lazarus/docs/xml/lazutils/lazutf8.xml

<?xml version="1.0" encoding="UTF-8"?>
<!--

Documentation for LCL (Lazarus Component Library) and LazUtils (Lazarus 
Utilities) are published under the Creative Commons Attribution-ShareAlike 4.0 
International public license.

https://creativecommons.org/licenses/by-sa/4.0/legalcode.txt
https://gitlab.com/freepascal.org/lazarus/lazarus/-/blob/main/docs/cc-by-sa-4-0.txt

Copyright (c) 1997-2025, by the Lazarus Development Team.

-->
<fpdoc-descriptions>
<package name="lazutils">
<!--
====================================================================
LazUTF8
====================================================================
-->
<module name="LazUTF8">
<short>
Routines for managing UTF-8-encoded strings.
</short>
<descr>
<p>
<file>lazutf8.pas</file> contains useful routines for managing UTF-8-encoded 
strings. All routines are thread-safe unless explicitly stated.
</p>
<p>
<file>lazutf8.pas</file> is part of the <file>LazUtils</file> package.
</p>
</descr>

<!-- unresolved externals -->
<element name="cwstring"/>
<element name="FPCAdds"/>
<element name="Windows"/>
<element name="Classes"/>
<element name="SysUtils"/>
<element name="StrUtils"/>

<element name="NeedRTLAnsi">
<short>
Indicates if the OS requires use of AnsiToUTF8 and UTF8ToAnsi for the RTL.
</short>
<descr>
<p>
<var>NeedRTLAnsi</var> is a <var>Boolean</var> function that indicates if the 
OS requires use of <var>AnsiToUTF8</var> and <var>UTF8ToAnsi</var> for the 
RTL. AnsiToUTF8 and UTF8ToAnsi need a widestring manager under Linux, BSD, 
and Mac OSX. Normally these OS's use UTF-8 as the system encoding so the 
<var>WideStringManager</var> is not needed.
</p>
<p>
For the Windows environment, NeedRTLAnsi is <b>True</b> if the default system 
code page is not <var>CP_UTF8</var>. For UNIX-like environments, NeedRTLAnsi 
is <b>True</b> when any of the <b>LC_ALL</b>, <b>LC_MESSAGES</b>, or 
<b>LANG</b> environment variables contain a language code other than UTF-8.
</p>
</descr>
<seealso>
<link id="#rtl.system.DefaultSystemCodePage">DefaultSystemCodePage</link>
</seealso>
</element>
<element name="NeedRTLAnsi.Result">
<short>True when the system encoding is not UTF-8.</short>
</element>

<element name="SetNeedRTLAnsi">
<short>Sets the value for the unit global variable.</short>
<descr></descr>
<seealso>
<link id="NeedRTLAnsi"/>
</seealso>
</element>
<element name="SetNeedRTLAnsi.NewValue">
<short>New value for the variable.</short>
</element>

<element name="UTF8ToSys">
<short>
Ensures UTF-8 characters (or format settings) are converted to the system 
code page.
</short>
<descr>
<p>
<var>UTF8ToSys</var> is an overloaded function used to convert the specified 
string value (or format settings) to the system codepage for the platform. 
UTF8ToSys works like <var>UTF8ToAnsi</var>, but is more independent of 
WideStringManager. For platforms where UTF8_RTL is not defined, and 
NeedRTLAnsi returns <b>True</b>, UTF8ToAnsi is called to convert non-ASCII 
values in <var>s</var>. For platforms where UTF8_RTL is defined, the value in 
s is used without modification.
</p>
<p>
An overloaded variant of the function handles <var>TFormatSettings</var> for 
the platform. The return value for the function is the specified values in 
<var>AFormatSettings</var> after being updated to reflect the system codepage 
for the platform. For platforms where UTF8_RTL is not defined, the values in 
the following format settings are updated: <var>CurrencyString</var>, 
<var>LongMonthNames</var>, <var>ShortMonthNames</var>, 
<var>LongDayNames</var>, and <var>ShortDayNames</var>.
</p>
<p>
No actions are needed for platforms where UTF8_RTL is defined.
</p>
</descr>
<seealso>
<link id="#rtl.system.Utf8ToAnsi">Utf8ToAnsi</link>
<link id="#rtl.sysutils.TFormatSettings">TFormatSettings</link>
</seealso>
</element>
<element name="UTF8ToSys.Result">
<short>Value for the string after conversion.</short>
</element>
<element name="UTF8ToSys.s">
<short>Value to examine in the function.</short>
</element>
<element name="UTF8ToSys.AFormatSettings">
<short>Format settings to examine in the function.</short>
</element>

<element name="SysToUTF8">
<short>
Converts strings (and format settings) from the system codepage to UTF-8.
</short>
<descr>
<p>
<var>SysToUTF8</var> is an overloaded function used to convert strings (and 
format settings) from the system codepage to UTF-8. SysToUTF8 works like 
<var>AnsiToUTF8</var>, but has no reliance on the widestring manager on 
platforms where UTF8_RTL is defined. For platforms where UTF8_RTL is not 
defined, and NeedRTLAnsi contains <b>True</b>, non-ASCII values are converted 
to UTF-8 by calling <var>AnsiToUTF8</var>.
</p>
<p>
An overloaded variant of the function handles <var>TFormatSettings</var> for 
the platform. The return value for the function is the values specified in 
AFormatSettings after conversion from the system codepage to UTF-8. The 
values in the following format settings are updated: 
<var>CurrencyString</var>, <var>LongMonthNames</var>, 
<var>ShortMonthNames</var>, <var>LongDayNames</var>, and 
<var>ShortDayNames</var>.
</p>
</descr>
<seealso>
<link id="#rtl.system.AnsiToUTF8">AnsiToUTF8</link>
<link id="#rtl.sysutils.TFormatSettings">TFormatSettings</link>
</seealso>
</element>
<element name="SysToUTF8.Result">
<short>Values after conversion to UTF-8.</short>
</element>
<element name="SysToUTF8.s">
<short>Values to examine in the function.</short>
</element>
<element name="SysToUTF8.AFormatSettings">
<short>Format settings to examine in the function.</short>
</element>

<element name="ConsoleToUTF8">
<short>
Converts an OEM-encoded string to UTF8.
</short>
<descr>
<p>
<var>ConsoleToUTF8</var> is a <var>String</var> function used to converts an 
OEM-encoded string to UTF8. The implementation of ConsoleToUTF8 is 
OS-specific, and essentially handles differences between various Windows 
platforms where use of <var>OemToChar</var> and <var>WinCPToUTF8</var> are 
required. For UNIX-like environments, the value in s is converted by calling 
<var>SysToUTF8</var>.
</p>
<p>
ConsoleToUTF8 is used in the implementation of the 
<var>GetEnvironmentStringUTF8</var> and <var>GetEnvironmentVariableUTF8</var> 
functions.
</p>
</descr>
<seealso>
<link id="SysToUTF8"/>
<link id="WinCPToUTF8"/>
<link id="GetEnvironmentStringUTF8"/>
<link id="GetEnvironmentVariableUTF8"/>
</seealso>
</element>
<element name="ConsoleToUTF8.Result">
<short>UTF-8-encoded value for the specified string.</short>
</element>
<element name="ConsoleToUTF8.s">
<short>Value to convert in the function.</short>
</element>

<element name="UTF8ToConsole">
<short>
Converts a UTF-8-encoded string to console (OEM) encoding.
</short>
<descr>
<p>
<var>UTF8ToConsole</var> converts a UTF-8-encoded string to console (OEM) 
encoding as used in <var>Write</var> and <var>WriteLn</var>. The 
implementation is platform specific.
</p>
<p>
For the Windows environment, either <var>UTF8ToSys</var> or 
<var>UTF8ToWinCP</var> is used to convert the value to the codepage or 
character set needed in RTL. The Windows <var>CharToOem</var> API is used to 
prepare the return value. In UNIX-like environments, <var>UTF8ToSys</var> is 
used to get the return value .
</p>
</descr>
<seealso>
<link id="UTF8ToSys"/>
<link id="UTF8ToWinCP"/>
</seealso>
</element>
<element name="UTF8ToConsole.Result">
<short>OEM-encoded value for the string.</short>
</element>
<element name="UTF8ToConsole.s">
<short>UTF-8-encode input values.</short>
</element>

<element name="WinCPToUTF8">
<short>
Converts the string from Windows code page to UTF-8.
</short>
<descr>
<p>
Converts the string from Windows code page to UTF-8. Used with some 
Windows-specific functions. For all Windows versions supporting 8-bit 
codepages (but not WinCE).
</p>
</descr>
<seealso/>
</element>
<element name="WinCPToUTF8.Result">
<short>UTF-8-encoded values for the string.</short>
</element>
<element name="WinCPToUTF8.s">
<short>Input values in Windows codepage encoding.</short>
</element>

<element name="UTF8ToWinCP">
<short>
Converts the UTF-8-encoded string to the Windows code page encoding.
</short>
<descr>
<p>
Converts the UTF-8-encoded string to the Windows code page encoding Used by 
<var>Write</var> and <var>WriteLn</var>.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8ToWinCP.Result">
<short>UTF-8-encoded input values.</short>
</element>
<element name="UTF8ToWinCP.s">
<short>Values in the Windows codepage encoding.</short>
</element>

<element name="ParamStrUTF8">
<short>
Gets the specified command line parameter and converts it to a UTF-8-encoded 
string.
</short>
<descr>
<p>
<var>ParamStrUTF8</var> is a <var>String</var> function used to convert the 
specified command line parameter to a UTF-8-encoded string. The 
implementation for ParamStrUTF8 is OS- or platform-specific. For UNIX-like 
environments, SysToUTF8 is called to convert the value for the command line 
parameter at the position in Param. For Windows platforms, the stub for the 
Ansi or WideString version of ParamStrUTF8 is called. ParamStrUTF8 is the 
UTF-8-enabled counterpart to the ParamStr routine in RTL.
</p>
<p>
<var>Index</var> is the ordinal position for the requested parameter value. 
Index should be in the range <b>0..<var>ParamCount</var></b>. Values in Index 
outside this range cause an empty string ('') to be returned for a parameter 
value.
</p>
<p>
In most cases, the parameter at position <b>0</b> contains the name and 
optional path to the executable file for the application. For cross-platform 
compatibility, use the ExeName property in TCustomApplication to get the path 
and name for the binary instead. Subsequent index positions contain any command 
line arguments passed to the executable.
</p>
<p>
The return value contains the UTF-8-encoded string with the value for the 
parameter at the specified position, or an empty string when not present.
</p>
</descr>
<seealso>
<link id="SysToUTF8"/>
<link id="#fcl.custapp.TCustomApplication.ExeName">TCustomApplication.ExeName</link>
<link id="#rtl.system.ParamStr">ParamStr</link>
</seealso>
</element>
<element name="ParamStrUTF8.Result">
<short>
UTF-8-encoded value for the specified command line parameter.
</short>
</element>
<element name="ParamStrUTF8.Param">
<short>
Ordinal position for the command line parameter retrieved in the routine.
</short>
</element>

<element name="GetFormatSettingsUTF8">
<short>
Gets the TFormatSettings for the platform.
</short>
<descr>
<p>
<var>GetFormatSettingsUTF8</var> is a procedure used to get the 
<var>TFormatSettings</var> for the Locale or Language Code for the platform. 
GetFormatSettingsUTF8 is defined for Windows environments only, and calls 
<var>GetLocaleFormatSettingsUTF8</var> using the ThreadLocale or Language 
Code ID needed for the platform.
</p>
</descr>
<seealso>
<link id="GetFormatSettingsUTF8"/>
<link id="GetLocaleFormatSettingsUTF8"/>
</seealso>
</element>

