lazarus/docs/xml/lazutils/lazunicode.xml

482 lines
16 KiB
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">
<!--
====================================================================
LazUnicode
====================================================================
-->
<module name="LazUnicode">
<short>
Provides encoding-agnostic Unicode string manipulation functions and an
enumerator.
</short>
<descr>
<p>
<file>lazunicode.pas</file> provides encoding-agnostic Unicode string
manipulation functions and an enumerator. It works transparently with UTF-8
and UTF-16 encodings, and allows one codebase to work for:
</p>
<ol>
<li>Lazarus using its default UTF-8 encoding</li>
<li>
Future FPC and Lazarus versions with Delphi compatible UTF-16 encoding
</li>
<li>
Delphi compatibility where String is defined as UnicodeString
</li>
</ol>
<remark>
Behavior of helper functions are altered using the <var>{$ModeSwitch
UnicodeStrings}</var> directive; the correct routines for handling UTF-8 or
UTF-16 are called based on the mode switch value.
</remark>
<p>
<file>lazunicode.pas</file> is part of the <file>LazUtils</file> package.
</p>
</descr>
<!-- unresolved externals -->
<element name="Classes"/>
<element name="SysUtils"/>
<element name="character"/>
<element name="LazUTF16"/>
<element name="LazUTF8"/>
<!-- function Visibility: default -->
<element name="CodePointCopy">
<short>
Copies the specified number of codepoints starting at a character position.
</short>
<descr>
<p>
Copies the number of codepoints in <var>CharCount</var> from <var>s</var>,
starting at the character position in <var>StartCharIndex</var>. For
platforms that require UTF-16, <var>UTF16Copy</var> is called. For other
platforms, <var>UTF8Copy</var> is called.
</p>
</descr>
<seealso>
<link id="#lazutils.lazutf16.UTF16Copy">UTF16Copy</link>
<link id="#lazutils.lazutf8.UTF8Copy">UTF8Copy</link>
</seealso>
</element>
<!-- function result Visibility: default -->
<element name="CodePointCopy.Result">
<short>Values copied from the string.</short>
</element>
<!-- argument Visibility: default -->
<element name="CodePointCopy.s">
<short>UTF-encoded string values.</short>
</element>
<!-- argument Visibility: default -->
<element name="CodePointCopy.StartCharIndex">
<short>Initial character position.</short>
</element>
<!-- argument Visibility: default -->
<element name="CodePointCopy.CharCount">
<short>Number of characters needed in the copy operation.</short>
</element>
<!-- function Visibility: default -->
<element name="CodePointLength">
<short>
Gets the number of codepoints in the specified string.
</short>
<descr>
Gets the number of codepoints in the specified string. For platforms that
require UTF-16, UTF16Length is called to get the return value for the
function. For other platforms, UTF8LengthFast is called to get the number of
codepoints.
</descr>
<seealso></seealso>
</element>
<!-- function result Visibility: default -->
<element name="CodePointLength.Result">
<short>Number of codepoints in the string.</short>
</element>
<!-- argument Visibility: default -->
<element name="CodePointLength.s">
<short>UTF-encoded values examined in the function.</short>
</element>
<!-- function Visibility: default -->
<element name="CodePointPos">
<short>
Gets the position where the search value is found in a string.
</short>
<descr>
<p>
Gets the position in SearchInText where SearchForText is found. StartPos
indicates the initial character position (codepoint) in SearchInText used for
the comparison. The default value is 1.
</p>
<p>
The return value contains the character position (codepoint) where the search
value was found. The return value is 0 (zero) if SearchForText is not found
in the string. For platforms that require UTF-16, UTF16Pos is called to get
the return value. For other platforms, UTF8Pos is called to get the character
position (codepoint).
</p>
</descr>
<errors></errors>
<seealso></seealso>
</element>
<!-- function result Visibility: default -->
<element name="CodePointPos.Result">
<short>
Character position (codepoint) where the search value was found in the string.
</short>
</element>
<!-- argument Visibility: default -->
<element name="CodePointPos.SearchForText">
<short>Values to locate in the string.</short>
</element>
<!-- argument Visibility: default -->
<element name="CodePointPos.SearchInText">
<short>String to search for the specified values.</short>
</element>
<!-- argument Visibility: default -->
<element name="CodePointPos.StartPos">
<short>Initial character position (codepoint) used in the comparison.</short>
</element>
<!-- function Visibility: default -->
<element name="CodePointSize">
<short>
Gets the number of bytes needed for a CodePoint in the specified value.
</short>
<descr>
Gets the number of bytes needed for the CodePoint specified in p. For
platforms that require UTF-16, TCharacter.IsHighSurrogate is called to get
the return value. For other platforms, UTF8CodepointSizeFast is called to get
the number of bytes for the codepoint. The return value is 1 or 2 for
UTF-16-enabled platforms, or in the range 1..4 for UTF-8-enabled platforms.
The return value can be 0 (zero) if p contains an empty string ('') or a
malformed codepoint.
