added composer files and installed vendor packages. Also modified xsls to display base project
This commit is contained in:
+3464
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,111 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
/**
|
||||
* BidiClass.php
|
||||
*
|
||||
* @since 2026-07-17
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*
|
||||
* This file is part of tc-lib-unicode-data software library.
|
||||
*/
|
||||
|
||||
namespace Com\Tecnick\Unicode\Data;
|
||||
|
||||
/**
|
||||
* Com\Tecnick\Unicode\Data\BidiClass
|
||||
*
|
||||
* Backed enum for the strong, weak and neutral bidirectional character classes.
|
||||
* The backing value of each case is the canonical class abbreviation used as the
|
||||
* keys of Type::STRONG, Type::WEAK and Type::NEUTRAL. The explicit formatting
|
||||
* codes (LRE, LRO, RLE, RLO, PDF, ...) are intentionally not part of this set.
|
||||
*
|
||||
* @since 2026-07-17
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*/
|
||||
enum BidiClass: string
|
||||
{
|
||||
// Strong types (Type::STRONG).
|
||||
case L = 'L';
|
||||
|
||||
case R = 'R';
|
||||
|
||||
case AL = 'AL';
|
||||
|
||||
// Weak types (Type::WEAK).
|
||||
case EN = 'EN';
|
||||
|
||||
case ES = 'ES';
|
||||
|
||||
case ET = 'ET';
|
||||
|
||||
case AN = 'AN';
|
||||
|
||||
case CS = 'CS';
|
||||
|
||||
case NSM = 'NSM';
|
||||
|
||||
case BN = 'BN';
|
||||
|
||||
// Neutral types (Type::NEUTRAL).
|
||||
case B = 'B';
|
||||
|
||||
case S = 'S';
|
||||
|
||||
case WS = 'WS';
|
||||
|
||||
case ON = 'ON';
|
||||
|
||||
/**
|
||||
* Resolve a loose bidirectional class value to the matching enum case.
|
||||
*
|
||||
* Accepts the canonical class abbreviation or an enum instance (returned
|
||||
* unchanged). Unknown values throw a \ValueError, matching the closed set
|
||||
* defined by Type::STRONG, Type::WEAK and Type::NEUTRAL.
|
||||
*
|
||||
* @param string|self $value Bidirectional class abbreviation or enum case.
|
||||
*/
|
||||
public static function fromLoose(string|self $value): self
|
||||
{
|
||||
if ($value instanceof self) {
|
||||
return $value;
|
||||
}
|
||||
|
||||
return self::from($value);
|
||||
}
|
||||
|
||||
/**
|
||||
* True for a strong type (L, R, AL).
|
||||
*/
|
||||
public function isStrong(): bool
|
||||
{
|
||||
return \array_key_exists($this->value, Type::STRONG);
|
||||
}
|
||||
|
||||
/**
|
||||
* True for a weak type (EN, ES, ET, AN, CS, NSM, BN).
|
||||
*/
|
||||
public function isWeak(): bool
|
||||
{
|
||||
return \array_key_exists($this->value, Type::WEAK);
|
||||
}
|
||||
|
||||
/**
|
||||
* True for a neutral type (B, S, WS, ON).
|
||||
*/
|
||||
public function isNeutral(): bool
|
||||
{
|
||||
return \array_key_exists($this->value, Type::NEUTRAL);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,183 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
/**
|
||||
* Bracket.php
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*
|
||||
* This file is part of tc-lib-unicode-data software library.
|
||||
*/
|
||||
|
||||
namespace Com\Tecnick\Unicode\Data;
|
||||
|
||||
/**
|
||||
* Com\Tecnick\Unicode\Data\Bracket
|
||||
*
|
||||
* Paired bracket properties (BidiBrackets.txt).
|
||||
*
|
||||
* Generated by tools/generate.php from the Unicode Character Database 17.0.0.
|
||||
* Do not edit manually.
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*/
|
||||
|
||||
class Bracket
|
||||
{
|
||||
/**
|
||||
* Opening paired brackets (Bidi_Paired_Bracket_Type=Open) and their closing counterpart.
|
||||
*
|
||||
* @var array<int, int>
|
||||
*/
|
||||
public const OPEN = [
|
||||
0x0028 => 0x0029, // PARENTHESIS
|
||||
0x005B => 0x005D, // SQUARE BRACKET
|
||||
0x007B => 0x007D, // CURLY BRACKET
|
||||
0x0F3A => 0x0F3B, // TIBETAN MARK GUG RTAGS GYON
|
||||
0x0F3C => 0x0F3D, // TIBETAN MARK ANG KHANG GYON
|
||||
0x169B => 0x169C, // OGHAM FEATHER MARK
|
||||
0x2045 => 0x2046, // SQUARE BRACKET WITH QUILL
|
||||
0x207D => 0x207E, // SUPERSCRIPT PARENTHESIS
|
||||
0x208D => 0x208E, // SUBSCRIPT PARENTHESIS
|
||||
0x2308 => 0x2309, // CEILING
|
||||
0x230A => 0x230B, // FLOOR
|
||||
0x2329 => 0x232A, // LEFT-POINTING ANGLE BRACKET
|
||||
0x2768 => 0x2769, // MEDIUM PARENTHESIS ORNAMENT
|
||||
0x276A => 0x276B, // MEDIUM FLATTENED PARENTHESIS ORNAMENT
|
||||
0x276C => 0x276D, // MEDIUM-POINTING ANGLE BRACKET ORNAMENT
|
||||
0x276E => 0x276F, // HEAVY-POINTING ANGLE QUOTATION MARK ORNAMENT
|
||||
0x2770 => 0x2771, // HEAVY-POINTING ANGLE BRACKET ORNAMENT
|
||||
0x2772 => 0x2773, // LIGHT TORTOISE SHELL BRACKET ORNAMENT
|
||||
0x2774 => 0x2775, // MEDIUM CURLY BRACKET ORNAMENT
|
||||
0x27C5 => 0x27C6, // S-SHAPED BAG DELIMITER
|
||||
0x27E6 => 0x27E7, // MATHEMATICAL WHITE SQUARE BRACKET
|
||||
0x27E8 => 0x27E9, // MATHEMATICAL ANGLE BRACKET
|
||||
0x27EA => 0x27EB, // MATHEMATICAL DOUBLE ANGLE BRACKET
|
||||
0x27EC => 0x27ED, // MATHEMATICAL WHITE TORTOISE SHELL BRACKET
|
||||
0x27EE => 0x27EF, // MATHEMATICAL FLATTENED PARENTHESIS
|
||||
0x2983 => 0x2984, // WHITE CURLY BRACKET
|
||||
0x2985 => 0x2986, // WHITE PARENTHESIS
|
||||
0x2987 => 0x2988, // Z NOTATION IMAGE BRACKET
|
||||
0x2989 => 0x298A, // Z NOTATION BINDING BRACKET
|
||||
0x298B => 0x298C, // SQUARE BRACKET WITH UNDERBAR
|
||||
0x298D => 0x2990, // SQUARE BRACKET WITH TICK IN TOP CORNER
|
||||
0x298F => 0x298E, // SQUARE BRACKET WITH TICK IN BOTTOM CORNER
|
||||
0x2991 => 0x2992, // ANGLE BRACKET WITH DOT
|
||||
0x2993 => 0x2994, // ARC LESS-THAN BRACKET
|
||||
0x2995 => 0x2996, // DOUBLE ARC GREATER-THAN BRACKET
|
||||
0x2997 => 0x2998, // BLACK TORTOISE SHELL BRACKET
|
||||
0x29D8 => 0x29D9, // WIGGLY FENCE
|
||||
0x29DA => 0x29DB, // DOUBLE WIGGLY FENCE
|
||||
0x29FC => 0x29FD, // LEFT-POINTING CURVED ANGLE BRACKET
|
||||
0x2E22 => 0x2E23, // TOP HALF BRACKET
|
||||
0x2E24 => 0x2E25, // BOTTOM HALF BRACKET
|
||||
0x2E26 => 0x2E27, // SIDEWAYS U BRACKET
|
||||
0x2E28 => 0x2E29, // DOUBLE PARENTHESIS
|
||||
0x2E55 => 0x2E56, // SQUARE BRACKET WITH STROKE
|
||||
0x2E57 => 0x2E58, // SQUARE BRACKET WITH DOUBLE STROKE
|
||||
0x2E59 => 0x2E5A, // TOP HALF PARENTHESIS
|
||||
0x2E5B => 0x2E5C, // BOTTOM HALF PARENTHESIS
|
||||
0x3008 => 0x3009, // ANGLE BRACKET
|
||||
0x300A => 0x300B, // DOUBLE ANGLE BRACKET
|
||||
0x300C => 0x300D, // CORNER BRACKET
|
||||
0x300E => 0x300F, // WHITE CORNER BRACKET
|
||||
0x3010 => 0x3011, // BLACK LENTICULAR BRACKET
|
||||
0x3014 => 0x3015, // TORTOISE SHELL BRACKET
|
||||
0x3016 => 0x3017, // WHITE LENTICULAR BRACKET
|
||||
0x3018 => 0x3019, // WHITE TORTOISE SHELL BRACKET
|
||||
0x301A => 0x301B, // WHITE SQUARE BRACKET
|
||||
0xFE59 => 0xFE5A, // SMALL PARENTHESIS
|
||||
0xFE5B => 0xFE5C, // SMALL CURLY BRACKET
|
||||
0xFE5D => 0xFE5E, // SMALL TORTOISE SHELL BRACKET
|
||||
0xFF08 => 0xFF09, // FULLWIDTH PARENTHESIS
|
||||
0xFF3B => 0xFF3D, // FULLWIDTH SQUARE BRACKET
|
||||
0xFF5B => 0xFF5D, // FULLWIDTH CURLY BRACKET
|
||||
0xFF5F => 0xFF60, // FULLWIDTH WHITE PARENTHESIS
|
||||
0xFF62 => 0xFF63, // HALFWIDTH CORNER BRACKET
|
||||
];
|
||||
|
||||
/**
|
||||
* Closing paired brackets (Bidi_Paired_Bracket_Type=Close) and their opening counterpart.
