mirror of
https://gitlab.com/signalytic/client-external/streamline/streamline-emr.git
synced 2026-09-13 03:31:31 +00:00
resolved conflicts
This commit is contained in:
@@ -0,0 +1,718 @@
|
||||
<?php
|
||||
|
||||
/*
|
||||
* This file is part of the Symfony package.
|
||||
*
|
||||
* (c) Fabien Potencier <fabien@symfony.com>
|
||||
*
|
||||
* For the full copyright and license information, please view the LICENSE
|
||||
* file that was distributed with this source code.
|
||||
*/
|
||||
|
||||
namespace Symfony\Component\String;
|
||||
|
||||
use Symfony\Component\String\Exception\ExceptionInterface;
|
||||
use Symfony\Component\String\Exception\InvalidArgumentException;
|
||||
use Symfony\Component\String\Exception\RuntimeException;
|
||||
|
||||
/**
|
||||
* Represents a string of abstract characters.
|
||||
*
|
||||
* Unicode defines 3 types of "characters" (bytes, code points and grapheme clusters).
|
||||
* This class is the abstract type to use as a type-hint when the logic you want to
|
||||
* implement doesn't care about the exact variant it deals with.
|
||||
*
|
||||
* @author Nicolas Grekas <p@tchwork.com>
|
||||
* @author Hugo Hamon <hugohamon@neuf.fr>
|
||||
*
|
||||
* @throws ExceptionInterface
|
||||
*/
|
||||
abstract class AbstractString implements \Stringable, \JsonSerializable
|
||||
{
|
||||
public const PREG_PATTERN_ORDER = \PREG_PATTERN_ORDER;
|
||||
public const PREG_SET_ORDER = \PREG_SET_ORDER;
|
||||
public const PREG_OFFSET_CAPTURE = \PREG_OFFSET_CAPTURE;
|
||||
public const PREG_UNMATCHED_AS_NULL = \PREG_UNMATCHED_AS_NULL;
|
||||
|
||||
public const PREG_SPLIT = 0;
|
||||
public const PREG_SPLIT_NO_EMPTY = \PREG_SPLIT_NO_EMPTY;
|
||||
public const PREG_SPLIT_DELIM_CAPTURE = \PREG_SPLIT_DELIM_CAPTURE;
|
||||
public const PREG_SPLIT_OFFSET_CAPTURE = \PREG_SPLIT_OFFSET_CAPTURE;
|
||||
|
||||
protected string $string = '';
|
||||
protected ?bool $ignoreCase = false;
|
||||
|
||||
abstract public function __construct(string $string = '');
|
||||
|
||||
/**
|
||||
* Unwraps instances of AbstractString back to strings.
|
||||
*
|
||||
* @return string[]|array
|
||||
*/
|
||||
public static function unwrap(array $values): array
|
||||
{
|
||||
foreach ($values as $k => $v) {
|
||||
if ($v instanceof self) {
|
||||
$values[$k] = $v->__toString();
|
||||
} elseif (\is_array($v) && $values[$k] !== $v = static::unwrap($v)) {
|
||||
$values[$k] = $v;
|
||||
}
|
||||
}
|
||||
|
||||
return $values;
|
||||
}
|
||||
|
||||
/**
|
||||
* Wraps (and normalizes) strings in instances of AbstractString.