<element name="GetLocaleFormatSettingsUTF8">
<short>
Gets format settings for a specific Language Code ID.
</short>
<descr>
<p>
<var>GetLocaleFormatSettingsUTF8</var> is a procedure used to get the 
<var>TFormatSettings</var> for the Locale or Language Code for the platform. 
GetLocaleFormatSettingsUTF8 is defined for Windows environments only. 
</p>
<p>
GetLocaleFormatSettingsUTF8 ensures that values in the format settings use 
the Language Code ID for the platform. The following format settings are 
converted to their Locale-specific values:
</p>
<ul>
<li>ShortMonthNames</li>
<li>LongMonthNames</li>
<li>ShortDayName</li>
<li>LongDayName</li>
<li>DateSeparator</li>
<li>ShortDateFormat</li>
<li>LongDateFormat</li>
<li>TimeSeparator</li>
<li>TimeAMString</li>
<li>TimePMString</li>
<li>ShortTimeFormat</li>
<li>LongTimeFormat</li>
<li>CurrencyString</li>
<li>CurrencyFormat</li>
<li>NegCurrFormat</li>
<li>ThousandSeparator</li>
<li>DecimalSeparator</li>
<li>CurrencyDecimals</li>
<li>ListSeparator</li>
</ul>
<p>
In LCL version 3.0 or higher, LongTimeFormat and ShortTimeFormat can contain 
AM / PM format specifiers; i. e. 'hh:nn:ss AMPM'
</p>
</descr>
<version>
Modified in LCL version 3.0 to return 12-hour time formats using AM / PM in 
format settings.
</version>
<seealso>
<link id="#rtl.sysutils.TFormatSettings">TFormatSettings</link>
</seealso>
</element>
<element name="GetLocaleFormatSettingsUTF8.LCID">
<short>Language Code ID.</short>
</element>
<element name="GetLocaleFormatSettingsUTF8.AFormatSettings">
<short>The locale-specific format settings for the platform.</short>
</element>

<element name="GetEnvironmentVariableCountUTF8">
<short>
Returns the number of system environment variables.
</short>
<descr>
<p>
Returns the number of UTF-8-encoded system environment variables. Used 
together with <var>GetEnvironmentStringUTF8</var>.
</p>
</descr>
</element>
<element name="GetEnvironmentVariableCountUTF8.Result">
<short>Number of variables in the system environment.</short>
</element>

<element name="GetEnvironmentStringUTF8">
<short>
Returns a system environment string.
</short>
<descr>
<p>
Returns a UTF-8-encoded system environment string stored at the specified 
position. The value in <var>Index</var> is in the range 
1..GetEnvironmentVariableCountUTF8. For Unix and Windows the string normally 
is in the form 'name=value'. Beware that Windows knows some special formats, 
e.g. '=C:=SomePath'. Nota bene: Raymond Chen called these "bookkeeping 
variables" which emulate the MS-DOS tracking mechanism for the current 
directory on different drives.
</p>
<p>
Use <var>GetEnvironmentVariableUTF8</var> to lookup values for environment 
variables by name.
</p>
</descr>
</element>
<element name="GetEnvironmentStringUTF8.Result">
<short>Value for the environment variable at the specified position.</short>
</element>
<element name="GetEnvironmentStringUTF8.Index">
<short>Position for the environment variable.</short>
</element>

<element name="GetEnvironmentVariableUTF8">
<short>
Returns the value of a system environment variable.
</short>
<descr>
<p>
Returns the value of an environment variable stored in the form 
'EnvVar=value'. See <var>GetEnvironmentStringUTF8</var> to retrieve the whole 
list of environment strings.
</p>
</descr>
</element>
<element name="GetEnvironmentVariableUTF8.Result">
<short>Value for the specified environment variable name.</short>
</element>
<element name="GetEnvironmentVariableUTF8.EnvVar">
<short>Environment variable with the value retrieved in the routine.</short>
</element>

<element name="SysErrorMessageUTF8">
<short>
Gets the UTF-8-encoded system error message for the specified error code.
</short>
<descr>
<p>
<var>SysErrorMessageUTF8</var> is used to get the UTF-8-encoded system error 
message for the specified error code. SysErrorMessageUTF8 calls the 
<var>SysUtils.SysErrorMessage</var> function and converts the error message 
using <var>SysToUTF8</var>.
</p>
</descr>
<seealso/>
</element>
<element name="SysErrorMessageUTF8.Result">
<short>UTF-8-encoded value for the system error message.</short>
</element>
<element name="SysErrorMessageUTF8.ErrorCode">
<short>Numeric system error code for the message.</short>
</element>

<element name="UTF8CodepointSize">
<short>
Returns the size of the UTF-8 codepoint in bytes.
</short>
<descr>
<p>
Returns the size of the UTF-8 codepoint in bytes. The return value is for a 
single codepoint.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8CodepointSize.Result">
<short>Number of bytes for the codepoint.</short>
</element>
<element name="UTF8CodepointSize.p">
<short>UTF-8-encoded value to examine in the function.</short>
</element>

<element name="UTF8CodepointSizeFast">
<short>
Fast version of UTF8CodepointSize.
</short>
<descr>
<p>
Fast version of <var>UTF8CodepointSize</var>. Assumes the UTF-8 codepoint is 
valid. The return value is for a single codepoint.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8CodepointSizeFast.Result">
<short>Number of bytes for the codepoint.</short>
</element>
<element name="UTF8CodepointSizeFast.p">
<short>Encoded values to examine in the function.</short>
</element>

<element name="UTF8CharacterLength">
<short>
Returns the number of bytes needed for the UTF-8 codepoint starting at p.
</short>
<descr>
<remark>
Deprecated. Use UTF8CodepointSize instead.
</remark>
<p>
It returns 0 if p is nil. It returns 1 if p is a 1-byte UTF-8 codepoint or p 
is an invalid UTF-8 sequence. Otherwise it returns a number 2..4. It does not 
check for malicious codepoints like #$c0#$80, nor for undefined codepoints 
like #$f3#$a0#$87#$b9. Use UTF8CharacterLength to step through a string with 
a simple loop:
</p>
<code>
while p^ &lt;&gt; #0 do
begin
  inc(p, UTF8CharacterLength(p));
end;
</code>
<p>
Even if p contains invalid UTF-8 codepoints it will run through the string 
without overflow.
</p>
</descr>
<seealso>
<link id="UTF8CharacterStrictLength">UTF8CharacterStrictLength</link>
</seealso>
</element>
<element name="UTF8CharacterLength.Result">
<short>Number of bytes required for the UTF-8 codepoint, or 0 (zero).</short>
</element>
<element name="UTF8CharacterLength.p">
<short>Pointer to the value examined in the routine.</short>
</element>

<element name="UTF8Length">
<short>
Gets the length of a UTF-8-encoded string in codepoints.
</short>
<descr>
<p>
<var>UTF8Length</var> is a function used to get the character length for the 
specified UTF-8-encoded string. The return value contains the number of 
UTF-8-encoded characters (or codepoints) found in the byte values for the 
string.
</p>
<p>
An overloaded variant of the function is provided which uses the 
<var>PChar</var> type to specify the byte values in the string. Internally, 
the String variant casts its value a PChar type and calls the overloaded 
variant.
</p>
<p>
UTF8Length iterates over the bytes in the UTF-8-encoded string data, and 
calls UTF8CodepointSize to determine the number of bytes needed for each 
codepoint. Use UTF8LengthFast for a version of the routine optimized for 
speed.
</p>
</descr>
<seealso>
<link id="UTF8CodepointSize"/>
<link id="UTF8LengthFast"/>
</seealso>
</element>
<element name="UTF8Length.Result">
<short>Number of codepoints in the byte values for the string.</short>
</element>
<element name="UTF8Length.s">
<short>UTF-8-encoded string to examine in the function.</short>
</element>
<element name="UTF8Length.p">
<short>Pointer to the UTF-8-encoded string to examine in the function.</short>
</element>
<element name="UTF8Length.ByteCount">
<short>Number of byte values in the UTF-8-encoded string.</short>
</element>

<element name="UTF8LengthFast">
<short>
Fast version of UTF8Length.
</short>
<descr>
<p>
<var>UTF8LengthFast</var> is an overloaded <var>PtrInt</var> function used to 
get the length of a UTF-8-encoded string in codepoints. UTF8LengthFast is the 
fast version of <var>UTF8Length</var>. It does not call the UTF8CodepointSize 
function. The UTF-8-encoded string data is assumed to be valid. The native 
data size for the CPU is used to process blocks of UTF-8-encoded data. For a 
64-bit CPU, this means that 8 bytes are read and processed at once.
</p>
<p>
The overloaded variants allow the UTF-8-encoded data to be specified as 
either a String type, or a null-terminated PChar type. Internally, the 
String-based variant casts its data to a PChar type and calls the overloaded 
variant.
</p>
<p>
UTF8LengthFast is a Free Pascal implementation of the C routine provided by 
Colin Percival:
</p>
<p>
<url 
href="https://www.daemonology.net/blog/2008-06-05-faster-utf8-strlen.html">
Even faster UTF-8 character counting
</url>
</p>
</descr>
<seealso>
<link id="UTF8Length"/>
</seealso>
</element>
<element name="UTF8LengthFast.Result">
<short>Number of codepoints in the string.</short>
</element>
<element name="UTF8LengthFast.s">
<short>String with UTF-8-encoded values.</short>
</element>
<element name="UTF8LengthFast.p">
<short>Pointer to the String with UTF-8-encoded values.</short>
</element>
<element name="UTF8LengthFast.ByteCount">
<short>Number of byte values in the UTF-8-encoded string.</short>
</element>

<element name="UTF8CodepointCount">
<short>
Gets the number of valid UTF-8 codepoints in the specified value.
</short>
<descr>
<p>
<var>UTF8CodepointCount</var> is an overloaded <var>SizeInt</var> function used 
to determine the number of UTF-8 codepoints found in the specified value. It is 
similar to the UTF8Length routine, but excludes any invalid codepoints found in 
the input value from the count in the return value. The overloaded variants 
allow the input value to be specified using either the String or the PChar type.
</p>
<p>
UTF8CodepointCount iterates over the byte values in the s or p arguments, and 
increments the return value when a valid UTF-8 codepoint is found. 
UTF8CodepointLen (in system.pp) is called to the get the size for each of the 
UTF-8 codepoints. Valid codepoints include those represented using combining 
characters. The process is repeated until all of the bytes in the input value 
have been examined, or until a codepoint with a length of zero (0) is 
encountered.
</p>
<p>
The return value is zero (0) if the s or p arguments are empty, or when the 
ByteCount argument is zero (0).
</p>
<p>
For example:
</p>
<code>
// var
//   Utf8Str, InvalidUtf8Str: String;
//   Cnt, Len: Integer;

{A macron (decomposed)}
Utf8Str := 'A' + #$CC#$84;

{invalid single byte UTF-8}
InvalidUtf8Str := #$C0#$C1#$F5#$F6#$F7#$F8#$F9#$FA#$FB#$FC#$FD#$FE#$FF;

Cnt := UTF8CodePointCount(Utf8Str); // Cnt = 2
Len := UTF8Length(Utf8Str); // Len = 2

Cnt := UTF8CodePointCount(InvalidUtf8Str); // Cnt = 0
Len := UTF8Length(InvalidUtf8Str); // Len = 13

Cnt := UTF8CodePointCount(InvalidUtf8Str + Utf8Str); // Cnt = 2
Len := UTF8Length(InvalidUtf8Str + Utf8Str); // Len = 15
</code>
</descr>
<version>
Added in LazUtils version 4.0.
</version>
<seealso>
<link id="UTF8Length"/>
<link id="UTF8CodepointSize"/>
<link id="UTF8LengthFast"/>
<link id="UTF8CharacterLength"/>
<link id="#rtl.system.UTF8CodepointLen">UTF8CodepointLen</link>
</seealso>
</element>
<element name="UTF8CodepointCount.Result">
<short>
Integer value with the number of valid codepoints including combining 
characters.
</short>
</element>
<element name="UTF8CodepointCount.s">
<short>
String with the codepoints examined in the routine.
</short>
</element>
<element name="UTF8CodepointCount.p">
<short>
PChar type with the codepoints examined in the routine.
</short>
</element>
<element name="UTF8CodepointCount.ByteCount">
<short>
Number of bytes in the PChar value.
</short>
</element>

<element name="UTF8CodepointToUnicode">
<short>
Converts a UTF-8-encoded character to its unique Unicode U+XXXX character 
value.
</short>
<descr>
<p>
<var>UTF8CodepointToUnicode</var> is a <var>Cardinal</var> function used to 
convert a UTF-8-encoded character to its representation as a unique Unicode 
U+XXXX hexadecimal character value. For example: The letter 'A' (Decimal 65) 
is expressed in Unicode as U+0041.
</p>
<p>
<var>CodepointLen</var> is an output variable used to store the number of 
UTF-8-encoded bytes needed for the codepoint. It will normally contain a 
value in the range 1..4 (the number of possible bytes used in the UTF-8 
encoding scheme). It can contain 0 (zero) when p is an empty PChar value.
</p>
<p>
The return value for the function contains the hexadecimal Unicode character 
value as a Cardinal data type. It can contain 0 (zero) when the value in p is 
not a valid UTF-8-encoded character.
</p>
<p>
Use <var>UTF8FixBroken</var> to fix invalid UTF-8 encoding in the string.
</p>
<p>
Use UnicodeToUTF8 to convert a Unicode character value to its UTF-8-encoded 
value.
</p>
<remark>
UTF8CodepointToUnicode does not check whether the codepoint is actually 
defined in Unicode tables.
</remark>
</descr>
<seealso/>
</element>
<element name="UTF8CodepointToUnicode.Result">
<short>Unicode character value for the UTF-8 character.</short>
</element>
<element name="UTF8CodepointToUnicode.p">
<short>The UTF-8-encode string value.</short>
</element>
<element name="UTF8CodepointToUnicode.CodepointLen">
<short>Number of bytes needed for the codepoint.</short>
</element>