|
||||
*
|
||||
* @var array<int, int>
|
||||
*/
|
||||
public const CLOSE = [
|
||||
0x0029 => 0x0028, // PARENTHESIS
|
||||
0x005D => 0x005B, // SQUARE BRACKET
|
||||
0x007D => 0x007B, // CURLY BRACKET
|
||||
0x0F3B => 0x0F3A, // TIBETAN MARK GUG RTAGS GYON
|
||||
0x0F3D => 0x0F3C, // TIBETAN MARK ANG KHANG GYON
|
||||
0x169C => 0x169B, // OGHAM FEATHER MARK
|
||||
0x2046 => 0x2045, // SQUARE BRACKET WITH QUILL
|
||||
0x207E => 0x207D, // SUPERSCRIPT PARENTHESIS
|
||||
0x208E => 0x208D, // SUBSCRIPT PARENTHESIS
|
||||
0x2309 => 0x2308, // CEILING
|
||||
0x230B => 0x230A, // FLOOR
|
||||
0x232A => 0x2329, // LEFT-POINTING ANGLE BRACKET
|
||||
0x2769 => 0x2768, // MEDIUM PARENTHESIS ORNAMENT
|
||||
0x276B => 0x276A, // MEDIUM FLATTENED PARENTHESIS ORNAMENT
|
||||
0x276D => 0x276C, // MEDIUM-POINTING ANGLE BRACKET ORNAMENT
|
||||
0x276F => 0x276E, // HEAVY-POINTING ANGLE QUOTATION MARK ORNAMENT
|
||||
0x2771 => 0x2770, // HEAVY-POINTING ANGLE BRACKET ORNAMENT
|
||||
0x2773 => 0x2772, // LIGHT TORTOISE SHELL BRACKET ORNAMENT
|
||||
0x2775 => 0x2774, // MEDIUM CURLY BRACKET ORNAMENT
|
||||
0x27C6 => 0x27C5, // S-SHAPED BAG DELIMITER
|
||||
0x27E7 => 0x27E6, // MATHEMATICAL WHITE SQUARE BRACKET
|
||||
0x27E9 => 0x27E8, // MATHEMATICAL ANGLE BRACKET
|
||||
0x27EB => 0x27EA, // MATHEMATICAL DOUBLE ANGLE BRACKET
|
||||
0x27ED => 0x27EC, // MATHEMATICAL WHITE TORTOISE SHELL BRACKET
|
||||
0x27EF => 0x27EE, // MATHEMATICAL FLATTENED PARENTHESIS
|
||||
0x2984 => 0x2983, // WHITE CURLY BRACKET
|
||||
0x2986 => 0x2985, // WHITE PARENTHESIS
|
||||
0x2988 => 0x2987, // Z NOTATION IMAGE BRACKET
|
||||
0x298A => 0x2989, // Z NOTATION BINDING BRACKET
|
||||
0x298C => 0x298B, // SQUARE BRACKET WITH UNDERBAR
|
||||
0x2990 => 0x298D, // SQUARE BRACKET WITH TICK IN TOP CORNER
|
||||
0x298E => 0x298F, // SQUARE BRACKET WITH TICK IN BOTTOM CORNER
|
||||
0x2992 => 0x2991, // ANGLE BRACKET WITH DOT
|
||||
0x2994 => 0x2993, // ARC LESS-THAN BRACKET
|
||||
0x2996 => 0x2995, // DOUBLE ARC GREATER-THAN BRACKET
|
||||
0x2998 => 0x2997, // BLACK TORTOISE SHELL BRACKET
|
||||
0x29D9 => 0x29D8, // WIGGLY FENCE
|
||||
0x29DB => 0x29DA, // DOUBLE WIGGLY FENCE
|
||||
0x29FD => 0x29FC, // LEFT-POINTING CURVED ANGLE BRACKET
|
||||
0x2E23 => 0x2E22, // TOP HALF BRACKET
|
||||
0x2E25 => 0x2E24, // BOTTOM HALF BRACKET
|
||||
0x2E27 => 0x2E26, // SIDEWAYS U BRACKET
|
||||
0x2E29 => 0x2E28, // DOUBLE PARENTHESIS
|
||||
0x2E56 => 0x2E55, // SQUARE BRACKET WITH STROKE
|
||||
0x2E58 => 0x2E57, // SQUARE BRACKET WITH DOUBLE STROKE
|
||||
0x2E5A => 0x2E59, // TOP HALF PARENTHESIS
|
||||
0x2E5C => 0x2E5B, // BOTTOM HALF PARENTHESIS
|
||||
0x3009 => 0x3008, // ANGLE BRACKET
|
||||
0x300B => 0x300A, // DOUBLE ANGLE BRACKET
|
||||
0x300D => 0x300C, // CORNER BRACKET
|
||||
0x300F => 0x300E, // WHITE CORNER BRACKET
|
||||
0x3011 => 0x3010, // BLACK LENTICULAR BRACKET
|
||||
0x3015 => 0x3014, // TORTOISE SHELL BRACKET
|
||||
0x3017 => 0x3016, // WHITE LENTICULAR BRACKET
|
||||
0x3019 => 0x3018, // WHITE TORTOISE SHELL BRACKET
|
||||
0x301B => 0x301A, // WHITE SQUARE BRACKET
|
||||
0xFE5A => 0xFE59, // SMALL PARENTHESIS
|
||||
0xFE5C => 0xFE5B, // SMALL CURLY BRACKET
|
||||
0xFE5E => 0xFE5D, // SMALL TORTOISE SHELL BRACKET
|
||||
0xFF09 => 0xFF08, // FULLWIDTH PARENTHESIS
|
||||
0xFF3D => 0xFF3B, // FULLWIDTH SQUARE BRACKET
|
||||
0xFF5D => 0xFF5B, // FULLWIDTH CURLY BRACKET
|
||||
0xFF60 => 0xFF5F, // FULLWIDTH WHITE PARENTHESIS
|
||||
0xFF63 => 0xFF62, // HALFWIDTH CORNER BRACKET
|
||||
];
|
||||
}
|
||||
@@ -0,0 +1,203 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
/**
|
||||
* Constant.php
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*
|
||||
* This file is part of tc-lib-unicode-data software library.
|
||||
*/
|
||||
|
||||
namespace Com\Tecnick\Unicode\Data;
|
||||
|
||||
/**
|
||||
* Com\Tecnick\Unicode\Data\Constant
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*/
|
||||
class Constant
|
||||
{
|
||||
/*
|
||||
* Explicit Directional Embeddings
|
||||
* -------------------------------
|
||||
* The following characters signal that a piece of text is to be treated as embedded.
|
||||
* For example, an English quotation in the middle of an Arabic sentence could be marked
|
||||
* as being embedded left-to-right text. If there were a Hebrew phrase in the middle of
|
||||
* the English quotation, that phrase could be marked as being embedded right-to-left text.
|
||||
* Embeddings can be nested one inside another, and in isolates and overrides.
