return>
+			<argument index="0" name="min_length" type="int">
+			</argument>
+			<argument index="1" name="character" type="String" default="&quot; &quot;">
+			</argument>
+			<description>
+				Formats a string to be at least [code]min_length[/code] long by adding [code]character[/code]s to the right of the string.
+			</description>
+		</method>
 		<method name="rsplit">
 			<return type="PackedStringArray">
 			</return>
@@ -953,7 +984,7 @@
 			<return type="PackedByteArray">
 			</return>
 			<description>
-				Converts the String (which is a character array) to [PackedByteArray] (which is an array of bytes). The conversion is faster compared to [method to_utf8], as this method assumes that all the characters in the String are ASCII characters.
+				Converts the String (which is a character array) to ASCII/Latin-1 encoded [PackedByteArray] (which is an array of bytes). The conversion is faster compared to [method to_utf8], as this method assumes that all the characters in the String are ASCII/Latin-1 characters, unsupported characters are replaced with spaces.
 			</description>
 		</method>
 		<method name="to_float">
@@ -984,11 +1015,25 @@
 				Returns the string converted to uppercase.
 			</description>
 		</method>
+		<method name="to_utf16">
+			<return type="PackedByteArray">
+			</return>
+			<description>
+				Converts the String (which is an array of characters) to UTF-16 encoded [PackedByteArray] (which is an array of bytes).
+			</description>
+		</method>
+		<method name="to_utf32">
+			<return type="PackedByteArray">
+			</return>
+			<description>
+				Converts the String (which is an array of characters) to UTF-32 encoded [PackedByteArray] (which is an array of bytes).
+			</description>
+		</method>
 		<method name="to_utf8">
 			<return type="PackedByteArray">
 			</return>
 			<description>
-				Converts the String (which is an array of characters) to [PackedByteArray] (which is an array of bytes). The conversion is a bit slower than [method to_ascii], but supports all UTF-8 characters. Therefore, you should prefer this function over [method to_ascii].
+				Converts the String (which is an array of characters) to UTF-8 encode [PackedByteArray] (which is an array of bytes). The conversion is a bit slower than [method to_ascii], but supports all UTF-8 characters. Therefore, you should prefer this function over [method to_ascii].
 			</description>
 		</method>
 		<method name="trim_prefix">