|
||||
*
|
||||
* @return static[]|array
|
||||
*/
|
||||
public static function wrap(array $values): array
|
||||
{
|
||||
$i = 0;
|
||||
$keys = null;
|
||||
|
||||
foreach ($values as $k => $v) {
|
||||
if (\is_string($k) && '' !== $k && $k !== $j = (string) new static($k)) {
|
||||
$keys ??= array_keys($values);
|
||||
$keys[$i] = $j;
|
||||
}
|
||||
|
||||
if (\is_string($v)) {
|
||||
$values[$k] = new static($v);
|
||||
} elseif (\is_array($v) && $values[$k] !== $v = static::wrap($v)) {
|
||||
$values[$k] = $v;
|
||||
}
|
||||
|
||||
++$i;
|
||||
}
|
||||
|
||||
return null !== $keys ? array_combine($keys, $values) : $values;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $needle
|
||||
*/
|
||||
public function after(string|iterable $needle, bool $includeNeedle = false, int $offset = 0): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$i = \PHP_INT_MAX;
|
||||
|
||||
if (\is_string($needle)) {
|
||||
$needle = [$needle];
|
||||
}
|
||||
|
||||
foreach ($needle as $n) {
|
||||
$n = (string) $n;
|
||||
$j = $this->indexOf($n, $offset);
|
||||
|
||||
if (null !== $j && $j < $i) {
|
||||
$i = $j;
|
||||
$str->string = $n;
|
||||
}
|
||||
}
|
||||
|
||||
if (\PHP_INT_MAX === $i) {
|
||||
return $str;
|
||||
}
|
||||
|
||||
if (!$includeNeedle) {
|
||||
$i += $str->length();
|
||||
}
|
||||
|
||||
return $this->slice($i);
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $needle
|
||||
*/
|
||||
public function afterLast(string|iterable $needle, bool $includeNeedle = false, int $offset = 0): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$i = null;
|
||||
|
||||
if (\is_string($needle)) {
|
||||
$needle = [$needle];
|
||||
}
|
||||
|
||||
foreach ($needle as $n) {
|
||||
$n = (string) $n;
|
||||
$j = $this->indexOfLast($n, $offset);
|
||||
|
||||
if (null !== $j && $j >= $i) {
|
||||
$i = $offset = $j;
|
||||
$str->string = $n;
|
||||
}
|
||||
}
|
||||
|
||||
if (null === $i) {
|
||||
return $str;
|
||||
}
|
||||
|
||||
if (!$includeNeedle) {
|
||||
$i += $str->length();
|
||||
}
|
||||
|
||||
return $this->slice($i);
|
||||
}
|
||||
|
||||
abstract public function append(string ...$suffix): static;
|
||||
|
||||
/**
|
||||
* @param string|string[] $needle
|
||||
*/
|
||||
public function before(string|iterable $needle, bool $includeNeedle = false, int $offset = 0): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$i = \PHP_INT_MAX;
|
||||
|
||||
if (\is_string($needle)) {
|
||||
$needle = [$needle];
|
||||
}
|
||||
|
||||
foreach ($needle as $n) {
|
||||
$n = (string) $n;
|
||||
$j = $this->indexOf($n, $offset);
|
||||
|
||||
if (null !== $j && $j < $i) {
|
||||
$i = $j;
|
||||
$str->string = $n;
|
||||
}
|
||||
}
|
||||
|
||||
if (\PHP_INT_MAX === $i) {
|
||||
return $str;
|
||||
}
|
||||
|
||||
if ($includeNeedle) {
|
||||
$i += $str->length();
|
||||
}
|
||||
|
||||
return $this->slice(0, $i);
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $needle
|
||||
*/
|
||||
public function beforeLast(string|iterable $needle, bool $includeNeedle = false, int $offset = 0): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$i = null;
|
||||
|
||||
if (\is_string($needle)) {
|
||||
$needle = [$needle];
|
||||
}
|
||||
|
||||
foreach ($needle as $n) {
|
||||
$n = (string) $n;
|
||||
$j = $this->indexOfLast($n, $offset);
|
||||
|
||||
if (null !== $j && $j >= $i) {
|
||||
$i = $offset = $j;
|
||||
$str->string = $n;
|
||||
}
|
||||
}
|
||||
|
||||
if (null === $i) {
|
||||
return $str;
|
||||
}
|
||||
|
||||
if ($includeNeedle) {
|
||||
$i += $str->length();
|
||||
}
|
||||
|
||||
return $this->slice(0, $i);
|
||||
}
|
||||
|
||||
/**
|
||||
* @return int[]
|
||||
*/
|
||||
public function bytesAt(int $offset): array
|
||||
{
|
||||
$str = $this->slice($offset, 1);
|
||||
|
||||
return '' === $str->string ? [] : array_values(unpack('C*', $str->string));
|
||||
}
|
||||
|
||||
abstract public function camel(): static;
|
||||
|
||||
/**
|
||||
* @return static[]
|
||||
*/
|
||||