|
||||
*/
|
||||
|
||||
/**
|
||||
* (U+202A) LEFT-TO-RIGHT EMBEDDING
|
||||
* Treat the following text as embedded left-to-right
|
||||
*/
|
||||
public const LRE = 0x202A;
|
||||
|
||||
/**
|
||||
* (U+202B) RIGHT-TO-LEFT EMBEDDING
|
||||
* Treat the following text as embedded right-to-left
|
||||
*/
|
||||
public const RLE = 0x202B;
|
||||
|
||||
/*
|
||||
* Explicit Directional Overrides
|
||||
* ------------------------------
|
||||
* The following characters allow the bidirectional character types to be overridden when
|
||||
* required for special cases, such as for part numbers. They are to be avoided wherever possible,
|
||||
* because of security concerns. For more information, see [UTR36].
|
||||
* Directional overrides can be nested one inside another, and in embeddings and isolates.
|
||||
*/
|
||||
|
||||
/**
|
||||
* (U+202D) for LEFT-TO-RIGHT OVERRIDE
|
||||
* Force following characters to be treated as strong left-to-right characters
|
||||
*/
|
||||
public const LRO = 0x202D;
|
||||
|
||||
/**
|
||||
* (U+202E) RIGHT-TO-LEFT OVERRIDE
|
||||
* Force following characters to be treated as strong right-to-left characters
|
||||
*/
|
||||
public const RLO = 0x202E;
|
||||
|
||||
/*
|
||||
* Terminating Explicit Directional Embeddings and Overrides
|
||||
* ---------------------------------------------------------
|
||||
*/
|
||||
|
||||
/**
|
||||
* (U+202C) POP DIRECTIONAL FORMATTING
|
||||
* End the scope of the last LRE, RLE, RLO, or LRO whose scope has not yet been terminated
|
||||
*/
|
||||
public const PDF = 0x202C;
|
||||
|
||||
/*
|
||||
* Explicit Directional Isolates
|
||||
* -----------------------------
|
||||
* The following characters signal that a piece of text is to be treated as directionally isolated
|
||||
* from its surroundings. They are very similar to the explicit embedding formatting characters.
|
||||
* However, while an embedding roughly has the effect of a strong character on the ordering of the
|
||||
* surrounding text, an isolate has the effect of a neutral like U+FFFC OBJECT REPLACEMENT CHARACTER,
|
||||
* and is assigned the corresponding display position in the surrounding text.
|
||||
* Furthermore, the text inside the isolate has no effect on the ordering of the text outside it, and vice versa.
|
||||
*
|
||||
* In addition to allowing the embedding of strongly directional text without unduly affecting the bidirectional
|
||||
* order of its surroundings, one of the isolate formatting characters also offers an extra feature:
|
||||
* embedding text while inferring its direction heuristically from its constituent characters.
|
||||
*
|
||||
* Isolates can be nested one inside another, and in embeddings and overrides.
|
||||
*/
|
||||
|
||||
/**
|
||||
* (U+2066) LEFT-TO-RIGHT ISOLATE
|
||||
* Treat the following text as isolated and left-to-right
|
||||
*/
|
||||
public const LRI = 0x2066;
|
||||
|
||||
/**
|
||||
* (U+2067) RIGHT-TO-LEFT ISOLATE
|
||||
* Treat the following text as isolated and right-to-left
|
||||
*/
|
||||
public const RLI = 0x2067;
|
||||
|
||||
/**
|
||||
* (U+2068) FIRST STRONG ISOLATE
|
||||
* Treat the following text as isolated and in the direction of its first
|
||||
* strong directional character that is not inside a nested isolate
|
||||
*/
|
||||
public const FSI = 0x2068;
|
||||
|
||||
/*
|
||||
* Terminating Explicit Directional Isolates
|
||||
* -----------------------------------------
|
||||
* The following character terminates the scope of the last LRI, RLI, or FSI whose scope
|
||||
* has not yet been terminated, as well as the scopes of any subsequent LREs, RLEs, LROs, or RLOs
|
||||
* whose scopes have not yet been terminated.
|
||||
*/
|
||||
|
||||
/**
|
||||
* (U+2069) POP DIRECTIONAL ISOLATE
|
||||
* End the scope of the last LRI, RLI, or FSI
|
||||
*/
|
||||
public const PDI = 0x2069;
|
||||
|
||||
/*
|
||||
* Implicit Directional Marks
|
||||
* --------------------------
|
||||
* These characters are very light-weight formatting.
|
||||
* They act exactly like right-to-left or left-to-right characters,
|
||||
* except that they do not display or have any other semantic effect.
|
||||
* Their use is more convenient than using explicit embeddings or overrides because their scope is much more local.
|
||||
*/
|
||||
|
||||
/**
|
||||
* (U+200E) LEFT-TO-RIGHT MARK
|
||||
* Left-to-right zero-width character
|
||||
*/
|
||||
public const LRM = 0x200E;
|
||||
|
||||
/**
|
||||
* (U+200F) RIGHT-TO-LEFT MARK
|
||||
* Right-to-left zero-width non-Arabic character
|
||||
*/
|
||||
public const RLM = 0x200F;
|
||||
|
||||
/**
|
||||
* (U+061C) ARABIC LETTER MARK
|
||||
* Right-to-left zero-width Arabic character
|
||||
*/
|
||||
public const ALM = 0x061C;
|
||||
|
||||
/*
|
||||
* Other useful characters
|
||||
* -----------------------
|
||||
*/
|
||||
|
||||
/**
|
||||
* (U+0020) SPACE
|
||||
*/
|
||||
public const SPACE = 0x20;
|
||||
|
||||
/**
|
||||
* (U+00A0) NO-BREAK SPACE
|
||||
* Type: CS (Common Separator)
|
||||
*/
|
||||
public const NO_BREAK_SPACE = 0x00A0;
|
||||
|
||||
/**
|
||||
* (U+200C) ZERO WIDTH NON-JOINER
|
||||
*/
|
||||
public const ZERO_WIDTH_NON_JOINER = 0x200C;
|
||||
|
||||
/**
|
||||
* (U+200B) ZERO WIDTH SPACE
|
||||
* Type: BN (Boundary Neutral)
|
||||
*/
|
||||
public const ZERO_WIDTH_SPACE = 0x200B;
|
||||
|
||||
/**
|
||||
* (U+002D) HYPHEN-MINUS
|
||||
* Type: ES (European Number Separator)
|
||||
*/
|
||||
public const HYPHEN = 0x002D;
|
||||
|
||||
/**
|
||||
* (U+00AD) SOFT HYPHEN
|
||||
* Type: BN (Boundary Neutral)
|
||||
*/
|
||||
public const SOFT_HYPHEN = 0x00AD;
|
||||
}
|
||||
+5744
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,315 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
/**
|
||||
* Identity.php
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*
|
||||
* This file is part of tc-lib-unicode-data software library.