<element name="UTF8CharacterToUnicode">
<short>
Returns the codepoint at p and the number of bytes to skip.
</short>
<descr>
<remark>
Deprecated. Use Use UTF8CodepointToUnicode instead.
</remark>
<p>
If p=nil then CharLen and result are 0 otherwise CharLen&gt;0. If there is an 
encoding error the Result is 0 and CharLen=1 to skip forward. It is safe to 
do:
</p>
<code>
var
  s: string;
  p:=1;
while p &lt;= length(s) do
begin
  UTF8CharacterToUnicode(@s[p], CharLen);
  inc(p, CharLen);
end;
</code>
<p>
For speed reasons, this function only checks for 1, 2, 3, or 4 byte encoding 
errors. It does not check whether the codepoint is defined in the Unicode 
table.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8CharacterToUnicode.Result"/>
<element name="UTF8CharacterToUnicode.p"/>
<element name="UTF8CharacterToUnicode.CharLen"/>

<element name="UnicodeToUTF8">
<short>
Encodes the given code point as an UTF-8 sequence of 1 to 4 bytes.
</short>
<descr>
<p>
<var>UnicodeToUTF8</var> is an <var>Integer</var> function used to convert 
the Unicode character value in CodePoint to the sequence of bytes needed for 
the UTF-8 encoding. UnicodeToUTF8 stores the UTF-8-encoded byte values for 
the Unicode character in the <var>Buf</var> parameter.
</p>
<p>
The return value contains the number of bytes required for the UTF-8-encoded 
value (in the range 1..4). If it contains 0 (zero), the Unicode codepoint was 
invalid and an <var>Exception</var> is raised.
</p>
<remark>
UnicodeToUTF8 does not process #0 byte values for the codepoint, as done for 
UTF-32.
</remark>
</descr>
<errors>
<p>
Raises an <var>Exception</var> when Utf8TryFindCodepointStartCodePoint is an 
invalid Unicode character value. Raised with the message 'UnicodeToUTF8: 
invalid Unicode: XXXXXXXX'.
</p>
</errors>
<seealso/>
</element>
<element name="UnicodeToUTF8.Result">
<short>Number of bytes needed for the UTF-8-encoded value.</short>
</element>
<element name="UnicodeToUTF8.Codepoint">
<short>Unicode character value to convert in the function.</short>
</element>
<element name="UnicodeToUTF8.Buf">
<short>Stores the UTF-8-encoded byte values for the codepoint.</short>
</element>

<element name="UnicodeToUTF8SkipErrors">
<short>
Stores a single Unicode codepoint as a UTF-8-encoded value in the buffer.
</short>
<descr>
<p>
<var>UnicodeToUTF8SkipErrors</var> is a simple and fast function used to 
write a single Unicode codepoint as a UTF-8-encoded value in Buf. It returns 
the number of bytes written. It does not append a terminating null (#0) 
character. It does not check if the codepoint actually exists in Unicode 
tables. It returns 0 if the codepoint can not be represented as a 1 to 4 byte 
UTF-8 sequence.
</p>
</descr>
<seealso/>
</element>
<element name="UnicodeToUTF8SkipErrors.Result">
<short>UTF-8-encoded value for the codepoint.</short>
</element>
<element name="UnicodeToUTF8SkipErrors.Codepoint">
<short>Codepoint (Unicode character) to convert in the function.</short>
</element>
<element name="UnicodeToUTF8SkipErrors.Buf">
<short>Buffer where the converted value is stored.</short>
</element>

<element name="UnicodeToUTF8Inline">
<short>
Encodes the given code point as an UTF-8 sequence of 1 to 4 bytes.
</short>
<descr>
<p>
<var>UnicodeToUTF8Inline</var> is an <var>Integer</var> function used to 
convert the Unicode character value in <var>CodePoint</var> to the sequence 
of bytes needed for the UTF-8 encoding. UnicodeToUTF8Inline stores the 
UTF-8-encoded byte values for the Unicode character in the <var>Buf</var> 
parameter.
</p>
<p>
The return value contains the number of bytes required for the UTF-8-encoded 
value (in the range 1..4).
</p>
<p>
Used in the implementation of <var>UnicodeToUTF8</var> and 
<var>UnicodeToUTF8SkipErrors</var>.
</p>
<remark>
UnicodeToUTF8Inline does not process #0 byte values for the codepoint, as 
done for UTF-32.
</remark>
</descr>
<seealso/>
</element>
<element name="UnicodeToUTF8Inline.Result">
<short>Number of bytes required for the UTF-8-encoded value.</short>
</element>
<element name="UnicodeToUTF8Inline.CodePoint">
<short>Unicode character value to convert.</short>
</element>
<element name="UnicodeToUTF8Inline.Buf">
<short>Destination where encoded byte values are stored.</short>
</element>

<element name="UTF8ToDoubleByteString">
<short>
Converts UTF-8 values to their DBCS equivalent.
</short>
<descr>
<p>
<var>UTF8ToDoubleByteString</var> is a <var>String</var> function used to 
convert UTF-8-encoded values to the representation used in Double Byte 
Character Sets (DBCS).
</p>
<p>
UTF8ToDoubleByteString calls <var>UTF8Length</var> to get the number of 
codepoints (or characters) in s, and calls <var>UTF8ToDoubleByte</var> to 
perform the conversion. Each codepoint is converted to Unicode by calling 
<var>UTF8CodepointToUnicode</var>.
</p>
<p>
The return value is a String type with the byte values from the conversion, 
or an empty string ('') when s does not contain a valid UTF-8-encoded string.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8ToDoubleByteString.Result">
<short>DBCS values for the specified codepoints.</short>
</element>
<element name="UTF8ToDoubleByteString.s">
<short>UTF-8-encoded values to convert in the function.</short>
</element>

<element name="UTF8ToDoubleByte">
<short>
Converts a UTF-8-encode string to its DBCS representation.
</short>
<descr>
<p>
<var>UTF8ToDoubleByte</var> is used to convert UTF-8-encoded values to the 
representation used in Double Byte Character Sets (DBCS). UTF8ToDoubleByte 
calls <var>UTF8CodepointToUnicode</var> to process each of the codepoints in 
<var>UTF8Str</var>.
</p>
<p>
The return value contains the byte values from the conversion.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8ToDoubleByte.Result">
<short>Number of double bytes converted in the function.</short>
</element>
<element name="UTF8ToDoubleByte.UTF8Str">
<short>UTF-8-encoded values to convert in the function.</short>
</element>
<element name="UTF8ToDoubleByte.Len">
<short>Length of the UTF-8-encoded input values.</short>
</element>
<element name="UTF8ToDoubleByte.DBStr">
<short>Storage for the Double Byte values.</short>
</element>

<element name="UTF8FindNearestCharStart">
<short>
Finds the start of the UTF-8 character at the specified position.
</short>
<descr>
<p>
Find the start of the UTF-8 character which contains <var>BytePos</var>. If 
BytePos is not part of a valid UTF-8 Codepoint the function returns BytePos. 
BytePos values starts at position 0.
</p>
<p>
Len is the length in bytes.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8FindNearestCharStart.Result">
<short>Position where the next codepoint begins.</short>
</element>
<element name="UTF8FindNearestCharStart.UTF8Str">
<short>Values to examine in the function.</short>
</element>
<element name="UTF8FindNearestCharStart.Len">
<short>Length of the input values.</short>
</element>
<element name="UTF8FindNearestCharStart.BytePos">
<short>Offset into UTF8Str for the initial byte value.</short>
</element>

<element name="Utf8TryFindCodepointStart">
<short>
Tries to find the start of a valid UTF-8 codepoint in a string.
</short>
<descr>
<p>
<var>Utf8TryFindCodepointStart</var> is a <var>Boolean</var> function which 
tries to find the start of a valid UTF-8 codepoint at the specified position 
in <var>AString</var>.
</p>
<p>
The return value contains <b>True</b> if the bytes at the specified position 
are a valid UTF-8 codepoint (1 - 4 bytes). When the return value is 
<b>True</b>, the value in CurPos is updated to contain the position in 
AString where the UTF-8 codepoint begins. Otherwise, the value in CurPos is 
unchanged. Please note, when CurPos points beyond the end of AString you will 
get a crash!
</p>
<remark>
UTF8CodepointStrictSize will <b>NOT</b> "look" beyond the terminating #0 in a 
PChar, so this is safe with AnsiString values.
</remark>
</descr>
<seealso/>
</element>
<element name="Utf8TryFindCodepointStart.Result">
<short>
True when the bytes at the specified position are a valid UTF-8 codepoint.
</short>
</element>
<element name="Utf8TryFindCodepointStart.AString">
<short>Pointer to the string to examine in the function.</short>
</element>
<element name="Utf8TryFindCodepointStart.CurPos">
<short>
Pointer to the first position in the string examined in the function.
</short>
</element>
<element name="Utf8TryFindCodepointStart.CodepointLen">
<short>Number of bytes in the codepoint, or 0 when invalid.</short>
</element>
<element name="Utf8TryFindCodepointStart.Index">
<short>Initial position in the string examined in the function.</short>
</element>
<element name="Utf8TryFindCodepointStart.CharLen">
<short>Number of bytes required for the UTF-8 codepoint.</short>
</element>

<element name="UTF8CodepointStart">
<short>
Finds the n-th UTF-8 codepoint.
</short>
<descr>
<p>
Finds the n-th UTF-8 codepoint, ignoring BIDI.
</p>
<p>
Len is the length in bytes for the values in UTF8Str. CodepointIndex is the 
position of the desired codepoint (starting at 0), in characters.
</p>
<p>
The return value contains the byte values for the codepoint, or Nil when a 
valid codepoint was not found.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8CodepointStart.Result">
<short>Byte values for the codepoint, or Nil.</short>
</element>
<element name="UTF8CodepointStart.UTF8Str">
<short>Values to examine in the function.</short>
</element>
<element name="UTF8CodepointStart.Len">
<short>Length in bytes for the input values.</short>
</element>
<element name="UTF8CodepointStart.CodepointIndex">
<short>Character position for the desired codepoint (zero-based).</short>
</element>

<element name="UTF8CharStart">
<short>
Deprecated. Use UTF8CodepointStart instead.
</short>
<descr>
<remark>
Deprecated. Use UTF8CodepointStart instead.
</remark>
</descr>
<seealso/>
</element>
<element name="UTF8CharStart.Result"/>
<element name="UTF8CharStart.UTF8Str"/>
<element name="UTF8CharStart.Len"/>
<element name="UTF8CharStart.CharIndex"/>

<element name="UTF8CodepointToByteIndex">
<short>
Finds the byte index of the n-th UTF-8 codepoint.
</short>
<descr>
<p>
<var>UTF8CodepointToByteIndex</var> is a <var>PtrInt</var> function used to 
find the byte index in UTF8Str where the n-th UTF-8 codepoint is located. It 
calls UTF8CodepointStart to get a pointer to the requested codepoint position.
</p>
<p>
The return value contains the difference between the pointer offsets in each 
of the PChar values. The return value is -1 when a codepoint is not found at 
the specified position.
</p>
<p>
UTF8CodepointToByteIndex ignores BIDI mode.
</p>
</descr>
<seealso>
<link id="UTF8CodepointStart"/>
<link id="UTF8CharToByteIndex"/>
</seealso>
</element>
<element name="UTF8CodepointToByteIndex.Result">
<short>
Byte position where the requested UTF-8 codepoint is located, or -1 when a codepoint is not available for the index value.
</short>
</element>
<element name="UTF8CodepointToByteIndex.UTF8Str">
<short>
PChar with the multi-byte UTF-8-encoded values examined in the routine.
</short>
</element>
<element name="UTF8CodepointToByteIndex.Len">
<short>
Length of the PChar value in UTF8Str in bytes.
</short>
</element>
<element name="UTF8CodepointToByteIndex.CodepointIndex">
<short>
Position of the codepoint requested in the routine. This is 1-based, like a character index in String.
</short>
</element>