</descr>
<seealso></seealso>
</element>
<!-- function result Visibility: default -->
<element name="CodePointSize.Result">
<short>Number of bytes required for a codepoint.</short>
</element>
<!-- argument Visibility: default -->
<element name="CodePointSize.p">
<short>String with the codepoint to examine in the function.</short>
</element>
<!-- function Visibility: default -->
<element name="IsCombining">
<short>
Determines if the specified value is a combining codepoint.
</short>
<descr>
Determines if the specified value is a combining codepoint. Please note,
there are many more rules for combining codepoints.The diacritical marks
handled in the function are only a subset of the possible Unicode values. For
platforms that require UTF-16, UTF16IsCombining is called to get the return
value for the specified codepoint. For other platforms, UTF8IsCombining is
called to examine the codepoint.
</descr>
<seealso></seealso>
</element>
<!-- function result Visibility: default -->
<element name="IsCombining.Result">
<short>
<b>True</b> when the codepoint represents a Unicode combining character.
</short>
</element>
<!-- argument Visibility: default -->
<element name="IsCombining.AChar">
<short>Codepoint to examine in the function.</short>
</element>
<!-- function Visibility: default -->
<element name="UnicodeToWinCP">
<short>
Converts the specified value to the Windows system codepage.
</short>
<descr>
Converts the specified value to the Windows system codepage. The Unicode
encoding used in s depends on the modeswitch value. For platforms that
require UTF-16, UTF16ToUTF8 and UTF8ToWinCP are called to get the return
value for the function, except when String is defined as UnicodeString. No
conversion is required in that situation. For other platforms, UTF8ToWinCP is
called to get the return value.
</descr>
<errors></errors>
<seealso></seealso>
</element>
<!-- function result Visibility: default -->
<element name="UnicodeToWinCP.Result">
<short>Values after conversion to the Windows code page.</short>
</element>
<!-- argument Visibility: default -->
<element name="UnicodeToWinCP.s">
<short>Unicode values to convert in the function.</short>
</element>
<!-- function Visibility: default -->
<element name="WinCPToUnicode">
<short>
Converts the specified string to Unicode.
</short>
<descr>
Converts the specified value from the Windows system codepage to Unicode. The
Unicode encoding used depends on the modeswitch value. For platforms that
require UTF-16, WinCPToUTF8 and UTF8ToUTF16 are called to get the return
value for the function. Except when String is defined as UnicodeString. No
conversion is required in that situation. For other platforms, WinCPToUTF8 is
called to get the return value.
</descr>
<errors></errors>
<seealso></seealso>
</element>
<!-- function result Visibility: default -->
<element name="WinCPToUnicode.Result">
<short>Unicode values for the specified string.</short>
</element>
<!-- argument Visibility: default -->
<element name="WinCPToUnicode.s">
<short>String with Windows code page values.</short>
</element>
<element name="StringOfCodePoint">
<short>
Creates a string with the specified number of codepoints.
</short>
<descr>
Creates a string with the specified number of codepoints. Like StringOfChar.
For platforms that require UTF-16, the values in ACodePoint are concatenated
together until the number of codepoints in N have been created. For other
platforms, Utf8StringOfChar is called to get the return value for the
function.
</descr>
<seealso></seealso>
</element>
<element name="StringOfCodePoint.Result">
<short>String with the specified number of codepoints.</short>
</element>
<element name="StringOfCodePoint.ACodePoint">
<short>Codepoint to use when creating the string.</short>
</element>
<element name="StringOfCodePoint.N">
<short>Number of codepoints required in the string.</short>
</element>
<!-- class Visibility: default -->
<element name="TUnicodeEnumeratorBase">
<short>Base class for a Unicode character enumerator.</short>
<descr>
Base class for a Unicode character enumerator.
</descr>
<errors></errors>
<seealso></seealso>
</element>
<!-- variable Visibility: private -->
<element name="TUnicodeEnumeratorBase.fSrcPos"/>
<element name="TUnicodeEnumeratorBase.fEndPos"/>
<element name="TUnicodeEnumeratorBase.fCurOne"/>
<element name="TUnicodeEnumeratorBase.fCurTwo"/>
<element name="TUnicodeEnumeratorBase.fCurThree"/>
<element name="TUnicodeEnumeratorBase.fCurFour"/>
<element name="TUnicodeEnumeratorBase.fCurrent"/>
<element name="TUnicodeEnumeratorBase.fCurrentCodeUnitCount"/>
<element name="TUnicodeEnumeratorBase.UpdateCurrent">
<short>
Copies byte values for the Current character (codepoint).
</short>
<descr>
Copies byte values used in Current for the character (codepoint) when
MoveNext is called to go to the next character. aCount contains the number of
byte values needed for the Unicode codepoint. UpdateCurrent increments the
internal pointer used to access values in the enumerator by the number of
bytes in aCount.
</descr>
<errors>
<p>
Raises an assertion error if the number of bytes in aCount is 0 (zero).
Raised with the message 'TUnicodeEnumeratorBase.UpdateCurrent: aCount=0'.
</p>
<p>
Raises an assertion error if the length of bytes copied to Current is
different that the value in aCount. Raised with the message
'TUnicodeEnumeratorBase.UpdateCurrent: Length(fCurrent)&lt;&gt;aCount.')'.