|
||||
*/
|
||||
|
||||
namespace Com\Tecnick\Unicode\Data;
|
||||
|
||||
/**
|
||||
* Com\Tecnick\Unicode\Data\Identity
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*/
|
||||
class Identity
|
||||
{
|
||||
/**
|
||||
* ToUnicode map for Identity-H stream
|
||||
*/
|
||||
public const CIDHMAP = <<<EOD
|
||||
/CIDInit /ProcSet findresource begin
|
||||
12 dict begin
|
||||
begincmap
|
||||
/CIDSystemInfo << /Registry (Adobe) /Ordering (UCS) /Supplement 0 >> def
|
||||
/CMapName /Adobe-Identity-UCS def
|
||||
/CMapType 2 def
|
||||
/WMode 0 def
|
||||
1 begincodespacerange
|
||||
<0000> <FFFF>
|
||||
endcodespacerange
|
||||
100 beginbfrange
|
||||
<0000> <00ff> <0000>
|
||||
<0100> <01ff> <0100>
|
||||
<0200> <02ff> <0200>
|
||||
<0300> <03ff> <0300>
|
||||
<0400> <04ff> <0400>
|
||||
<0500> <05ff> <0500>
|
||||
<0600> <06ff> <0600>
|
||||
<0700> <07ff> <0700>
|
||||
<0800> <08ff> <0800>
|
||||
<0900> <09ff> <0900>
|
||||
<0a00> <0aff> <0a00>
|
||||
<0b00> <0bff> <0b00>
|
||||
<0c00> <0cff> <0c00>
|
||||
<0d00> <0dff> <0d00>
|
||||
<0e00> <0eff> <0e00>
|
||||
<0f00> <0fff> <0f00>
|
||||
<1000> <10ff> <1000>
|
||||
<1100> <11ff> <1100>
|
||||
<1200> <12ff> <1200>
|
||||
<1300> <13ff> <1300>
|
||||
<1400> <14ff> <1400>
|
||||
<1500> <15ff> <1500>
|
||||
<1600> <16ff> <1600>
|
||||
<1700> <17ff> <1700>
|
||||
<1800> <18ff> <1800>
|
||||
<1900> <19ff> <1900>
|
||||
<1a00> <1aff> <1a00>
|
||||
<1b00> <1bff> <1b00>
|
||||
<1c00> <1cff> <1c00>
|
||||
<1d00> <1dff> <1d00>
|
||||
<1e00> <1eff> <1e00>
|
||||
<1f00> <1fff> <1f00>
|
||||
<2000> <20ff> <2000>
|
||||
<2100> <21ff> <2100>
|
||||
<2200> <22ff> <2200>
|
||||
<2300> <23ff> <2300>
|
||||
<2400> <24ff> <2400>
|
||||
<2500> <25ff> <2500>
|
||||
<2600> <26ff> <2600>
|
||||
<2700> <27ff> <2700>
|
||||
<2800> <28ff> <2800>
|
||||
<2900> <29ff> <2900>
|
||||
<2a00> <2aff> <2a00>
|
||||
<2b00> <2bff> <2b00>
|
||||
<2c00> <2cff> <2c00>
|
||||
<2d00> <2dff> <2d00>
|
||||
<2e00> <2eff> <2e00>
|
||||
<2f00> <2fff> <2f00>
|
||||
<3000> <30ff> <3000>
|
||||
<3100> <31ff> <3100>
|
||||
<3200> <32ff> <3200>
|
||||
<3300> <33ff> <3300>
|
||||
<3400> <34ff> <3400>
|
||||
<3500> <35ff> <3500>
|
||||
<3600> <36ff> <3600>
|
||||
<3700> <37ff> <3700>
|
||||
<3800> <38ff> <3800>
|
||||
<3900> <39ff> <3900>
|
||||
<3a00> <3aff> <3a00>
|
||||
<3b00> <3bff> <3b00>
|
||||
<3c00> <3cff> <3c00>
|
||||
<3d00> <3dff> <3d00>
|
||||
<3e00> <3eff> <3e00>
|
||||
<3f00> <3fff> <3f00>
|
||||
<4000> <40ff> <4000>
|
||||
<4100> <41ff> <4100>
|
||||
<4200> <42ff> <4200>
|
||||
<4300> <43ff> <4300>
|
||||
<4400> <44ff> <4400>
|
||||
<4500> <45ff> <4500>
|
||||
<4600> <46ff> <4600>
|
||||
<4700> <47ff> <4700>
|
||||
<4800> <48ff> <4800>
|
||||
<4900> <49ff> <4900>
|
||||
<4a00> <4aff> <4a00>
|
||||
<4b00> <4bff> <4b00>
|
||||
<4c00> <4cff> <4c00>
|
||||
<4d00> <4dff> <4d00>
|
||||
<4e00> <4eff> <4e00>
|
||||
<4f00> <4fff> <4f00>
|
||||
<5000> <50ff> <5000>
|
||||
<5100> <51ff> <5100>
|
||||
<5200> <52ff> <5200>
|
||||
<5300> <53ff> <5300>
|
||||
<5400> <54ff> <5400>
|
||||
<5500> <55ff> <5500>
|
||||
<5600> <56ff> <5600>
|
||||
<5700> <57ff> <5700>
|
||||
<5800> <58ff> <5800>
|
||||
<5900> <59ff> <5900>
|
||||
<5a00> <5aff> <5a00>
|
||||
<5b00> <5bff> <5b00>
|
||||
<5c00> <5cff> <5c00>
|
||||
<5d00> <5dff> <5d00>
|
||||
<5e00> <5eff> <5e00>
|
||||
<5f00> <5fff> <5f00>
|
||||
<6000> <60ff> <6000>
|
||||
<6100> <61ff> <6100>
|
||||
<6200> <62ff> <6200>
|
||||
<6300> <63ff> <6300>
|
||||
endbfrange
|
||||
100 beginbfrange
|
||||
<6400> <64ff> <6400>
|
||||
<6500> <65ff> <6500>
|
||||
<6600> <66ff> <6600>
|
||||
<6700> <67ff> <6700>
|
||||
<6800> <68ff> <6800>
|
||||
<6900> <69ff> <6900>
|
||||
<6a00> <6aff> <6a00>
|
||||
<6b00> <6bff> <6b00>
|
||||
<6c00> <6cff> <6c00>
|
||||
<6d00> <6dff> <6d00>
|
||||
<6e00> <6eff> <6e00>
|
||||
<6f00> <6fff> <6f00>
|
||||
<7000> <70ff> <7000>
|
||||
<7100> <71ff> <7100>
|
||||
<7200> <72ff> <7200>
|
||||
<7300> <73ff> <7300>
|
||||
<7400> <74ff> <7400>
|
||||
<7500> <75ff> <7500>
|
||||
<7600> <76ff> <7600>
|
||||
<7700> <77ff> <7700>
|
||||
<7800> <78ff> <7800>
|
||||
<7900> <79ff> <7900>
|
||||
<7a00> <7aff> <7a00>
|
||||
<7b00> <7bff> <7b00>
|
||||
<7c00> <7cff> <7c00>
|
||||
<7d00> <7dff> <7d00>
|
||||
<7e00> <7eff> <7e00>
|
||||
<7f00> <7fff> <7f00>
|
||||
<8000> <80ff> <8000>
|
||||
<8100> <81ff> <8100>
|
||||
<8200> <82ff> <8200>
|
||||
<8300> <83ff> <8300>
|
||||
<8400> <84ff> <8400>
|
||||
<8500> <85ff> <8500>
|
||||
<8600> <86ff> <8600>
|
||||
<8700> <87ff> <8700>
|
||||
<8800> <88ff> <8800>
|
||||
<8900> <89ff> <8900>
|
||||
<8a00> <8aff> <8a00>
|
||||
<8b00> <8bff> <8b00>
|
||||
<8c00> <8cff> <8c00>
|
||||
<8d00> <8dff> <8d00>
|
||||
<8e00> <8eff> <8e00>
|
||||
<8f00> <8fff> <8f00>
|
||||
<9000> <90ff> <9000>
|
||||
<9100> <91ff> <9100>
|
||||
<9200> <92ff> <9200>
|
||||
<9300> <93ff> <9300>
|
||||
<9400> <94ff> <9400>
|
||||
<9500> <95ff> <9500>
|
||||
<9600> <96ff> <9600>
|
||||
<9700> <97ff> <9700>
|
||||
<9800> <98ff> <9800>
|
||||
<9900> <99ff> <9900>
|
||||
<9a00> <9aff> <9a00>
|
||||
<9b00> <9bff> <9b00>
|
||||
<9c00> <9cff> <9c00>
|
||||
<9d00> <9dff> <9d00>
|
||||
<9e00> <9eff> <9e00>