abstract public function chunk(int $length = 1): array;
|
||||
|
||||
public function collapseWhitespace(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = trim(preg_replace("/(?:[ \n\r\t\x0C]{2,}+|[\n\r\t\x0C])/", ' ', $str->string), " \n\r\t\x0C");
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $needle
|
||||
*/
|
||||
public function containsAny(string|iterable $needle): bool
|
||||
{
|
||||
return null !== $this->indexOf($needle);
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $suffix
|
||||
*/
|
||||
public function endsWith(string|iterable $suffix): bool
|
||||
{
|
||||
if (\is_string($suffix)) {
|
||||
throw new \TypeError(\sprintf('Method "%s()" must be overridden by class "%s" to deal with non-iterable values.', __FUNCTION__, static::class));
|
||||
}
|
||||
|
||||
foreach ($suffix as $s) {
|
||||
if ($this->endsWith((string) $s)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
public function ensureEnd(string $suffix): static
|
||||
{
|
||||
if (!$this->endsWith($suffix)) {
|
||||
return $this->append($suffix);
|
||||
}
|
||||
|
||||
$suffix = preg_quote($suffix);
|
||||
$regex = '{('.$suffix.')(?:'.$suffix.')++$}D';
|
||||
|
||||
return $this->replaceMatches($regex.($this->ignoreCase ? 'i' : ''), '$1');
|
||||
}
|
||||
|
||||
public function ensureStart(string $prefix): static
|
||||
{
|
||||
$prefix = new static($prefix);
|
||||
|
||||
if (!$this->startsWith($prefix)) {
|
||||
return $this->prepend($prefix);
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$i = $prefixLen = $prefix->length();
|
||||
|
||||
while ($this->indexOf($prefix, $i) === $i) {
|
||||
$str = $str->slice($prefixLen);
|
||||
$i += $prefixLen;
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $string
|
||||
*/
|
||||
public function equalsTo(string|iterable $string): bool
|
||||
{
|
||||
if (\is_string($string)) {
|
||||
throw new \TypeError(\sprintf('Method "%s()" must be overridden by class "%s" to deal with non-iterable values.', __FUNCTION__, static::class));
|
||||
}
|
||||
|
||||
foreach ($string as $s) {
|
||||
if ($this->equalsTo((string) $s)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
abstract public function folded(): static;
|
||||
|
||||
public function ignoreCase(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->ignoreCase = true;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $needle
|
||||
*/
|
||||
public function indexOf(string|iterable $needle, int $offset = 0): ?int
|
||||
{
|
||||
if (\is_string($needle)) {
|
||||
throw new \TypeError(\sprintf('Method "%s()" must be overridden by class "%s" to deal with non-iterable values.', __FUNCTION__, static::class));
|
||||
}
|
||||
|
||||
$i = \PHP_INT_MAX;
|
||||
|
||||
foreach ($needle as $n) {
|
||||
$j = $this->indexOf((string) $n, $offset);
|
||||
|
||||
if (null !== $j && $j < $i) {
|
||||
$i = $j;
|
||||
}
|
||||
}
|
||||
|
||||
return \PHP_INT_MAX === $i ? null : $i;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $needle
|
||||
*/
|
||||
public function indexOfLast(string|iterable $needle, int $offset = 0): ?int
|
||||
{
|
||||
if (\is_string($needle)) {
|
||||
throw new \TypeError(\sprintf('Method "%s()" must be overridden by class "%s" to deal with non-iterable values.', __FUNCTION__, static::class));
|
||||
}
|
||||
|
||||
$i = null;
|
||||
|
||||
foreach ($needle as $n) {
|
||||
$j = $this->indexOfLast((string) $n, $offset);
|
||||
|
||||
if (null !== $j && $j >= $i) {
|
||||
$i = $offset = $j;
|
||||
}
|
||||
}
|
||||
|
||||
return $i;
|
||||
}
|
||||
|
||||
public function isEmpty(): bool
|
||||
{
|
||||
return '' === $this->string;
|
||||
}
|
||||
|
||||
abstract public function join(array $strings, ?string $lastGlue = null): static;
|
||||
|
||||
public function jsonSerialize(): string
|
||||
{
|
||||
return $this->string;
|
||||
}
|
||||
|
||||
abstract public function length(): int;
|
||||
|
||||
abstract public function lower(): static;
|
||||
|
||||
/**
|
||||
* Matches the string using a regular expression.