<element name="UTF8CharToByteIndex">
<short>
Deprecated. Use UTF8CodepointToByteIndex instead.
</short>
<descr>
<remark>
Deprecated. Use UTF8CodepointToByteIndex instead.
</remark>
</descr>
<seealso/>
</element>
<element name="UTF8CharToByteIndex.Result"/>
<element name="UTF8CharToByteIndex.UTF8Str"/>
<element name="UTF8CharToByteIndex.Len"/>
<element name="UTF8CharToByteIndex.CharIndex"/>

<element name="UTF8FixBroken">
<short>
Replaces all invalid UTF-8 characters in a string with the specified character.
</short>
<descr>
<p>
<var>UTF8FixBroken</var> is an overloaded routine used to replace all invalid 
UTF-8 characters in the specified value with a replacement character. The 
overloaded variants allow the UTF-8-encoded content to be specified using 
either a PChar or a String type.
</p>
<p>
<var>ReplaceChar</var> contains the character used to replace any invalid UTF-8 
characters found in the input value. The default value for ReplaceChar is the 
Space character (Hex $20 Decimal 32).
</p>
<p>
The PChar variant examines the specified byte values to determine when an 
invalid UTF-8 codepoint is found. This includes 1, 2, or 3 byte values, those 
that fall outside of the ranges allowed in UTF-8, and common byte sequences 
used to inject XSS vulnerabilities. UTF8FixBroken stops processing at the first 
occurrence of the byte value #0 (Decimal 0). UTF-8 byte sequences updated in 
the routine are stored in the original PChar argument.
</p>
<p>
The String variant converts the input argument to a PChar type and calls 
FindInvalidUTF8Codepoint to locate invalid UTF-8 byte sequences. If invalid 
bytes are found, UniqueString is called to get a new reference-counted String 
for the return value generated by calling the overloaded PChar variant.
</p>
</descr>
<version>
Modified in LazUtils version 4.0 to include the ReplaceChar argument.
</version>
<seealso>
<link id="FindInvalidUTF8Codepoint"/>
<link id="#rtl.system.UniqueString">UniqueString</link>
</seealso>
</element>
<element name="UTF8FixBroken.P">
<short>
PChar with the UTF-8-encoded values examined in the routine.
</short>
</element>
<element name="UTF8FixBroken.S">
<short>
String with the UTF-8-encoded values examined in the routine.
</short>
</element>
<element name="UTF8FixBroken.ReplaceChar">
<short>
Character used to replace invalid codepoints in the input argument. The default 
value for the argument is the Space character (decimal 32 hex $20).
</short>
</element>

<element name="UTF8CodepointStrictSize">
<short>Gets the number of bytes needed for the UTF-8 codepoint.</short>
<descr>
<p>
Gets the number of bytes needed for the UTF-8 codepoint in <var>P</var>. The 
return value contains the number of bytes need for the codepoint (in the 
range 1..4), or 0 (zero) when P is not assigned or the codepoint is invalid.
</p>
<remark>
UTF8CodepointStrictSize stops examining the byte values in P when #0 (Decimal 
0) is encountered.
</remark>
</descr>
<seealso/>
</element>
<element name="UTF8CodepointStrictSize.Result">
<short>Number of bytes needed for the codepoint.</short>
</element>
<element name="UTF8CodepointStrictSize.P">
<short>UTF-8-encoded values to examine.</short>
</element>

<element name="UTF8CharacterStrictLength">
<short>
Returns the length in bytes (1..4) for a valid UTF-8 character. Otherwise 0.
</short>
<descr>
<remark>
Deprecated. Use UTF8CodepointStrictSize instead.
</remark>
</descr>
<seealso/>
</element>
<element name="UTF8CharacterStrictLength.Result"/>
<element name="UTF8CharacterStrictLength.P"/>

<element name="UTF8CStringToUTF8String">
<short>
Copies from a C-style string with UTF-8 encoding to UTF-8 string.
</short>
<descr>
<p>
<var>UTF8CStringToUTF8String</var> is a <var>String</var> function used to 
copy the specified number of characters (codepoints) from a C-style string 
with UTF-8 encoding. The return value is a UTF-encoded string with C-style 
specials characters converted to their common equivalents. The following 
C-style quoted characters are handled in the function:
</p>
<dl>
<dt>\t</dt>
<dd>Converted to a Tab character (Decimal 9)</dd>
<dt>\"</dt>
<dd>Converted to a Double Quote character (Decimal 34)</dd>
<dt>\\</dt>
<dd>Converted to a Reverse Solidus character (Decimal 92)</dd>
<dt>\n</dt>
<dd>Converted to the LineEnding ending for the OS or platform</dd>
</dl>
<p>
The return value is a string which contains the number of codepoints in 
<var>SourceStart</var> specified in <var>SourceLen</var>, or an empty string 
('') when SourceLen is 0 (zero).
</p>
</descr>
<seealso/>
</element>
<element name="UTF8CStringToUTF8String.Result">
<short>UTF-8-encode string with C-style quoting removed.</short>
</element>
<element name="UTF8CStringToUTF8String.SourceStart">
<short>PChar with the UTF-8-encoded C-style string.</short>
</element>
<element name="UTF8CStringToUTF8String.SourceLen">
<short>Number of codepoints to copy in the method.</short>
</element>

<element name="UTF8Pos">
<short>
Returns the character index where the search text starts in the string.
</short>
<descr>
<p>
Returns the character index where <var>SearchForText</var> starts in 
<var>SearchInText</var>. An optional <var>StartPos</var> can be given to 
start searching at a given character index. StartPos starts at 1.
</p>
<p>
Returns 0 if the search text is not found in the string.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8Pos.Result">
<short>Character position where the search text was located.</short>
</element>
<element name="UTF8Pos.SearchForText">
<short>Value to locate in the string.</short>
</element>
<element name="UTF8Pos.SearchInText">
<short>String to search for the specified value.</short>
</element>

<element name="UTF8PosP">
<short>
Returns a pointer to the position where SearchForText starts in SearchInText, 
or Nil when not found.
</short>
<descr/>
<seealso/>
</element>
<element name="UTF8PosP.Result">
<short>
Pointer to the character value where SearchForText was located in 
SearchInText, or Nil when not found.
</short>
</element>
<element name="UTF8PosP.SearchForText">
<short>
Pointer to the character(s) to locate in SearchInText.
</short>
</element>
<element name="UTF8PosP.SearchForTextLen">
<short>
Number of bytes in SearchForText.
</short>
</element>
<element name="UTF8PosP.SearchInText">
<short>
Pointer to the character values examined in the routine.
</short>
</element>
<element name="UTF8PosP.SearchInTextLen">
<short>
Number of bytes in SearchInText.
</short>
</element>

<element name="UTF8Copy">
<short>
Copies the specified number of codepoints from the UTF-8-encoded string.
</short>
<descr>
<p>
<var>UTF8Copy</var> is a <var>String</var> function used copy to 
UTF-8-encoded values from <var>s</var> starting at the position in 
<var>StartCharIndex</var>. <var>CharCount</var> specifies the number of 
multi-byte characters (or codepoints) to include in the return value. The 
return value is an empty string ('') when s is not a valid UTF-8-encoded 
string.
</p>
<p>
UTF8Copy behaves like a substring function.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8Copy.Result">
<short>String with codepoints copied from the specified source.</short>
</element>
<element name="UTF8Copy.s">
<short>String with values to copy in the function.</short>
</element>
<element name="UTF8Copy.StartCharIndex">
<short>Initial character position for the copy operation.</short>
</element>
<element name="UTF8Copy.CharCount">
<short>Number of characters (codepoints) to copy in the function.</short>
</element>

<element name="UTF8Delete">
<short>
Deletes characters (or codepoints) in a UTF-8-encoded string.
</short>
<descr>
<p>
<var>UTF8Delete</var> is an overloaded procedure used to delete characters 
(or codepoints) in a UTF-8-encoded string starting at a given position.
</p>
<p>
<var>StartCharIndex</var> contains the character position in s where values 
will be removed. <var>StartCharIndex</var> refers to codepoints and not 
individual byte or character values. A single character can be expressed as 
1-4 byte values in UTF-8 encoding. <var>CharCount</var> indicates the number 
of codepoints to remove in the function.
</p>
<p>
The value in <var>s</var> is updated directly in the function.
</p>
<p>
An overloaded variant of the procedure is provided for platforms where the 
Win1252 code page is used. On these platforms, raw byte values values in s 
are converted to the UTF-8 code page prior to performing the delete operation.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8Delete.s">
<short>String with values to delete in the procedure.</short>
</element>
<element name="UTF8Delete.StartCharIndex">
<short>Initial character position where values will be deleted.</short>
</element>
<element name="UTF8Delete.CharCount">
<short>
Number of characters (or codepoints) to remove in the procedure.
</short>
</element>

<element name="UTF8Insert">
<short>
Inserts the specified UTF-8 values into a string at the specified character 
position.
</short>
<descr>
<p>
<var>UTF8Insert</var> inserts the specified values into a string at the 
specified character position. UTF8Insert is an overloaded procedure. The 
variants allow the string arguments to be specified as either String or 
UTF8String types.
</p>
<p>
<var>source</var> is the UTF-8-encoded values inserted in the routine.
</p>
<p>
<var>s</var> is the string where the values from source are inserted at the 
specified character position.
</p>
<p>
The value in <var>StartCharIndex</var> starts at <b>1</b>, and represents the 
n-th codepoint (or character) in the destination string (s) where the values 
are inserted.
</p>
<p>
UTF8Insert calls UTF8CodepointStart to determine the position in s where the 
codepoint represented by StartCharIndex is located. No actions are performed in 
the routine if a valid codepoint is not found at the position specified in 
StartCharIndex. The RTL Insert routine is called to insert the UTF-8-encoded 
values from source into s.
</p>
</descr>
<seealso>
<link id="UTF8CodepointStart"/>
<link id="UTF8Delete"/>
<link id="UTF8Pos"/>
</seealso>
</element>
<element name="UTF8Insert.source">
<short>
String with the values inserted in the routine.
</short>
</element>
<element name="UTF8Insert.s">
<short>
String where the values from source are inserted.
</short>
</element>
<element name="UTF8Insert.StartCharIndex">
<short>
Starting character position (1-based) where the inserted values from source are 
stored in s.
</short>
</element>

<element name="UTF8StringReplace">
<short>
Replaces one or more values in a UTF-8-encoded string which match a given 
pattern.
</short>
<descr>
<p>
<var>UTF8StringReplace</var> is an overloaded <var>String</var> function 
which replaces values in a string matching a given pattern.
</p>
<p>
<var>S</var> is the UTF-8-encoded string to update in the function. 
<var>OldPattern</var> is a pattern with the values to be replaced in S. 
<var>NewPattern</var> is the replacement value for OldPattern in S. 
</p>
<p>
<var>Flags</var> contains <var>TReplaceFlags</var> values and control the 
options enabled in the operation. <var>rfIgnoreCase</var> causes 
case-insensitive comparisons to be used for values in S and OldPattern; both 
values are converted to lowercase copies for the purpose. 
<var>rfReplaceAll</var> causes all occurrences of OldPattern to be replaced 
with NewPattern in S. If the flag is omitted, only the first occurrence of 
OldPattern in S is replaced in the routine.
</p>
<p>
<var>ALanguage</var> is the 2-digit ISO 639-1 Language Code, like 'es' or 
'de', used when converting values to lowercase for case-insensitive search. 
The default value is an empty string ('') and offers maximum speed when the 
language is not significant.
</p>
<p>
<var>Count</var> is an output variable used to return the actual number of 
replacements performed in the function.
</p>
<p>
UTF8StringReplace provides support for UTF-8 codepoints which have different 
sizes (byte counts) for the uppercase and lowercase variants of patterns. It 
ensures that the return value is resized (when needed) to account for 
individual codepoint sizes altered in S due to case conversion.
</p>
<p>
The return value is a UTF-8-encoded string with the updated values from S 
following replacements.
</p>
<p>
No actions are performed in the routine if OldPattern is an empty string ('').
</p>
</descr>
<seealso/>
</element>
<element name="UTF8StringReplace.Result">
<short>UTF-8-encoded values after the replace operation.</short>
</element>
<element name="UTF8StringReplace.S">
<short>Original UTF-8-encoded values to examine.</short>
</element>
<element name="UTF8StringReplace.OldPattern">
<short>Pattern to replace in the function.</short>
</element>
<element name="UTF8StringReplace.NewPattern">
<short>Replacement values for the operation.</short>
</element>
<element name="UTF8StringReplace.Flags">
<short>Replace options enabled in the function.</short>
</element>
<element name="UTF8StringReplace.ALanguage">
<short>Language Code used for locale-specific lowercase conversions.</short>
</element>
<element name="UTF8StringReplace.Count">
<short>Number of times the search pattern was replaced in the string.</short>
</element>