|
||||
<9f00> <9fff> <9f00>
|
||||
<a000> <a0ff> <a000>
|
||||
<a100> <a1ff> <a100>
|
||||
<a200> <a2ff> <a200>
|
||||
<a300> <a3ff> <a300>
|
||||
<a400> <a4ff> <a400>
|
||||
<a500> <a5ff> <a500>
|
||||
<a600> <a6ff> <a600>
|
||||
<a700> <a7ff> <a700>
|
||||
<a800> <a8ff> <a800>
|
||||
<a900> <a9ff> <a900>
|
||||
<aa00> <aaff> <aa00>
|
||||
<ab00> <abff> <ab00>
|
||||
<ac00> <acff> <ac00>
|
||||
<ad00> <adff> <ad00>
|
||||
<ae00> <aeff> <ae00>
|
||||
<af00> <afff> <af00>
|
||||
<b000> <b0ff> <b000>
|
||||
<b100> <b1ff> <b100>
|
||||
<b200> <b2ff> <b200>
|
||||
<b300> <b3ff> <b300>
|
||||
<b400> <b4ff> <b400>
|
||||
<b500> <b5ff> <b500>
|
||||
<b600> <b6ff> <b600>
|
||||
<b700> <b7ff> <b700>
|
||||
<b800> <b8ff> <b800>
|
||||
<b900> <b9ff> <b900>
|
||||
<ba00> <baff> <ba00>
|
||||
<bb00> <bbff> <bb00>
|
||||
<bc00> <bcff> <bc00>
|
||||
<bd00> <bdff> <bd00>
|
||||
<be00> <beff> <be00>
|
||||
<bf00> <bfff> <bf00>
|
||||
<c000> <c0ff> <c000>
|
||||
<c100> <c1ff> <c100>
|
||||
<c200> <c2ff> <c200>
|
||||
<c300> <c3ff> <c300>
|
||||
<c400> <c4ff> <c400>
|
||||
<c500> <c5ff> <c500>
|
||||
<c600> <c6ff> <c600>
|
||||
<c700> <c7ff> <c700>
|
||||
endbfrange
|
||||
56 beginbfrange
|
||||
<c800> <c8ff> <c800>
|
||||
<c900> <c9ff> <c900>
|
||||
<ca00> <caff> <ca00>
|
||||
<cb00> <cbff> <cb00>
|
||||
<cc00> <ccff> <cc00>
|
||||
<cd00> <cdff> <cd00>
|
||||
<ce00> <ceff> <ce00>
|
||||
<cf00> <cfff> <cf00>
|
||||
<d000> <d0ff> <d000>
|
||||
<d100> <d1ff> <d100>
|
||||
<d200> <d2ff> <d200>
|
||||
<d300> <d3ff> <d300>
|
||||
<d400> <d4ff> <d400>
|
||||
<d500> <d5ff> <d500>
|
||||
<d600> <d6ff> <d600>
|
||||
<d700> <d7ff> <d700>
|
||||
<d800> <d8ff> <d800>
|
||||
<d900> <d9ff> <d900>
|
||||
<da00> <daff> <da00>
|
||||
<db00> <dbff> <db00>
|
||||
<dc00> <dcff> <dc00>
|
||||
<dd00> <ddff> <dd00>
|
||||
<de00> <deff> <de00>
|
||||
<df00> <dfff> <df00>
|
||||
<e000> <e0ff> <e000>
|
||||
<e100> <e1ff> <e100>
|
||||
<e200> <e2ff> <e200>
|
||||
<e300> <e3ff> <e300>
|
||||
<e400> <e4ff> <e400>
|
||||
<e500> <e5ff> <e500>
|
||||
<e600> <e6ff> <e600>
|
||||
<e700> <e7ff> <e700>
|
||||
<e800> <e8ff> <e800>
|
||||
<e900> <e9ff> <e900>
|
||||
<ea00> <eaff> <ea00>
|
||||
<eb00> <ebff> <eb00>
|
||||
<ec00> <ecff> <ec00>
|
||||
<ed00> <edff> <ed00>
|
||||
<ee00> <eeff> <ee00>
|
||||
<ef00> <efff> <ef00>
|
||||
<f000> <f0ff> <f000>
|
||||
<f100> <f1ff> <f100>
|
||||
<f200> <f2ff> <f200>
|
||||
<f300> <f3ff> <f300>
|
||||
<f400> <f4ff> <f400>
|
||||
<f500> <f5ff> <f500>
|
||||
<f600> <f6ff> <f600>
|
||||
<f700> <f7ff> <f700>
|
||||
<f800> <f8ff> <f800>
|
||||
<f900> <f9ff> <f900>
|
||||
<fa00> <faff> <fa00>
|
||||
<fb00> <fbff> <fb00>
|
||||
<fc00> <fcff> <fc00>
|
||||
<fd00> <fdff> <fd00>
|
||||
<fe00> <feff> <fe00>
|
||||
<ff00> <ffff> <ff00>
|
||||
endbfrange
|
||||
endcmap
|
||||
CMapName currentdict /CMap defineresource pop
|
||||
end
|
||||
end
|
||||
EOD;
|
||||
}
|
||||
@@ -0,0 +1,68 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
/**
|
||||
* Latin.php
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*
|
||||
* This file is part of tc-lib-unicode-data software library.
|
||||
*/
|
||||
|
||||
namespace Com\Tecnick\Unicode\Data;
|
||||
|
||||
/**
|
||||
* Com\Tecnick\Unicode\Data\Latin
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*/
|
||||
class Latin
|
||||
{
|
||||
/**
|
||||
* Array of character substitutions from UTF-8 Unicode to Latin1.
|
||||
*
|
||||
* @var array<int, int>
|
||||
*/
|
||||
public const SUBSTITUTE = [
|
||||
8364 => 128, // Euro1
|
||||
338 => 140, // OE
|
||||
352 => 138, // Scaron
|
||||
376 => 159, // Ydieresis
|
||||
381 => 142, // Zcaron2
|
||||
8226 => 149, // bullet3
|
||||
710 => 136, // circumflex
|
||||
8224 => 134, // dagger
|
||||
8225 => 135, // daggerdbl
|
||||
8230 => 133, // ellipsis
|
||||
8212 => 151, // emdash
|
||||
8211 => 150, // endash
|
||||
402 => 131, // florin
|
||||
8249 => 139, // guilsinglleft
|
||||
8250 => 155, // guilsinglright
|
||||
339 => 156, // oe
|
||||
8240 => 137, // perthousand
|
||||
8222 => 132, // quotedblbase
|
||||
8220 => 147, // quotedblleft
|
||||
8221 => 148, // quotedblright
|
||||
8216 => 145, // quoteleft
|
||||
8217 => 146, // quoteright
|
||||
8218 => 130, // quotesinglbase
|
||||
353 => 154, // scaron
|
||||
732 => 152, // tilde
|
||||
8482 => 153, // trademark
|
||||
382 => 158, // zcaron2
|
||||
];
|
||||
}
|
||||
@@ -0,0 +1,476 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
/**
|
||||
* Mirror.php
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*
|
||||
* This file is part of tc-lib-unicode-data software library.
|
||||
*/
|
||||
|
||||
namespace Com\Tecnick\Unicode\Data;
|
||||
|
||||
/**
|
||||
* Com\Tecnick\Unicode\Data\Mirror
|
||||
*
|
||||
* Bidi_Mirroring_Glyph property values (BidiMirroring.txt).
|
||||
*
|
||||
* Generated by tools/generate.php from the Unicode Character Database 17.0.0.
|
||||
* Do not edit manually.
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*/
|
||||
|
||||
class Mirror
|
||||
{
|
||||
/**
|
||||
* Mirrored form of the characters that are mirrored when displayed in a
|
||||
* right-to-left context (rule L4 of UAX #9).