</p>
</errors>
</element>
<element name="TUnicodeEnumeratorBase.UpdateCurrent.aCount">
<short>Number of bytes needed for the codepoint.</short>
</element>
<!-- constructor Visibility: public -->
<element name="TUnicodeEnumeratorBase.Create">
<short>
Constructor for the class instance.
</short>
<descr>
Create initializes internal member variable used to access byte values for
Unicode codepoints. A is the string with codepoints traversed using the
enumerator.
</descr>
<seealso></seealso>
</element>
<!-- argument Visibility: default -->
<element name="TUnicodeEnumeratorBase.Create.A">
<short>Unicode string for the enumerator.</short>
</element>
<!-- property Visibility: public -->
<element name="TUnicodeEnumeratorBase.Current">
<short>
Byte values for the current codepoint in the enumerator.
</short>
<descr>
Current is a read-only String property which provides access to the byte
values for the current codepoint in the enumerator. Current is updated in
UpdateCurrent when the MoveNext method is called.
</descr>
<seealso></seealso>
</element>
<!-- property Visibility: public -->
<element name="TUnicodeEnumeratorBase.CurrentCodeUnitCount">
<short>
Number of bytes in the Current codepoint.
</short>
<descr>
CurrentCodeUnitCount is a read-only Integer property which contains the
number of bytes needed for the codepoint in Current. CurrentCodeUnitCount is
updated in UpdateCurrent when MoveNext is called.
</descr>
<seealso></seealso>
</element>
<!-- class Visibility: default -->
<element name="TCodePointEnumerator">
<short>
Base class for a Unicode codepoint enumerator.
</short>
<descr>
Base class for a Unicode codepoint enumerator. TCodePointEnumerator allows
traversal of Unicode codepoints. Uses UTF-8 or UTF-16 encodings depending on
value in <var>$ModeSwitch</var>. Extends the ancestor class to provide
navigation in the enumerator using the MoveNext method.
</descr>
<seealso></seealso>
</element>
<!-- function Visibility: public -->
<element name="TCodePointEnumerator.MoveNext">
<short>
Provides navigation to the next codepoint in the enumerator.
</short>
<descr>
Provides navigation to the next Unicode codepoint in the enumerator. The
return value contains <b>True</b> when more characters (codepoints) are
available to the enumerator. UpdateCurrent is called using the value from
CodePointSize to store the value for the Current property.
</descr>
<seealso></seealso>
</element>
<!-- function result Visibility: public -->
<element name="TCodePointEnumerator.MoveNext.Result">
<short><b>True</b> when more characters (codepoints) are available.</short>
</element>
<!-- class Visibility: default -->
<element name="TUnicodeCharacterEnumerator">
<short>
Implements an enumerator for Unicode codepoints.
</short>
<descr>
Implements an enumerator for Unicode codepoints. TUnicodeCharacterEnumerator
allows traversal of characters (codepoints) in a Unicode-encoded string.
Values use either UTF-16 or UTF-8 encoding depending on the value for
<var>$ModeSwitch</var>. An overridden MoveNext method is provided to handle
combining diacritical marks in the Unicode codepoints.
</descr>
<seealso></seealso>
</element>
<!-- variable Visibility: private -->
<element name="TUnicodeCharacterEnumerator.fCurrentCodePointCount"/>
<!-- property Visibility: public -->
<element name="TUnicodeCharacterEnumerator.CurrentCodePointCount">
<short>
Number of bytes used for the Current codepoint.
</short>
<descr>
CurrentCodePointCount is a read-only Integer property that indicates the
number of bytes used for the Current codepoint. CurrentCodePointCount is
updated in the MoveNext method, and includes any combining diacritical marks
found in the codepoints.
</descr>
<seealso></seealso>
</element>
<!-- function Visibility: public -->
<element name="TUnicodeCharacterEnumerator.MoveNext">
<short>
Adds support for combining diacritical marks when moving to the next
codepoint.
</short>
<descr>
<p>
MoveNext is an overridden method which adds support for combining diacritical
marks when moving to the next codepoint for the enumerator. The return value
is <b>True</b> when more characters (codepoints) are available to the
enumerator. MoveNext updates the value in CurrentCodeUnitCount, and includes
combining diacritical marks in the byte count. MoveNext calls UpdateCurrent
to store the value for the Current property.
</p>
<remark>
MoveNext does not call the inherited method.
</remark>
</descr>
<seealso></seealso>
</element>
<!-- function result Visibility: public -->
<element name="TUnicodeCharacterEnumerator.MoveNext.Result">
<short>
<b>True</b> when more characters (codepoints) are available to the enumerator.
</short>
</element>
<!-- operator Visibility: default -->
<element name="enumerator(string):tunicodecharacterenumerator">
<short>
Enumerator which combines diacritical marks.
</short>
<descr>
<p>
The enumerator operator enables For ... In loops. This enumerator combines
diacritical marks in the String argument for the operator. It is used by
default although there are more rules for combining codepoints. Diacritical
marks cover rules for most western languages.
</p>
</descr>
</element>
</module>
<!-- LazUnicode -->
</package>
</fpdoc-descriptions>