<element name="UTF8LowerCase">
<short>
Converts the specified string to lowercase using Unicode case mapping rules.
</short>
<descr>
<p>
<var>UTF8LowerCase</var> is a <var>String</var> function used to convert the 
UTF-8-encoded value in AInStr to its lowercase equivalent. UTF8LowerCase uses 
Unicode Data defined on on the Unicode.org website at 
ftp://ftp.unicode.org/Public/UNIDATA/UnicodeData.txt. FTP lik removed.
The conversion is performed using the Case Mapping Rules defined
in https://www.ksu.ru/eng/departments/ktk/test/perl/lib/unicode/UCDFF301.html#CaseMappings [dead link renoved].
</p>
<p>
ALanguage indicates the language code to use for the conversion. ALanguage 
should be specified using ISO 639-1 format, which uses 2 characters to 
represent each language. If the language has no code in ISO 639-1, then the 
3-chars code from ISO 639-2 should be used. For example: "tr"for the Turkish 
language locale. Special handling is provided in the function for Turkish 
('tr') and Azeri ('az') language codes. ALanguage can be set to an empty 
string ('') for maximum speed in the conversion.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8LowerCase.Result">
<short>Lowercase values for the specified string.</short>
</element>
<element name="UTF8LowerCase.AInStr">
<short>Values to convert in the function.</short>
</element>
<element name="UTF8LowerCase.ALanguage">
<short>Language code for the operation.</short>
</element>

<element name="UTF8LowerString">
<short>
Converts the specified string to lowercase using Unicode case mapping rules.
</short>
<descr>
<p>
Calls UTF8LowerCase to get the return value for the function.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8LowerString.Result">
<short>Lowercase values for the specified string.</short>
</element>
<element name="UTF8LowerString.S">
<short>String value to convert in the function.</short>
</element>

<element name="UTF8UpperCase">
<short>
Converts the specified string to uppercase using Unicode case mapping rules.
</short>
<descr>
<p>
<var>UTF8UpperCase</var> is a <var>String</var> function used to convert the 
UTF-8-encoded value in AInStr to its uppercase equivalent. UTF8UpperCase uses 
Unicode Data as defined at the Unicode.org website. 
[ftp://ftp.unicode.org/Public/UNIDATA/UnicodeData.txt] FTP link removed.
The conversion is performed using the Case Mapping Rules defined at 
https://www.ksu.ru/eng/departments/ktk/test/perl/lib/unicode/UCDFF301.html#CaseMappings. Dead link removed.
</p>
<p>
ALanguage indicates the language code to use for the conversion. ALanguage 
should be specified using ISO 639-1 format, which uses 2 characters to 
represent each language. If the language has no code in ISO 639-1, then the 
3-chars code from ISO 639-2 should be used. For example: "tr"for the Turkish 
language locale. Special handling is provided in the function for Turkish 
('tr') and Azeri ('az') language codes.ALanguage can be set to an empty 
string ('') for maximum speed in the conversion.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8UpperCase.Result">
<short>Uppercase values for the specified string.</short>
</element>
<element name="UTF8UpperCase.AInStr">
<short>Values to convert in the function.</short>
</element>
<element name="UTF8UpperCase.ALanguage">
<short>Language code for the operation.</short>
</element>

<element name="UTF8UpperString">
<short>
Inline variant of UTF8UpperCase.
</short>
<descr>
Inline variant of UTF8UpperCase.
</descr>
<seealso/>
</element>
<element name="UTF8UpperString.Result">
<short>Uppercase values for the string.</short>
</element>
<element name="UTF8UpperString.s">
<short>Values to convert in the function.</short>
</element>

<element name="UTF8UpperCaseFast">
<short>
Gets the uppercase value for the specified text. Optimized to improve speed for ASCII content in the argument.
</short>
<descr>
<p>
<var>UTF8UpperCaseFast</var> examines the ordinal values for the characters in 
<var>AText</var> to determine how the return value is derived. It is optimized 
for ASCII content (byte values in the range 1..128). It converts individual 
characters in the range ['a'..'z'] by subtracting 32 from their ordinal values.
</p>
<p>
If a non-ASCII byte value is found in AText, the return value is derived by 
calling UTF8UpperCase with the value in AText as an argument.
</p>
</descr>
<version>
Added in LazUtils version 4.0.
</version>
<seealso>
<link id="UTF8UpperCase"/>
<link id="UTF8LowerCaseFast"/>
</seealso>
</element>
<element name="UTF8UpperCaseFast.Result">
<short>
Uppercase value for the specified text.
</short>
</element>
<element name="UTF8UpperCaseFast.AText">
<short>
String with the content examined and converted to its uppercase representation.
</short>
</element>

<element name="UTF8LowerCaseFast">
<short>
Gets the lowercase value for the specified text. Optimized to improve speed for ASCII content in the argument.
</short>
<descr>
<p>
<var>UTF8LowerCaseFast</var> examines the ordinal values for the characters in 
<var>AText</var> to determine how the return value is derived. It is optimized 
for ASCII content (byte values in the range 1..128). It converts individual 
characters in the range ['A'..'Z'] by adding 32 to their ordinal values.
</p>
<p>
If a non-ASCII byte value is found in AText, the return value is derived by 
calling UTF8LowerCase with the value in AText as an argument.
</p>
</descr><version>
Added in LazUtils version 4.0.
</version>
<seealso>
<link id="UTF8LowerCase"/>
<link id="UTF8UpperCase"/>
<link id="UTF8UpperCaseFast"/>
</seealso>
</element>
<element name="UTF8LowerCaseFast.Result">
<short>
Lowercase value for the specified text.
</short>
</element>
<element name="UTF8LowerCaseFast.AText">
<short>
String with the content examined and converted to its lowercase representation.
</short>
</element>

<element name="UTF8SwapCase">
<short>
Provides a simplistic implementation of UTF8UpperCase and UTF8LowerCase.
</short>
<descr>
<p>
<var>UTF8SwapCase</var> provides a "naive" implementation that uses 
<var>UTF8UpperCase</var> and <var>UTF8LowerCase</var>. Performance is 
acceptable for short and reasonably long strings, but it could benefit from 
better performance and lower memory consumption.
</p>
<p>
AInStr contains a UTF-8-encoded string with values to convert it the method. 
Each character in AInStr will have its case "toggled" in the function. In 
other words, an uppercase character is converted to lowercase, and vice versa.
</p>
<p>
ALanguage indicates the language code to use for the conversion. ALanguage 
should be specified using ISO 639-1 format, which uses 2 characters to 
represent each language. If the language has no code in ISO 639-1, then the 
3-character code from ISO 639-2 should be used. For example: "tr"for the 
Turkish language locale. Special handling is provided in the function for 
Turkish ('tr') and Azeri ('az') language codes. ALanguage can be set to an 
empty string ('') for maximum speed in the conversion.
</p>
<p>
No actions are performed in the method when the number of bytes for the 
converted value differs from the number of bytes in the original value. In 
this case, the return value contains the unmodified string in AInStr. The 
return value is an empty string ('') when AInStr is an empty string ('').
</p>
</descr>
<seealso/>
</element>
<element name="UTF8SwapCase.Result">
<short>String with the converted case values.</short>
</element>
<element name="UTF8SwapCase.AInStr">
<short>Original values for the conversion.</short>
</element>
<element name="UTF8SwapCase.ALanguage">
<short>Language code for the locale used in the conversion.</short>
</element>

<element name="UTF8ProperCase">
<short>
Capitalizes the first letter of each word in the string.
</short>
<descr>
<p>
<var>UTF8ProperCase</var> is a <var>String</var> function used to capitalize 
the first letter of each word in the specified string. WordDelims is set 
which contains the system characters used as word boundaries in the string.
</p>
<p>
UTF8ProperCase converts all of the values in AInStr to their lowercase 
equivalents, before converting letters following a word delimiter to 
uppercase.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8ProperCase.Result">
<short>Converting values for the string.</short>
</element>
<element name="UTF8ProperCase.AInStr">
<short>Values to convert in the function.</short>
</element>
<element name="UTF8ProperCase.WordDelims">
<short>Characters used as word delimiters.</short>
</element>

<element name="FindInvalidUTF8Codepoint">
<short>
Finds the position where an invalid UTF-8 codepoint is found in the string.
</short>
<descr>
<p>
<var>FindInvalidUTF8Codepoint</var> is a <var>PtrInt</var> function used to 
find the position where an invalid UTF-8 codepoint is located in the 
specified value. The return value contains <b>-1</b> when none of the values 
in p are invalid, or the zero-based offset into p where the invalid encoding 
was located.
</p>
<p>
<var>StopOnNonUTF8</var> indicates if the function should exit when an 
encoded value is found that is not defined for the UTF-8 encoding, or for 
single byte characters inserted in the middle of a UTF-8 encoding (used in 
XSS attacks).
</p>
</descr>
<seealso/>
</element>
<element name="FindInvalidUTF8Codepoint.Result">
<short>Offset into the string for the error.</short>
</element>
<element name="FindInvalidUTF8Codepoint.p">
<short>Values to examine in the function.</short>
</element>
<element name="FindInvalidUTF8Codepoint.Count">
<short>Length of the input values.</short>
</element>
<element name="FindInvalidUTF8Codepoint.StopOnNonUTF8">
<short>True to exit on an malformed codepoint.</short>
</element>

<element name="FindInvalidUTF8Character">
<short>
Returns -1 if OK, otherwise byte index of invalid UTF-8 codepoint.
</short>
<descr>
<remark>
Deprecated. Use FindInvalidUTF8Codepoint instead.
</remark>
<p>
It always stops on irregular codepoints. For example Codepoint 0 is normally 
encoded as #0, but it can also be encoded as #192#0. Because most software 
does not check this, it can be exploited and is a security risk. If 
StopOnNonUTF8 is <b>False</b> it will ignore undefined codes. For example 
#128. By default it stops on such codes.
</p>
</descr>
<seealso/>
</element>
<element name="FindInvalidUTF8Character.Result"/>
<element name="FindInvalidUTF8Character.p"/>
<element name="FindInvalidUTF8Character.Count"/>
<element name="FindInvalidUTF8Character.StopOnNonASCII"/>

<element name="UTF8StringOfChar">
<short>
Creates a string filled with the specified number of given codepoints.
</short>
<descr>
<p>
<var>UTF8StringOfChar</var> is a function used to create a UTF-8-encoded 
string filled with the specified number of occurrences of the given 
codepoint. <var>AUtf8Char</var> is the UTF-8 codepoint to reproduce in the 
function. No actions are performed if AUtf8Char is an empty string (''), or 
contains a malformed UTF-8 codepoint.
</p>
<p>
The return value is filled with byte values for the codepoint (1 to 4 bytes 
as per the UTF-8 encoding). The process is repeated until the number of 
codepoints in <var>N</var> have been stored in the return value.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8StringOfChar.Result`">
<short>
String with the specified number of occurrence of the codepoint.
</short>
</element>
<element name="UTF8StringOfChar.AUtf8Char">
<short>Codepoint to reproduce in the function.</short>
</element>
<element name="UTF8StringOfChar.N">
<short>Number of occurrences to include in the return value.</short>
</element>

<element name="UTF8AddChar">
<short>
Adds the specified number of UTF-8 codepoints to a string.
</short>
<descr>
<p>
<var>UTF8AddChar</var> is a <var>String</var> function used to add the 
specified number of UTF-8 codepoints to a string. <var>AUtf8Char</var> is the 
UTF-8-encoded codepoint to add to string value in <var>S</var>. <var>N</var> 
indicates the number of times the codepoint should be added to the string.
</p>
<p>
No actions are performed in the function when AUtf8Char is an empty string 
(''), or contains a malformed UTF-8 codepoint.
</p>
<remark>
Values added to the string in S are inserted at the beginning of the string 
(prepended).
</remark>
</descr>
<seealso/>
</element>
<element name="UTF8AddChar.Result">
<short>Updated value for the string.</short>
</element>
<element name="UTF8AddChar.AUtf8Char">
<short>Codepoint to prepend to the string value.</short>
</element>
<element name="UTF8AddChar.S">
<short>Original values for the string.</short>
</element>
<element name="UTF8AddChar.N">
<short>Number of codepoints to prepend to the string.</short>
</element>