|
||||
*
|
||||
* @var array<int, int>
|
||||
*/
|
||||
public const UNI = [
|
||||
0x0028 => 0x0029,
|
||||
0x0029 => 0x0028,
|
||||
0x003C => 0x003E,
|
||||
0x003E => 0x003C,
|
||||
0x005B => 0x005D,
|
||||
0x005D => 0x005B,
|
||||
0x007B => 0x007D,
|
||||
0x007D => 0x007B,
|
||||
0x00AB => 0x00BB,
|
||||
0x00BB => 0x00AB,
|
||||
0x0F3A => 0x0F3B,
|
||||
0x0F3B => 0x0F3A,
|
||||
0x0F3C => 0x0F3D,
|
||||
0x0F3D => 0x0F3C,
|
||||
0x169B => 0x169C,
|
||||
0x169C => 0x169B,
|
||||
0x2039 => 0x203A,
|
||||
0x203A => 0x2039,
|
||||
0x2045 => 0x2046,
|
||||
0x2046 => 0x2045,
|
||||
0x207D => 0x207E,
|
||||
0x207E => 0x207D,
|
||||
0x208D => 0x208E,
|
||||
0x208E => 0x208D,
|
||||
0x2208 => 0x220B,
|
||||
0x2209 => 0x220C,
|
||||
0x220A => 0x220D,
|
||||
0x220B => 0x2208,
|
||||
0x220C => 0x2209,
|
||||
0x220D => 0x220A,
|
||||
0x2215 => 0x29F5,
|
||||
0x221F => 0x2BFE,
|
||||
0x2220 => 0x29A3,
|
||||
0x2221 => 0x299B,
|
||||
0x2222 => 0x29A0,
|
||||
0x2224 => 0x2AEE,
|
||||
0x223C => 0x223D,
|
||||
0x223D => 0x223C,
|
||||
0x2243 => 0x22CD,
|
||||
0x2245 => 0x224C,
|
||||
0x224C => 0x2245,
|
||||
0x2252 => 0x2253,
|
||||
0x2253 => 0x2252,
|
||||
0x2254 => 0x2255,
|
||||
0x2255 => 0x2254,
|
||||
0x2264 => 0x2265,
|
||||
0x2265 => 0x2264,
|
||||
0x2266 => 0x2267,
|
||||
0x2267 => 0x2266,
|
||||
0x2268 => 0x2269,
|
||||
0x2269 => 0x2268,
|
||||
0x226A => 0x226B,
|
||||
0x226B => 0x226A,
|
||||
0x226E => 0x226F,
|
||||
0x226F => 0x226E,
|
||||
0x2270 => 0x2271,
|
||||
0x2271 => 0x2270,
|
||||
0x2272 => 0x2273,
|
||||
0x2273 => 0x2272,
|
||||
0x2274 => 0x2275,
|
||||
0x2275 => 0x2274,
|
||||
0x2276 => 0x2277,
|
||||
0x2277 => 0x2276,
|
||||
0x2278 => 0x2279,
|
||||
0x2279 => 0x2278,
|
||||
0x227A => 0x227B,
|
||||
0x227B => 0x227A,
|
||||
0x227C => 0x227D,
|
||||
0x227D => 0x227C,
|
||||
0x227E => 0x227F,
|
||||
0x227F => 0x227E,
|
||||
0x2280 => 0x2281,
|
||||
0x2281 => 0x2280,
|
||||
0x2282 => 0x2283,
|
||||
0x2283 => 0x2282,
|
||||
0x2284 => 0x2285,
|
||||
0x2285 => 0x2284,
|
||||
0x2286 => 0x2287,
|
||||
0x2287 => 0x2286,
|
||||
0x2288 => 0x2289,
|
||||
0x2289 => 0x2288,
|
||||
0x228A => 0x228B,
|
||||
0x228B => 0x228A,
|
||||
0x228F => 0x2290,
|
||||
0x2290 => 0x228F,
|
||||
0x2291 => 0x2292,
|
||||
0x2292 => 0x2291,
|
||||
0x2298 => 0x29B8,
|
||||
0x22A2 => 0x22A3,
|
||||
0x22A3 => 0x22A2,
|
||||
0x22A6 => 0x2ADE,
|
||||
0x22A8 => 0x2AE4,
|
||||
0x22A9 => 0x2AE3,
|
||||
0x22AB => 0x2AE5,
|
||||
0x22B0 => 0x22B1,
|
||||
0x22B1 => 0x22B0,
|
||||
0x22B2 => 0x22B3,
|
||||
0x22B3 => 0x22B2,
|
||||
0x22B4 => 0x22B5,
|
||||
0x22B5 => 0x22B4,
|
||||
0x22B6 => 0x22B7,
|
||||
0x22B7 => 0x22B6,
|
||||
0x22B8 => 0x27DC,
|
||||
0x22C9 => 0x22CA,
|
||||
0x22CA => 0x22C9,
|
||||
0x22CB => 0x22CC,
|
||||
0x22CC => 0x22CB,
|
||||
0x22CD => 0x2243,
|
||||
0x22D0 => 0x22D1,
|
||||
0x22D1 => 0x22D0,
|
||||
0x22D6 => 0x22D7,
|
||||
0x22D7 => 0x22D6,
|
||||
0x22D8 => 0x22D9,
|
||||
0x22D9 => 0x22D8,
|
||||
0x22DA => 0x22DB,
|
||||
0x22DB => 0x22DA,
|
||||
0x22DC => 0x22DD,
|
||||
0x22DD => 0x22DC,
|
||||
0x22DE => 0x22DF,
|
||||
0x22DF => 0x22DE,
|
||||
0x22E0 => 0x22E1,
|
||||
0x22E1 => 0x22E0,
|
||||
0x22E2 => 0x22E3,
|
||||
0x22E3 => 0x22E2,
|
||||
0x22E4 => 0x22E5,
|
||||
0x22E5 => 0x22E4,
|
||||
0x22E6 => 0x22E7,
|
||||
0x22E7 => 0x22E6,
|
||||
0x22E8 => 0x22E9,
|
||||
0x22E9 => 0x22E8,
|
||||
0x22EA => 0x22EB,
|
||||
0x22EB => 0x22EA,
|
||||
0x22EC => 0x22ED,
|
||||
0x22ED => 0x22EC,
|
||||
0x22F0 => 0x22F1,
|
||||
0x22F1 => 0x22F0,
|
||||
0x22F2 => 0x22FA,
|
||||
0x22F3 => 0x22FB,
|
||||
0x22F4 => 0x22FC,
|
||||
0x22F6 => 0x22FD,
|
||||
0x22F7 => 0x22FE,
|
||||
0x22FA => 0x22F2,
|
||||
0x22FB => 0x22F3,
|
||||
0x22FC => 0x22F4,
|
||||
0x22FD => 0x22F6,
|
||||
0x22FE => 0x22F7,
|
||||
0x2308 => 0x2309,
|
||||
0x2309 => 0x2308,
|
||||
0x230A => 0x230B,
|
||||
0x230B => 0x230A,
|
||||
0x2329 => 0x232A,
|
||||
0x232A => 0x2329,
|
||||
0x2768 => 0x2769,
|
||||
0x2769 => 0x2768,
|
||||
0x276A => 0x276B,
|
||||
0x276B => 0x276A,
|
||||
0x276C => 0x276D,
|
||||
0x276D => 0x276C,
|
||||
0x276E => 0x276F,
|
||||
0x276F => 0x276E,
|
||||
0x2770 => 0x2771,
|
||||
0x2771 => 0x2770,
|
||||
0x2772 => 0x2773,
|
||||
0x2773 => 0x2772,
|
||||
0x2774 => 0x2775,
|
||||
0x2775 => 0x2774,
|
||||
0x27C3 => 0x27C4,
|
||||
0x27C4 => 0x27C3,
|
||||
0x27C5 => 0x27C6,
|
||||
0x27C6 => 0x27C5,
|
||||
0x27C8 => 0x27C9,
|
||||
0x27C9 => 0x27C8,
|
||||
0x27CB => 0x27CD,
|
||||
0x27CD => 0x27CB,
|
||||
0x27D5 => 0x27D6,
|
||||
0x27D6 => 0x27D5,
|
||||
0x27DC => 0x22B8,
|
||||
0x27DD => 0x27DE,
|
||||
0x27DE => 0x27DD,
|
||||
0x27E2 => 0x27E3,
|
||||
0x27E3 => 0x27E2,
|
||||
0x27E4 => 0x27E5,
|
||||
0x27E5 => 0x27E4,
|
||||
0x27E6 => 0x27E7,
|
||||
0x27E7 => 0x27E6,
|
||||
0x27E8 => 0x27E9,
|
||||
0x27E9 => 0x27E8,
|
||||
0x27EA => 0x27EB,
|
||||
0x27EB => 0x27EA,
|
||||
0x27EC => 0x27ED,
|
||||
0x27ED => 0x27EC,
|
||||
0x27EE => 0x27EF,
|
||||
0x27EF => 0x27EE,
|
||||
0x2983 => 0x2984,
|
||||
0x2984 => 0x2983,
|
||||
0x2985 => 0x2986,
|
||||
0x2986 => 0x2985,
|
||||
0x2987 => 0x2988,
|
||||
0x2988 => 0x2987,
|
||||
0x2989 => 0x298A,
|
||||
0x298A => 0x2989,
|
||||
0x298B => 0x298C,
|
||||
0x298C => 0x298B,
|
||||
0x298D => 0x2990,
|
||||
0x298E => 0x298F,
|
||||
0x298F => 0x298E,
|
||||
0x2990 => 0x298D,
|
||||
0x2991 => 0x2992,
|
||||
0x2992 => 0x2991,
|
||||
0x2993 => 0x2994,
|
||||
0x2994 => 0x2993,
|
||||
0x2995 => 0x2996,
|
||||
0x2996 => 0x2995,
|
||||
0x2997 => 0x2998,
|
||||
0x2998 => 0x2997,
|
||||
0x299B => 0x2221,
|
||||
0x29A0 => 0x2222,
|
||||
0x29A3 => 0x2220,
|
||||
0x29A4 => 0x29A5,
|
||||
0x29A5 => 0x29A4,
|
||||
0x29A8 => 0x29A9,
|
||||
0x29A9 => 0x29A8,
|
||||
0x29AA => 0x29AB,
|
||||
0x29AB => 0x29AA,
|
||||
0x29AC => 0x29AD,
|
||||
0x29AD => 0x29AC,
|
||||
0x29AE => 0x29AF,
|
||||
0x29AF => 0x29AE,
|
||||
0x29B8 => 0x2298,
|
||||
0x29C0 => 0x29C1,
|
||||
0x29C1 => 0x29C0,
|
||||
0x29C4 => 0x29C5,
|
||||
0x29C5 => 0x29C4,
|
||||
0x29CF => 0x29D0,
|
||||
0x29D0 => 0x29CF,
|
||||
0x29D1 => 0x29D2,
|
||||
0x29D2 => 0x29D1,
|
||||
0x29D4 => 0x29D5,
|
||||
0x29D5 => 0x29D4,
|
||||
0x29D8 => 0x29D9,
|
||||
0x29D9 => 0x29D8,
|
||||
0x29DA => 0x29DB,
|
||||
0x29DB => 0x29DA,
|
||||
0x29E8 => 0x29E9,
|
||||
0x29E9 => 0x29E8,
|
||||
0x29F5 => 0x2215,
|
||||
0x29F8 => 0x29F9,
|
||||
0x29F9 => 0x29F8,
|
||||
0x29FC => 0x29FD,
|
||||
0x29FD => 0x29FC,
|
||||
0x2A2B => 0x2A2C,
|
||||
0x2A2C => 0x2A2B,
|
||||
0x2A2D => 0x2A2E,
|
||||
0x2A2E => 0x2A2D,
|
||||
0x2A34 => 0x2A35,
|
||||
0x2A35 => 0x2A34,
|
||||
0x2A3C => 0x2A3D,
|
||||
0x2A3D => 0x2A3C,
|
||||
0x2A64 => 0x2A65,
|
||||
0x2A65 => 0x2A64,
|
||||
0x2A79 => 0x2A7A,
|
||||
0x2A7A => 0x2A79,
|
||||
0x2A7B => 0x2A7C,
|
||||
0x2A7C => 0x2A7B,
|
||||
0x2A7D => 0x2A7E,
|
||||
0x2A7E => 0x2A7D,
|
||||
0x2A7F => 0x2A80,
|
||||
0x2A80 => 0x2A7F,
|
||||
0x2A81 => 0x2A82,
|
||||
0x2A82 => 0x2A81,
|
||||
0x2A83 => 0x2A84,
|
||||
0x2A84 => 0x2A83,
|
||||
0x2A85 => 0x2A86,
|
||||
0x2A86 => 0x2A85,
|
||||
0x2A87 => 0x2A88,
|
||||
0x2A88 => 0x2A87,
|
||||
0x2A89 => 0x2A8A,
|
||||
0x2A8A => 0x2A89,
|
||||
0x2A8B => 0x2A8C,
|
||||
0x2A8C => 0x2A8B,
|
||||
0x2A8D => 0x2A8E,
|
||||
0x2A8E => 0x2A8D,
|
||||
0x2A8F => 0x2A90,
|
||||
0x2A90 => 0x2A8F,
|
||||
0x2A91 => 0x2A92,
|
||||
0x2A92 => 0x2A91,
|
||||
0x2A93 => 0x2A94,
|
||||
0x2A94 => 0x2A93,
|
||||
0x2A95 => 0x2A96,
|
||||
0x2A96 => 0x2A95,
|
||||
0x2A97 => 0x2A98,
|
||||
0x2A98 => 0x2A97,
|
||||
0x2A99 => 0x2A9A,
|
||||
0x2A9A => 0x2A99,
|
||||
0x2A9B => 0x2A9C,
|
||||
0x2A9C => 0x2A9B,
|
||||
0x2A9D => 0x2A9E,
|
||||
0x2A9E => 0x2A9D,
|
||||
0x2A9F => 0x2AA0,
|
||||
0x2AA0 => 0x2A9F,
|
||||
0x2AA1 => 0x2AA2,
|
||||
0x2AA2 => 0x2AA1,
|
||||
0x2AA6 => 0x2AA7,
|
||||
0x2AA7 => 0x2AA6,
|
||||
0x2AA8 => 0x2AA9,
|
||||
0x2AA9 => 0x2AA8,
|
||||
0x2AAA => 0x2AAB,
|
||||
0x2AAB => 0x2AAA,
|
||||
0x2AAC => 0x2AAD,
|
||||
0x2AAD => 0x2AAC,
|
||||
0x2AAF => 0x2AB0,
|
||||
0x2AB0 => 0x2AAF,
|
||||
0x2AB1 => 0x2AB2,
|
||||
0x2AB2 => 0x2AB1,
|
||||
0x2AB3 => 0x2AB4,
|
||||
0x2AB4 => 0x2AB3,
|
||||
0x2AB5 => 0x2AB6,
|
||||
0x2AB6 => 0x2AB5,
|
||||
0x2AB7 => 0x2AB8,
|
||||
0x2AB8 => 0x2AB7,
|
||||
0x2AB9 => 0x2ABA,
|
||||
0x2ABA => 0x2AB9,
|
||||
0x2ABB => 0x2ABC,
|
||||
0x2ABC => 0x2ABB,
|
||||
0x2ABD => 0x2ABE,
|
||||
0x2ABE => 0x2ABD,
|
||||
0x2ABF => 0x2AC0,
|
||||
0x2AC0 => 0x2ABF,
|
||||
0x2AC1 => 0x2AC2,
|
||||
0x2AC2 => 0x2AC1,
|
||||
0x2AC3 => 0x2AC4,
|
||||
0x2AC4 => 0x2AC3,
|
||||
0x2AC5 => 0x2AC6,
|
||||
0x2AC6 => 0x2AC5,
|
||||
0x2AC7 => 0x2AC8,
|
||||
0x2AC8 => 0x2AC7,
|
||||
0x2AC9 => 0x2ACA,
|
||||
0x2ACA => 0x2AC9,
|
||||
0x2ACB => 0x2ACC,
|
||||
0x2ACC => 0x2ACB,
|
||||
0x2ACD => 0x2ACE,
|
||||
0x2ACE => 0x2ACD,
|
||||
0x2ACF => 0x2AD0,
|
||||
0x2AD0 => 0x2ACF,
|
||||
0x2AD1 => 0x2AD2,
|
||||
0x2AD2 => 0x2AD1,
|
||||
0x2AD3 => 0x2AD4,
|
||||
0x2AD4 => 0x2AD3,
|
||||
0x2AD5 => 0x2AD6,
|
||||
0x2AD6 => 0x2AD5,
|
||||
0x2ADE => 0x22A6,
|
||||
0x2AE3 => 0x22A9,
|
||||
0x2AE4 => 0x22A8,
|
||||
0x2AE5 => 0x22AB,
|
||||
0x2AEC => 0x2AED,
|
||||
0x2AED => 0x2AEC,
|
||||
0x2AEE => 0x2224,
|
||||
0x2AF7 => 0x2AF8,
|
||||
0x2AF8 => 0x2AF7,
|
||||
0x2AF9 => 0x2AFA,
|
||||
0x2AFA => 0x2AF9,
|
||||
0x2BFE => 0x221F,
|
||||
0x2E02 => 0x2E03,
|
||||
0x2E03 => 0x2E02,
|
||||
0x2E04 => 0x2E05,
|
||||
0x2E05 => 0x2E04,
|
||||
0x2E09 => 0x2E0A,
|
||||
0x2E0A => 0x2E09,
|
||||
0x2E0C => 0x2E0D,
|
||||
0x2E0D => 0x2E0C,
|
||||
0x2E1C => 0x2E1D,
|
||||
0x2E1D => 0x2E1C,
|
||||
0x2E20 => 0x2E21,
|
||||
0x2E21 => 0x2E20,
|
||||
0x2E22 => 0x2E23,
|
||||
0x2E23 => 0x2E22,
|
||||
0x2E24 => 0x2E25,
|
||||
0x2E25 => 0x2E24,
|
||||
0x2E26 => 0x2E27,
|
||||
0x2E27 => 0x2E26,
|
||||
0x2E28 => 0x2E29,
|
||||
0x2E29 => 0x2E28,
|
||||
0x2E55 => 0x2E56,
|
||||
0x2E56 => 0x2E55,
|
||||
0x2E57 => 0x2E58,
|
||||
0x2E58 => 0x2E57,
|
||||
0x2E59 => 0x2E5A,
|
||||
0x2E5A => 0x2E59,
|
||||
0x2E5B => 0x2E5C,
|
||||
0x2E5C => 0x2E5B,
|
||||
0x3008 => 0x3009,
|
||||
0x3009 => 0x3008,
|
||||
0x300A => 0x300B,
|
||||
0x300B => 0x300A,
|
||||
0x300C => 0x300D,
|
||||
0x300D => 0x300C,
|
||||
0x300E => 0x300F,
|
||||
0x300F => 0x300E,
|
||||
0x3010 => 0x3011,
|
||||
0x3011 => 0x3010,
|
||||
0x3014 => 0x3015,
|
||||
0x3015 => 0x3014,
|
||||
0x3016 => 0x3017,
|
||||
0x3017 => 0x3016,
|
||||
0x3018 => 0x3019,
|
||||
0x3019 => 0x3018,
|
||||
0x301A => 0x301B,
|
||||
0x301B => 0x301A,
|
||||
0xFE59 => 0xFE5A,
|
||||
0xFE5A => 0xFE59,
|
||||
0xFE5B => 0xFE5C,
|
||||
0xFE5C => 0xFE5B,
|
||||
0xFE5D => 0xFE5E,
|
||||
0xFE5E => 0xFE5D,
|
||||
0xFE64 => 0xFE65,
|
||||
0xFE65 => 0xFE64,
|
||||
0xFF08 => 0xFF09,
|
||||
0xFF09 => 0xFF08,
|
||||
0xFF1C => 0xFF1E,
|
||||
0xFF1E => 0xFF1C,
|
||||
0xFF3B => 0xFF3D,
|
||||
0xFF3D => 0xFF3B,
|
||||
0xFF5B => 0xFF5D,
|
||||
0xFF5D => 0xFF5B,
|
||||
0xFF5F => 0xFF60,
|
||||
0xFF60 => 0xFF5F,
|
||||
0xFF62 => 0xFF63,
|
||||
0xFF63 => 0xFF62,
|
||||
];
|
||||
}
|
||||
@@ -0,0 +1,86 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
/**
|
||||
* Pattern.php
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*
|
||||
* This file is part of tc-lib-unicode-data software library.