<element name="UTF8AddCharR">
<short>
Appends the specified number of UTF-8 codepoints to a string.
</short>
<descr>
<p>
<var>UTF8AddChar</var> is a <var>String</var> function used to append the 
specified number of UTF-8 codepoints to a string. <var>AUtf8Char</var> is the 
UTF-8-encoded codepoint to add to string value in <var>S</var>. <var>N</var> 
indicates the number of times the codepoint should be appended to the string.
</p>
<p>
No actions are performed in the function when AUtf8Char is an empty string 
(''), or contains a malformed UTF-8 codepoint.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8AddCharR.Result">
<short>Updated value for the string.</short>
</element>
<element name="UTF8AddCharR.AUtf8Char">
<short>Codepoint to append to the string value.</short>
</element>
<element name="UTF8AddCharR.S">
<short>Original values for the string.</short>
</element>
<element name="UTF8AddCharR.N">
<short>Number of codepoints to append to the string.</short>
</element>

<element name="UTF8PadLeft">
<short>
Adds the specified number of values in AUtf8Char to the beginning of a string.
</short>
<descr>
<p>
<var>UTF8PadLeft</var> is used to add the specified number of values in 
<var>AUtf8Char</var> to the beginning of a string. The default value for 
AUtf8Char is #32 ([SPACE]), but can contain any valid UTF-8 codepoint (1 to 4 
bytes). UTF8PadLeft calls <var>Utf8AddChar</var> to create the return value 
for the function.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8PadLeft.Result">
<short>
Updated value for the string with characters inserted at the beginning.
</short>
</element>
<element name="UTF8PadLeft.S">
<short>Original string value to modify in the function.</short>
</element>
<element name="UTF8PadLeft.N">
<short>Number of codepoints desired in the modified string.</short>
</element>
<element name="UTF8PadLeft.AUtf8Char">
<short>UTF-8 codepoint to insert into the string.</short>
</element>

<element name="UTF8PadRight">
<short>
Appends the specified number of UTF-8 codepoints to the end of a string.
</short>
<descr>
<p>
<var>UTF8PadRight</var> is used to append the specified number of UTF-8 
codepoints to the end of a string. The default value for <var>AUtf8Char</var> 
is #32 ([SPACE]), but can contain any valid UTF-8 codepoint (1 to 4 bytes). 
UTF8PadRight calls <var>Utf8AddCharR</var> to create the return value for the 
function.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8PadRight.Result">
<short>Updated value for the string.</short>
</element>
<element name="UTF8PadRight.S">
<short>Original string to modify in the function.</short>
</element>
<element name="UTF8PadRight.N">
<short>Number of codepoints desired in the modified string.</short>
</element>
<element name="UTF8PadRight.AUtf8Char">
<short>Codepoint to append to the string value.</short>
</element>

<element name="UTF8PadCenter">
<short>
Center aligns a string to the specified length.
</short>
<descr>
<p>
<var>UTF8PadCenter</var> is used to center align a string to the specified 
length (number of codepoints). <var>N</var> indicates the length of the 
modified string after padding on the left and right with the UTF-8 codepoint 
in <var>AUtf8Char</var>. The default value for AUtf8Char is #32 ([SPACE]), 
but can contains any valid UTF-8 codepoint (1 to 4 bytes).
</p>
</descr>
<seealso/>
</element>
<element name="UTF8PadCenter.Result">
<short>Modified value for the string after center alignment.</short>
</element>
<element name="UTF8PadCenter.S">
<short>Original string value.</short>
</element>
<element name="UTF8PadCenter.N">
<short>Desired length for the string (in codepoints).</short>
</element>
<element name="UTF8PadCenter.AUtf8Char">
<short>UTF-8 codepoint used as a padding character.</short>
</element>

<element name="UTF8LeftStr">
<short>
Gets the specified number of characters (codepoints) at the start of the 
string.
</short>
<descr>
<p>
<var>UTF8LeftStr</var> is used to get the specified number of characters 
(codepoints) at the beginning of the UTF-8-encoded string. UTF8LeftStr calls 
<var>Utf8Copy</var> to get the return value for the function.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8LeftStr.Result">
<short>Values from the specified string.</short>
</element>
<element name="UTF8LeftStr.AText">
<short>Original string to examine in the function.</short>
</element>
<element name="UTF8LeftStr.ACount">
<short>Number of characters (codepoints) to get from the string.</short>
</element>

<element name="UTF8RightStr">
<short>
Gets the specified number of characters (codepoints) at the end of the string.
</short>
<descr>
<p>
<var>UTF8RightStr</var> is used to get the specified number of characters 
(codepoints) at the end of the UTF-8-encoded string. UTF8RightStr calls 
<var>Utf8Copy</var> to get the return value for the function.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8RightStr.Result">
<short>Values from the string.</short>
</element>
<element name="UTF8RightStr.AText">
<short>Original string to examine in the function.</short>
</element>
<element name="UTF8RightStr.ACount">
<short>Number of characters (codepoints) to get from the string.</short>
</element>

<element name="UTF8QuotedStr">
<short>
Performs safe quoting for the specified UTF-8-encoded string value.
</short>
<descr>
<p>
<var>UTF8QuotedStr</var> is a <var>String</var> function used to double all 
occurrences of the byte sequence in the Quote argument. It works like the 
QuotedStr or AnsiQuotedStr routines from the RTL <file>sysutils</file> unit, 
but allows the Quote character to contain a valid multi-byte UTF-8 codepoint. 
Processing in the routine is halted when the #0 (Decimal 0) character is 
encountered.
</p>
<p>
Like its counterparts, UTF8QuotedStr encloses the return value with the 
character specified in the Quote argument.
</p>
</descr>
<seealso>
<link id="#rtl.sysutils.QuotedStr">QuotedStr</link>
<link id="#rtl.sysutils.AnsiQuotedStr">AnsiQuotedStr</link>
</seealso>
</element>
<element name="UTF8QuotedStr.Result">
<short>
Value in S after safe UTF-8 quoting has been applied.
</short>
</element>
<element name="UTF8QuotedStr.S">
<short>
String with the values examined and quoted in the routine.
</short>
</element>
<element name="UTF8QuotedStr.Quote">
<short>
Byte sequence with the quote character used in the routine.
</short>
</element>

<element name="UTF8StartsText">
<short>
Determines if a string starts with the specified value.
</short>
<descr>
<p>
<var>UTF8StartsText</var> determines if the value in <var>AText</var> begins 
with the value in <var>ASubText</var>. Both values can contain a valid 
UTF-8-encoded string. The return value is <b>False</b> when ASubText is an 
empty string (''), or ASubText contains more characters (codepoints) than the 
value in AText.
</p>
<p>
UTF8StartsText calls <var>Utf8Copy</var> and 
<var>UTF8CompareLatinTextFast</var> to perform a case-insensitive comparison 
between the values.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8StartsText.Result">
<short>True when the strings starts with the specified text.</short>
</element>
<element name="UTF8StartsText.ASubText">
<short>Value to locate at the start of the string.</short>
</element>
<element name="UTF8StartsText.AText">
<short>String to examine in the function.</short>
</element>

<element name="UTF8EndsText">
<short>
Determines if a string ends with the specified value.
</short>
<descr>
<p>
<var>UTF8EndsText</var> determines if the value in <var>AText</var> ends with 
the value in <var>ASubText</var>. Both values can contain a valid 
UTF-8-encoded string. The return value is <b>False</b> when ASubText is an 
empty string (''), or ASubText contains more characters (codepoints) than the 
value in AText.
</p>
<p>
UTF8StartsText calls <var>Utf8Copy</var> and 
<var>UTF8CompareLatinTextFast</var> to perform a case-insensitive comparison 
between the values.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8EndsText.Result">
<short>True when the strings ends with the specified text.</short>
</element>
<element name="UTF8EndsText.ASubText">
<short>Value to locate at the end of the string.</short>
</element>
<element name="UTF8EndsText.AText">
<short>String to examine in the function.</short>
</element>

<element name="UTF8ReverseString">
<short>
Reverses the order of codepoints in the specified string.
</short>
<descr>
<p>
<var>UTF8ReverseString</var> is used to create a string with the specified 
content in reverse order. p contains the UTF-8-encoded values for the 
original string.
</p>
<p>
ByteCount indicates the total number of bytes needed to represent the 
codepoints in <var>p</var>.
</p>
<p>
UTF8ReverseString calls <var>UTF8CodepointSize</var> and moves the needed 
number of byte values in p to the return value for the function.
</p>
</descr>
<seealso>
<link id="UTF8CodepointSize"/>
</seealso>
</element>
<element name="UTF8ReverseString.Result">
<short>String with the reversed text values.</short>
</element>
<element name="UTF8ReverseString.p">
<short>PChar type with values reversed in the routine.</short>
</element>
<element name="UTF8ReverseString.ByteCount">
<short>Number of bytes reversed in the routine.</short>
</element>
<element name="UTF8ReverseString.AText">
<short>String with the values reversed in the routine.</short>
</element>

<element name="UTF8RPos">
<short>
Gets the right-most position in the Source string for the value in Substr.
</short>
<descr></descr>
<seealso>
<link id="UTF8Length"/>
</seealso>
</element>
<element name="UTF8RPos.Result">
<short>Pointer to the position in Source.</short>
</element>
<element name="UTF8RPos.Substr">
<short>Value to locate in Source.</short>
</element>
<element name="UTF8RPos.Source">
<short>String with values examined in the routine.</short>
</element>

<element name="UTF8WrapText">
<short>
Creates a word-wrapped version of the specified string.
</short>
<descr>
<p>
<var>UTF8WrapText</var> is an overloaded <var>String</var> function used to 
wrap lines of text in <var>S</var> at the number of characters (codepoints) 
specified in <var>MaxCol</var>.
</p>
<p>
The overloaded variant allow additional parameters to be provided with the 
EOL character sequence and a set of characters where a line break can be 
inserted. Default characters are used in <var>BreakChars</var> for the 
variant without a BreakChars argument. They include: ' ' (Space), '-' (Dash), 
and #9 (Tab). <var>BreakStr</var> contains the end-of-line sequence used to 
represent a line break inserted into the return value.
</p>
<p>
Use <var>Indent</var> to specify the number of Space (#32) characters inserted 
as indentation at the beginning of each word-wrapped line. The default value is 
0 (zero) and omits indentation in the word-wrapped lines. A negative value in 
Indent causes the argument to be set to 0.
</p>
<p>
The Indent argument affects the number of UTF-8 characters allowed in each 
word-wrapped line. When set to a positive non-zero value, the maximum number of 
characters allowed per line is <b>MaxCol - Indent</b>.
</p>
<p>
No actions are performed in the function when S is an empty string (''), 
MaxCol is set to 0 (zero), or BreakChars is an empty set ([]).
</p>
</descr>
<version>
Modified in LazUtils 4.0 to include the overload with an indentation argument.
</version>
<seealso>
<link id="#lazutils.lazstringutils.BreakString">BreakString</link>
</seealso>
</element>
<element name="UTF8WrapText.Result">
<short>Word-wrapped version of the specified text.</short>
</element>
<element name="UTF8WrapText.S">
<short>String with values word-wrapped in the routine.</short>
</element>
<element name="UTF8WrapText.BreakStr">
<short>End-of-line sequence used in the routine.</short>
</element>
<element name="UTF8WrapText.BreakChars">
<short>Set of characters where a line break cab be inserted.</short>
</element>
<element name="UTF8WrapText.MaxCol">
<short>Maximum line width in number of UTF-8 characters.</short>
</element>
<element name="UTF8WrapText.Indent">
<short>
Number of Space (#32) characters used to indent the individual lines of 
word-wrapped text.
</short>
</element>

<element name="IsPureAscii">
<short>
Determines whether the specified string contains only single-byte ASCII  
characters.
</short>
<descr>
<p>
Used in the implementation of the TStringListUTF8Fast.InsertItem method.
</p>
</descr>
<version>
Added in LazUtils version 3.2.
</version>
<seealso>
<link id="TStringListUTF8Fast.InsertItem"/>
</seealso>
</element>
<element name="IsPureAscii.Result">
<short>
Returns <b>True</b> if all of the characters in S have a value less than $7F.
</short>
</element>
<element name="IsPureAscii.S">
<short>
String with the characters examined in the method.
</short>
</element>