|
||||
*/
|
||||
|
||||
namespace Com\Tecnick\Unicode\Data;
|
||||
|
||||
/**
|
||||
* Com\Tecnick\Unicode\Data\Pattern
|
||||
*
|
||||
* Regular expressions matching directional text.
|
||||
*
|
||||
* Generated by tools/generate.php from the Unicode Character Database 17.0.0.
|
||||
* Do not edit manually.
|
||||
*
|
||||
* @since 2011-05-23
|
||||
* @category Library
|
||||
* @package UnicodeData
|
||||
* @author Nicola Asuni <info@tecnick.com>
|
||||
* @copyright 2011-2026 Nicola Asuni - Tecnick.com LTD
|
||||
* @license https://www.gnu.org/copyleft/lesser.html GNU-LGPL v3 (see LICENSE)
|
||||
* @link https://github.com/tecnickcom/tc-lib-unicode-data
|
||||
*/
|
||||
|
||||
class Pattern
|
||||
{
|
||||
/**
|
||||
* Pattern matching the strong right-to-left characters (Bidi_Class=R) and the
|
||||
* right-to-left explicit formatting characters (RLE, RLO, RLI).
|
||||
* Arabic characters are matched by the ARABIC pattern instead.
|
||||
* The subject string must be valid UTF-8.
|
||||
*/
|
||||
public const RTL =
|
||||
'/['
|
||||
. '\x{05BE}\x{05C0}\x{05C3}\x{05C6}\x{05D0}-\x{05EA}\x{05EF}-\x{05F4}\x{07C0}-\x{07EA}'
|
||||
. '\x{07F4}\x{07F5}\x{07FA}\x{07FE}-\x{0815}\x{081A}\x{0824}\x{0828}\x{0830}-\x{083E}'
|
||||
. '\x{0840}-\x{0858}\x{085E}\x{200F}\x{202B}\x{202E}\x{2067}\x{FB1D}\x{FB1F}-\x{FB28}'
|
||||
. '\x{FB2A}-\x{FB36}\x{FB38}-\x{FB3C}\x{FB3E}\x{FB40}\x{FB41}\x{FB43}\x{FB44}\x{FB46}-\x{FB4F}'
|
||||
. '\x{10800}-\x{10805}\x{10808}\x{1080A}-\x{10835}\x{10837}\x{10838}\x{1083C}'
|
||||
. '\x{1083F}-\x{10855}\x{10857}-\x{1089E}\x{108A7}-\x{108AF}\x{108E0}-\x{108F2}'
|
||||
. '\x{108F4}\x{108F5}\x{108FB}-\x{1091B}\x{10920}-\x{10939}\x{1093F}-\x{10959}'
|
||||
. '\x{10980}-\x{109B7}\x{109BC}-\x{109CF}\x{109D2}-\x{10A00}\x{10A10}-\x{10A13}'
|
||||
. '\x{10A15}-\x{10A17}\x{10A19}-\x{10A35}\x{10A40}-\x{10A48}\x{10A50}-\x{10A58}'
|
||||
. '\x{10A60}-\x{10A9F}\x{10AC0}-\x{10AE4}\x{10AEB}-\x{10AF6}\x{10B00}-\x{10B35}'
|
||||
. '\x{10B40}-\x{10B55}\x{10B58}-\x{10B72}\x{10B78}-\x{10B91}\x{10B99}-\x{10B9C}'
|
||||
. '\x{10BA9}-\x{10BAF}\x{10C00}-\x{10C48}\x{10C80}-\x{10CB2}\x{10CC0}-\x{10CF2}'
|
||||
. '\x{10CFA}-\x{10CFF}\x{10D4A}-\x{10D65}\x{10D6F}-\x{10D85}\x{10D8E}\x{10D8F}'
|
||||
. '\x{10E80}-\x{10EA9}\x{10EAD}\x{10EB0}\x{10EB1}\x{10F00}-\x{10F27}\x{10F70}-\x{10F81}'
|
||||
. '\x{10F86}-\x{10F89}\x{10FB0}-\x{10FCB}\x{10FE0}-\x{10FF6}\x{1E800}-\x{1E8C4}'
|
||||
. '\x{1E8C7}-\x{1E8CF}\x{1E900}-\x{1E943}\x{1E94B}\x{1E950}-\x{1E959}\x{1E95E}\x{1E95F}'
|
||||
. ']/u';
|
||||
|
||||
/**
|
||||
* Pattern matching the Arabic characters (Bidi_Class=AL and Bidi_Class=AN).
|
||||
* The subject string must be valid UTF-8.
|
||||
*/
|
||||
public const ARABIC =
|
||||
'/['
|
||||
. '\x{0600}-\x{0605}\x{0608}\x{060B}\x{060D}\x{061B}-\x{064A}\x{0660}-\x{0669}\x{066B}-\x{066F}'
|
||||
. '\x{0671}-\x{06D5}\x{06DD}\x{06E5}\x{06E6}\x{06EE}\x{06EF}\x{06FA}-\x{070D}\x{070F}\x{0710}'
|
||||
. '\x{0712}-\x{072F}\x{074D}-\x{07A5}\x{07B1}\x{0860}-\x{086A}\x{0870}-\x{0891}'
|
||||
. '\x{08A0}-\x{08C9}\x{08E2}\x{FB50}-\x{FBC2}\x{FBD3}-\x{FD3D}\x{FD50}-\x{FD8F}'
|
||||
. '\x{FD92}-\x{FDC7}\x{FDF0}-\x{FDFC}\x{FE70}-\x{FE74}\x{FE76}-\x{FEFC}\x{10D00}-\x{10D23}'
|
||||
. '\x{10D30}-\x{10D39}\x{10D40}-\x{10D49}\x{10E60}-\x{10E7E}\x{10EC2}-\x{10EC7}'
|
||||
. '\x{10F30}-\x{10F45}\x{10F51}-\x{10F59}\x{1EC71}-\x{1ECB4}\x{1ED01}-\x{1ED3D}'
|
||||
. '\x{1EE00}-\x{1EE03}\x{1EE05}-\x{1EE1F}\x{1EE21}\x{1EE22}\x{1EE24}\x{1EE27}'
|
||||
. '\x{1EE29}-\x{1EE32}\x{1EE34}-\x{1EE37}\x{1EE39}\x{1EE3B}\x{1EE42}\x{1EE47}\x{1EE49}\x{1EE4B}'
|
||||
. '\x{1EE4D}-\x{1EE4F}\x{1EE51}\x{1EE52}\x{1EE54}\x{1EE57}\x{1EE59}\x{1EE5B}\x{1EE5D}\x{1EE5F}'
|
||||
. '\x{1EE61}\x{1EE62}\x{1EE64}\x{1EE67}-\x{1EE6A}\x{1EE6C}-\x{1EE72}\x{1EE74}-\x{1EE77}'
|
||||
. '\x{1EE79}-\x{1EE7C}\x{1EE7E}\x{1EE80}-\x{1EE89}\x{1EE8B}-\x{1EE9B}\x{1EEA1}-\x{1EEA3}'
|
||||
. '\x{1EEA5}-\x{1EEA9}\x{1EEAB}-\x{1EEBB}'
|
||||
. ']/u';
|
||||
}
|
||||
+16561
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user