<element name="TEscapeMode">
<short>
Represents styles used to escape control characters.
</short>
<descr>
<p>
<var>TEscapeMode</var> is an enumerated type with values that determine the 
output style for escaped characters in <var>Utf8EscapeControlChars</var>.
</p>
</descr>
<seealso/>
</element>
<element name="TEscapeMode.emPascal">
<short>Pascal-style escape characters '#27'</short>
</element>
<element name="TEscapeMode.emHexPascal">
<short>Pascal-style hexadecimal strings '#$1B'</short>
</element>
<element name="TEscapeMode.emHexC">
<short>C-style hexadecimal strings '\0x1B'</short>
</element>
<element name="TEscapeMode.emC">
<short>C-style strings '\e'</short>
</element>
<element name="TEscapeMode.emAsciiControlNames">
<short>ASCII-style control names '[ESC]'</short>
</element>

<element name="Utf8EscapeControlChars">
<short>
Translates control characters in a UTF-8-encoded string into human readable 
format.
</short>
<descr>
<p>
<var>Utf8EscapeControlChars</var> translates control characters inside a 
UTF-8-encoded string into human readable format. Characters in the range 
#0..#31 are converted into the human-readable values for the control 
characters in the format specified by <var>EscapeMode</var>, including:
</p>
<dl>
<dt>emPascal</dt>
<dd>Pascal-style escape characters '#27'</dd>
<dt>emHexPascal</dt>
<dd>Pascal-style hexadecimal strings '#$1B'</dd>
<dt>emHexC</dt>
<dd>C-style hexadecimal strings '\0x1B'</dd>
<dt>emC</dt>
<dd>C-style strings '\e'</dd>
<dt>emAsciiControlNames</dt>
<dd>ASCII-style control names '[ESC]'</dd>
</dl>
<p>
Utf8EscapeControlChars calls <var>FindInvalidUTF8Codepoint</var> to see if 
<var>S</var> contains any invalid codepoints for the UTF-8 encoding. 
<var>UTF8FixBroken</var> is called to repair the input value.
</p>
<p>
Utf8EscapeControlChars iterates over the characters in S, and converts any 
character value in the eligible range using an internal lookup table for the 
value in EscapeMode. All other character values (or values in multi-byte 
UTF-8 code points) are included in the return value in their unmodified form.
</p>
<p>
Mainly used as a diagnostic or logging tool.
</p>
</descr>
<seealso>
<link id="UTF8FixBroken"/>
<link id="TEscapeMode"/>
</seealso>
</element>
<element name="Utf8EscapeControlChars.Result">
<short>String with the escaped values for control characters in S.</short>
</element>
<element name="Utf8EscapeControlChars.S">
<short>UTF-8 encoded string with values converted in the routine.</short>
</element>
<element name="Utf8EscapeControlChars.EscapeMode">
<short>Controls the human readable format for escaped characters.</short>
</element>

<element name="TUTF8TrimFlag">
<short>
Controls trimming actions performed in UTF8Trim.
</short>
<descr>
<p>
<var>TUTF8TrimFlag</var> is an enumerated type with values that control 
trimming actions performed in the <var>UTF8Trim</var> function.
</p>
</descr>
<seealso>
<link id="TUTF8TrimFlags"/>
<link id="UTF8Trim"/>
</seealso>
</element>
<element name="TUTF8TrimFlag.u8tKeepStart">
<short>Keeps leading whitespace.</short>
</element>
<element name="TUTF8TrimFlag.u8tKeepEnd">
<short>Keeps trailing whitespace.</short>
</element>
<element name="TUTF8TrimFlag.u8tKeepTabs">
<short>Keeps tab characters.</short>
</element>
<element name="TUTF8TrimFlag.u8tKeepLineBreaks">
<short>Keeps line breaks.</short>
</element>
<element name="TUTF8TrimFlag.u8tKeepNoBreakSpaces">
<short>Keeps no-break space characters.</short>
</element>
<element name="TUTF8TrimFlag.u8tKeepControlCodes">
<short>Keeps control codes other than tabs and line breaks.</short>
</element>

<element name="TUTF8TrimFlags">
<short>
Stores values from the TUTF8TrimFlag enumeration.
</short>
<descr>
<p>
<var>TUTF8TrimFlags</var> is a set type used to store values from the 
<var>TUTF8TrimFlag</var> enumeration. TUTF8TrimFlags is the type passed in 
arguments to the <var>UTF8Trim</var> function.
</p>
</descr>
<seealso>
<link id="TUTF8TrimFlag"/>
<link id="UTF8Trim"/>
</seealso>
</element>

<element name="UTF8Trim">
<short>
Removes leading and trailing whitespace or control characters.
</short>
<descr>
<p>
<var>UTF8Trim</var> removes spaces, tabs, line breaks and control characters 
at both the start and the end of the UTF-8-encoded value in <var>s</var>. Use 
<var>Flags</var> to delete at the start only or at the end only, or to to not 
delete line breaks. Control characters are the Unicode sets C0 and C1, and 
the left-to-right and right-to-left marks.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8Trim.Result">
<short>Trimmed values for the string.</short>
</element>
<element name="UTF8Trim.s">
<short>String with values to trim.</short>
</element>
<element name="UTF8Trim.Flags">
<short>Actions to perform in the function.</short>
</element>

<element name="UTF8CompareStr">
<short>
Compares the UTF-8-encoded string values.
</short>
<descr>
<p>
<var>UTF8CompareStr</var> is a function used to compare the specified 
UTF-8-encoded string values. The return value indicates the relative sort 
order for the compared values, and includes:
</p>
<dl>
<dt>0</dt>
<dd>Values are the same</dd>
<dt>&lt;1</dt>
<dd>Value S1 comes before S2 in an alphabetic sort order</dd>
<dt>&gt;1</dt>
<dd>Value S1 comes after S2 in an alphabetic sort order</dd>
</dl>
<p>
Internally, UTF8CompareStr calls <var>WideCompareText</var> using the values 
in S1 and S2 converted to UTF-16 code points.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8CompareStr.Result">
<short>Relative order for the compared values.</short>
</element>
<element name="UTF8CompareStr.S1">
<short>First value for the comparison.</short>
</element>
<element name="UTF8CompareStr.S2">
<short>Second value for the comparison.</short>
</element>
<element name="UTF8CompareStr.Count1">
<short>Length of the first value.</short>
</element>
<element name="UTF8CompareStr.Count2">
<short>Length of the second value.</short>
</element>

<element name="UTF8CompareStrP">
<short>Compares the specified PChar values.</short>
<descr>
<p>
Calls UTF8CompareStr to get the return value for the function.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8CompareStrP.Result">
<short>Relative order for the compared values.</short>
</element>
<element name="UTF8CompareStrP.S1">
<short>First PChar value for the comparison.</short>
</element>
<element name="UTF8CompareStrP.S2">
<short>Second PChar value for the comparison.</short>
</element>

<element name="UTF8CompareText">
<short>
Case-insensitive comparison of two UTF-8-encoded values.
</short>
<descr>
<p>
<var>UTF8CompareText</var> is a function used to perform a case-insensitive 
comparison between the specified UTF-8-encoded values. The return value 
indicates the relative sort order for the compared values, and includes:
</p>
<dl>
<dt>0</dt>
<dd>Values are the same</dd>
<dt>&lt; 0</dt>
<dd>Value S1 comes before S2 in an alphabetic sort order</dd>
<dt>&gt; 0</dt>
<dd>Value S1 comes after S2 in an alphabetic sort order</dd>
</dl>
<p>
Internally, UTF8CompareText uses <var>WideCompareText</var> when multi-byte 
codepoints are found in the compared values. This function guarantees proper 
collation on all supported platforms.
</p>
</descr>
<seealso/>
</element>
<element name="UTF8CompareText.Result">
<short>Relative order for the compared values.</short>
</element>
<element name="UTF8CompareText.S1">
<short>First value for the comparison.</short>
</element>
<element name="UTF8CompareText.S2">
<short>Second value for the comparison.</short>
</element>

<element name="UTF8CompareTextP">
<short>
Performs a case-insensitive comparision for the specified UTF-8-encoded PChar 
values.
</short>
<descr>
<p>
Converts values in S1 and S2 to UTF-16 encoding, and calls WideCompareText to 
get the return value for the case-insensitive comparison. The return value 
contains the relative difference between the compared values. For instance:
</p>
<ul>
<li>&lt;0 when S1&lt;S2.</li>
<li>0 when S1=S2.</li>
<li>&gt;0 when S1&gt;S2.</li>
</ul>
</descr>
<seealso/>
</element>
<element name="UTF8CompareTextP.Result">
<short>
Integer result for the case-insensitive comparison.
</short>
</element>
<element name="UTF8CompareTextP.S1">
<short>
PChar with the values used in the comparison.
</short>
</element>
<element name="UTF8CompareTextP.S2">
<short>
PChar with the values used in the comparison.
</short>
</element>

<element name="UTF8CompareLatinTextFast">
<short>
Deprecated. Use UTF8CompareText or AnsiCompareText instead.
</short>
<descr>
<p>
<var>UTF8CompareLatinTextFast</var> is like UTF8CompareText, but does not 
return strict alphabetical order. The order is deterministic and good for 
binary search and similar uses. It avoids the conversions from UTF-8 to UTF-16 
needed to use WideCompareText.
</p>
<p>
UTF8CompareLatinTextFast optimizes the comparison of values using single-byte 
encoding by converting uppercase characters to lowercase characters for the 
comparison. Multi-byte portions (with character values larger than Decimal 
127) are optimized to ignore leading bytes sequences common to both compared 
values.
</p>
<p>
Otherwise, the routine falls back to AnsiCompareText to compare lowercase 
ASCII values in S1 and S2.
</p>
<p>
The return value is a pointer to an Integer where the relative sort order for 
the compared values is stored.
</p>
<dl>
<dt>&lt;0</dt>
<dd>S1 comes before S2 in the sort order.</dd>
<dt>&gt;0</dt>
<dd>S1 comes after S2 in the sort order.</dd>
<dt>0 (zero)</dt>
<dd>S1 and S2 have the same value in the sort order.</dd>
</dl>
</descr>
<version>
Deprecated in LazUtils version 3.2 (Feb 2024).
</version>
<seealso>
<link id="UTF8CompareText"/>
<link id="#rtl.sysutils.AnsiCompareText">AnsiCompareText</link>
</seealso>
</element>
<element name="UTF8CompareLatinTextFast.Result">
<short>
Pointer to an Integer with the relative order for the compared values.
</short>
</element>
<element name="UTF8CompareLatinTextFast.S1">
<short>
UTF-8-encoded String value used in the comparison.
</short>
</element>
<element name="UTF8CompareLatinTextFast.S2">
<short>
UTF-8-encoded String value used in the comparison.
</short>
</element>

<element name="UTF8CompareStrCollated">
<short>
Deprecated. Use UTF8CompareStr instead.
</short>
<descr>
<p>
<var>UTF8CompareStrCollated</var> is used to compare two strings using 
language-specific sorting. The return value contains the relative sort order 
for the compared values, as defined for <var>UTF8CompareStr</var>.
</p>
</descr>
<version>
Deprecated in LazUtils version 3.2 (Feb 2024).
</version>
<seealso/>
</element>
<element name="UTF8CompareStrCollated.Result">
<short>Relative order for the compared values.</short>
</element>
<element name="UTF8CompareStrCollated.S1">
<short>First string for the comparison.</short>
</element>
<element name="UTF8CompareStrCollated.S2">
<short>Second string for the comparison.</short>
</element>

<element name="CompareStrListUTF8LowerCase">
<short>
Compares the specified lines of text in a TStringList.
</short>
<descr>
<p>
<var>CompareStrListUTF8LowerCase</var> is an <var>Integer</var> function used 
to compare the specified lines of text in the <var>TStringList</var> 
argument. <var>Index1</var> and <var>Index2</var> contain the ordinal 
positions for the respective lines of text. CompareStrListUTF8LowerCase calls 
<var>UTF8CompareText</var> to perform a case-insensitive comparison between 
the values.
</p>
<p>
The return value contains the relative sort order for the compared values, as 
defined for <var>UTF8CompareText</var>.
</p>
</descr>
<seealso>
<link id="UTF8CompareText"/>
</seealso>
</element>
<element name="CompareStrListUTF8LowerCase.Result">
<short>Relative order for the compared values.</short>
</element>
<element name="CompareStrListUTF8LowerCase.List">
<short>TStringList with values for the comparison.</short>
</element>
<element name="CompareStrListUTF8LowerCase.Index1">
<short>Position of the first text line.</short>
</element>
<element name="CompareStrListUTF8LowerCase.Index2">
<short>Position of the second text line.</short>
</element>

<element name="TStringListUTF8Fast">
<short>
Implements a string list using fast ASCII comparison functions when its data is 
pure ASCII.
</short>
<descr>
<p>
When data is Unicode, it switches to slower AnsiCompare functions. The switch 
is managed by setting the UseLocale property/option and should not be changed 
by the user.
</p>
</descr>
<seealso>
<link id="#rtl.classes.TStringList">TStringList</link>
</seealso>
</element>

<element name="TStringListUTF8Fast.InsertItem">
<short>
Ensures that the UseLocale property is enabled when a new line with non-ASCII 
data is stored in the string list.
</short>
<descr/>
<seealso/>
</element>
<element name="TStringListUTF8Fast.InsertItem.Index">
<short>
Ordinal position in the string list where the value in S is stored.
</short>
</element>
<element name="TStringListUTF8Fast.InsertItem.S">
<short>
String value examined and stored in the method.
</short>
</element>

<element name="TStringListUTF8Fast.Create">
<short>
Constructor for the class instance.
</short>
<descr>
<p>
<var>Create</var> is the overridden constructor for the class instance. It 
calls the inherited method on entry to set the default encoding and options 
used in the class instance. Create ensures that the UseLocale property is set 
to <b>False</b> to allow fast comparisons for ASCII data stored in the string 
list.
</p>
</descr>
<seealso>
<link id="TStringListUTF8Fast.InsertItem"/>
<link id="#rtl.classes.TStrings.UseLocale">TStrings.UseLocale</link>
<link id="#rtl.classes.TStrings.DefaultEncoding">TStrings.DefaultEncoding</link>
</seealso>
</element>

<element name="TConvertResult">
<short>
Indicates the result from UTF-8 &lt;-&gt; UTF-16 conversions.
</short>
<descr>
<p>
<var>TConvertResult</var> is an enumeration type with values that indicate 
the result from <var>ConvertUTF8ToUTF16</var> and 
<var>ConvertUTF16ToUTF8</var> function calls.
</p>
</descr>
<seealso/>
</element>
<element name="TConvertResult.trNoError">
<short>No error in the conversion.</short>
</element>
<element name="TConvertResult.trNullSrc">
<short>Source value is null.</short>
</element>
<element name="TConvertResult.trNullDest">
<short>Destination value is null.</short>
</element>
<element name="TConvertResult.trDestExhausted">
<short>Destination value is too small for the converted value.</short>
</element>
<element name="TConvertResult.trInvalidChar">
<short>An invalid encoding was found in the source value.</short>
</element>
<element name="TConvertResult.trUnfinishedChar">
<short>An unfinished encoding was found in the source value.</short>
</element>

<element name="TConvertOption">
<short>
Indicates options enabled during UTF-8 &lt;-&gt; UTF-16 conversions.
</short>
<descr>
<p>
<var>TConvertOption</var> is an enumeration type with values that indicate 
options enabled during UTF-8 &lt;-&gt; UTF-16 conversions.
</p>
</descr>
<seealso/>
</element>
<element name="TConvertOption.toInvalidCharError">
<short>Stop on invalid source char and report error.</short>
</element>
<element name="TConvertOption.toInvalidCharToSymbol">
<short>Replace invalid source chars with '?'</short>
</element>
<element name="TConvertOption.toUnfinishedCharError">
<short>Stop on unfinished source char and report error.</short>
</element>
<element name="TConvertOption.toUnfinishedCharToSymbol">
<short>Replace unfinished source char with '?'</short>
</element>

<element name="TConvertOptions">
<short>
Stores values from the TConvertOption enumeration.
</short>
<descr>
<p>
Stores values from the <var>TConvertOption</var> enumeration. Passed as an 
argument to <var>ConvertUTF8ToUTF16</var> and <var>ConvertUTF16ToUTF8</var>.
</p>
</descr>
<seealso>
<link id="TConvertOption"/>
<link id="ConvertUTF8ToUTF16"/>
<link id="ConvertUTF16ToUTF8"/>
</seealso>
</element>

<element name="ConvertUTF8ToUTF16">
<short>
Converts values from UTF-8 encoding to UTF-16 encoding.
</short>
<descr>
<p>
<var>ConvertUTF8ToUTF16</var> is used to convert the specified UTF-8 encoded 
string to UTF-16 encoded (system endian).
</p>
<p>
<var>Options</var> indicates the conversion options enabled in the function, 
and can include the following values:
</p>
<dl>
<dt>toInvalidCharError</dt>
<dd>
Stop on invalid source char and report error
</dd>
<dt>toInvalidCharToSymbol</dt>
<dd>
Replace invalid source chars with '?'
</dd>
<dt>toUnfinishedCharError</dt>
<dd>
Stop on unfinished source char and report error
</dd>
<dt>toUnfinishedCharToSymbol</dt>
<dd>
Replace unfinished source char with '?'
</dd>
</dl>
<p>
The return value is a value from the <var>TConvertResult</var> enumeration, 
including:
</p>
<dl>
<dt>
trNoError
</dt>
<dd>
The string was successfully converted without any error
</dd>
<dt>
trNullSrc
</dt>
<dd>
Pointer to source string is nil
</dd>
<dt>
trNullDest
</dt>
<dd>
Pointer to destination string is nil
</dd>
<dt>
trDestExhausted
</dt>
<dd>
Destination buffer size is not big enough to hold converted string
</dd>
<dt>
trInvalidChar
</dt>
<dd>
Invalid source char has occurred
</dd>
<dt>
trUnfinishedChar
</dt>
<dd>
Unfinished source char has occurred
</dd>
</dl>
</descr>
<seealso/>
</element>
<element name="ConvertUTF8ToUTF16.Result">
<short>Converted values from the function.</short>
</element>
<element name="ConvertUTF8ToUTF16.Dest">
<short>Pointer to destination string.</short>
</element>
<element name="ConvertUTF8ToUTF16.DestWideCharCount">
<short>Wide char count allocated in destination string.</short>
</element>
<element name="ConvertUTF8ToUTF16.Src">
<short>Pointer to source string.</short>
</element>
<element name="ConvertUTF8ToUTF16.SrcCharCount">
<short>Char count allocated in source string.</short>
</element>
<element name="ConvertUTF8ToUTF16.Options">
<short>
Conversion options, if none is set, both invalid and unfinished source chars 
are skipped.
</short>
</element>
<element name="ConvertUTF8ToUTF16.ActualWideCharCount">
<short>Actual WideChar count used int he conversion.</short>
</element>

<element name="ConvertUTF16ToUTF8">
<short>Converts values from UTF-16 encoding to UTF-8 encoding.</short>
<descr>
<p>
Converts the specified UTF-16 encoded string (system endian) to its UTF-8 
encoding.
</p>
<p>
<var>Options</var> indicates the conversion options enabled in the function, 
and can include the following values:
</p>
<dl>
<dt>toInvalidCharError</dt>
<dd>
Stop on invalid source char and report error
</dd>
<dt>toInvalidCharToSymbol</dt>
<dd>
Replace invalid source chars with '?'
</dd>
<dt>toUnfinishedCharError</dt>
<dd>
Stop on unfinished source char and report error
</dd>
<dt>toUnfinishedCharToSymbol</dt>
<dd>
Replace unfinished source char with '?'
</dd>
</dl>
<p>
The return value is a value from the <var>TConvertResult</var> enumeration, 
including:
</p>
<dl>
<dt>
trNoError
</dt>
<dd>
The string was successfully converted without any error
</dd>
<dt>
trNullSrc
</dt>
<dd>
Pointer to source string is nil
</dd>
<dt>
trNullDest
</dt>
<dd>
Pointer to destination string is nil
</dd>
<dt>
trDestExhausted
</dt>
<dd>
Destination buffer size is not big enough to hold converted string
</dd>
<dt>
trInvalidChar
</dt>
<dd>
Invalid source char has occurred
</dd>
<dt>
trUnfinishedChar
</dt>
<dd>
Unfinished source char has occurred
</dd>
</dl>
</descr>
<seealso>
<link id="TConvertOptions"/>
<link id="TConvertOption"/>
<link id="TConvertResult"/>
</seealso>
</element>
<element name="ConvertUTF16ToUTF8.Result">
<short>Converted values from the function.</short>
</element>
<element name="ConvertUTF16ToUTF8.Dest">
<short>Pointer to destination string.</short>
</element>
<element name="ConvertUTF16ToUTF8.DestCharCount">
<short>Char count allocated in destination string.</short>
</element>
<element name="ConvertUTF16ToUTF8.Src">
<short>Pointer to source string.</short>
</element>
<element name="ConvertUTF16ToUTF8.SrcWideCharCount">
<short>Wide char count allocated in source string.</short>
</element>
<element name="ConvertUTF16ToUTF8.Options">
<short>Conversion options, if none is set, both
invalid and unfinished source chars are skipped.</short>
</element>
<element name="ConvertUTF16ToUTF8.ActualCharCount">
<short>
Actual char count converted from source string to destination string.
</short>
</element>

<element name="UTF8ToUTF16">
<short>
Converts the UTF-8 encoded string to UTF-16 encoding (system endian).
</short>
<descr>
<p>
Converts the UTF-8 encoded string to UTF-16 encoding (system endian).
</p>
</descr>
<seealso/>
</element>

<element name="UTF16ToUTF8">
<short>
Converts a UTF-16-encoded string (system endian) to UTF-8 encoding.
</short>
<descr>
<p>
UTF16ToUTF8 is a TConvertResult function used to convert the specified 
UTF-16-encoded string (system endian) to UTF-8 encoding.
</p>
<p>
The return value is a <var>TConvertResult</var> enumeration value, and 
includes:
</p>
<dl>
<dt>
trNoError
</dt>
<dd>
The string was successfully converted without any error
</dd>
<dt>
trNullSrc
</dt>
<dd>
Pointer to source string is Nil
</dd>
<dt>
trNullDest
</dt>
<dd>
Pointer to destination string is Nil
</dd>
<dt>
trDestExhausted
</dt>
<dd>
Destination buffer size is not big enough to hold converted string
</dd>
<dt>
trInvalidChar
</dt>
<dd>
Invalid source char has occurred
</dd>
<dt>
trUnfinishedChar
</dt>
<dd>
Unfinished source char has occurred
</dd>
</dl>
</descr>
<seealso>
<link id="TConvertResult"/>
</seealso>
</element>
<element name="UTF16ToUTF8.Result">
<short>UTF-8-encoded string.</short>
</element>
<element name="UTF16ToUTF8.S">
<short>Source UTF-16 string (system endian).</short>
</element>
<element name="UTF16ToUTF8.P">
<short>Pointer to the Source UTF-16 string (system endian).</short>
</element>
<element name="UTF16ToUTF8.WideCnt">
<short>Number of WideChar values in the source string.</short>
</element>

<element name="LazGetLanguageIDs">
<short>
Deprecated. Use the GetLanguageID function from the 
<file>translations.pas</file> unit instead.
</short>
<descr/>
<version>
Deprecated in LazUtils version 2.3.0.
</version>
<seealso>
<link id="#lazutils.translations.GetLanguageID"/>
</seealso>
</element>
<element name="LazGetLanguageIDs.Lang"/>
<element name="LazGetLanguageIDs.FallbackLang"/>

<element name="LazGetShortLanguageID">
<short>
Deprecated. Use the GetLanguageID function from the 
<file>translations.pas</file> unit instead.
</short>
<descr/>
<version>
Deprecated in LazUtils version 2.3.0.
</version>
<seealso>
<link id="#lazutils.translations.GetLanguageID"/>
</seealso>
</element>
<element name="LazGetShortLanguageID.Lang"/>

<element name="FPUpChars">
<short>
Contains uppercase characters for all values in the char type.
</short>
<descr>
<p>
<var>FPUpChars</var> is an array of char type and uses the Lower and Upper 
bounds permitted for the char type. Values in FPUpChars are assigned in the 
initialization section for the <file>lazutf8.pas</file> unit, and contains 
the uppercase equivalent for all characters in the char type.
</p>
</descr>
<seealso/>
</element>

<element name="UTF8GetStandardCodePage">
<short>Gets the default system code page for the wide string manager.</short>
<descr>
<p>
<var>UTF8GetStandardCodePage</var> is a <var>TSystemCodePage</var> function 
used to get the default code page for strings in the Wide String manager. 
UTF8GetStandardCodePage is implemented for Windows platforms that use a 
UTF-8-enabled Run-time Library (RTL). It is assigned as the procedure used by 
the wide string manager for the platform.
</p>
<p>
<var>stdcp</var> contains the <var>TStandardCodePageEnum</var> enumeration 
value that identifies the default code page for the platform.
</p>
<p>
The return value is set to the <var>CP_UTF8</var> constant.
</p>
</descr>
<seealso/>
</element>

</module>
<!-- LazUTF8 -->
</package>
</fpdoc-descriptions>