|
||||
*
|
||||
* Pass PREG_PATTERN_ORDER or PREG_SET_ORDER as $flags to get all occurrences matching the regular expression.
|
||||
*
|
||||
* @return array All matches in a multi-dimensional array ordered according to flags
|
||||
*/
|
||||
abstract public function match(string $regexp, int $flags = 0, int $offset = 0): array;
|
||||
|
||||
abstract public function padBoth(int $length, string $padStr = ' '): static;
|
||||
|
||||
abstract public function padEnd(int $length, string $padStr = ' '): static;
|
||||
|
||||
abstract public function padStart(int $length, string $padStr = ' '): static;
|
||||
|
||||
abstract public function prepend(string ...$prefix): static;
|
||||
|
||||
public function repeat(int $multiplier): static
|
||||
{
|
||||
if (0 > $multiplier) {
|
||||
throw new InvalidArgumentException(\sprintf('Multiplier must be positive, %d given.', $multiplier));
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$str->string = str_repeat($str->string, $multiplier);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
abstract public function replace(string $from, string $to): static;
|
||||
|
||||
abstract public function replaceMatches(string $fromRegexp, string|callable $to): static;
|
||||
|
||||
abstract public function reverse(): static;
|
||||
|
||||
abstract public function slice(int $start = 0, ?int $length = null): static;
|
||||
|
||||
abstract public function snake(): static;
|
||||
|
||||
public function kebab(): static
|
||||
{
|
||||
return $this->snake()->replace('_', '-');
|
||||
}
|
||||
|
||||
abstract public function splice(string $replacement, int $start = 0, ?int $length = null): static;
|
||||
|
||||
/**
|
||||
* @return static[]
|
||||
*/
|
||||
public function split(string $delimiter, ?int $limit = null, ?int $flags = null): array
|
||||
{
|
||||
if (null === $flags) {
|
||||
throw new \TypeError('Split behavior when $flags is null must be implemented by child classes.');
|
||||
}
|
||||
|
||||
if ($this->ignoreCase) {
|
||||
$delimiter .= 'i';
|
||||
}
|
||||
|
||||
set_error_handler(static fn ($t, $m) => throw new InvalidArgumentException($m));
|
||||
|
||||
try {
|
||||
if (false === $chunks = preg_split($delimiter, $this->string, $limit, $flags)) {
|
||||
throw new RuntimeException('Splitting failed with error: '.preg_last_error_msg());
|
||||
}
|
||||
} finally {
|
||||
restore_error_handler();
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
|
||||
if (self::PREG_SPLIT_OFFSET_CAPTURE & $flags) {
|
||||
foreach ($chunks as &$chunk) {
|
||||
$str->string = $chunk[0];
|
||||
$chunk[0] = clone $str;
|
||||
}
|
||||
} else {
|
||||
foreach ($chunks as &$chunk) {
|
||||
$str->string = $chunk;
|
||||
$chunk = clone $str;
|
||||
}
|
||||
}
|
||||
|
||||
return $chunks;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $prefix
|
||||
*/
|
||||
public function startsWith(string|iterable $prefix): bool
|
||||
{
|
||||
if (\is_string($prefix)) {
|
||||
throw new \TypeError(\sprintf('Method "%s()" must be overridden by class "%s" to deal with non-iterable values.', __FUNCTION__, static::class));
|
||||
}
|
||||
|
||||
foreach ($prefix as $prefix) {
|
||||
if ($this->startsWith((string) $prefix)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
abstract public function title(bool $allWords = false): static;
|
||||
|
||||
public function toByteString(?string $toEncoding = null): ByteString
|
||||
{
|
||||
$b = new ByteString();
|
||||
|
||||
$toEncoding = \in_array($toEncoding, ['utf8', 'utf-8', 'UTF8'], true) ? 'UTF-8' : $toEncoding;
|
||||
|
||||
if (null === $toEncoding || $toEncoding === $fromEncoding = $this instanceof AbstractUnicodeString || preg_match('//u', $b->string) ? 'UTF-8' : 'Windows-1252') {
|
||||
$b->string = $this->string;
|
||||
|
||||
return $b;
|
||||
}
|
||||
|
||||
try {
|
||||
$b->string = mb_convert_encoding($this->string, $toEncoding, 'UTF-8');
|
||||
} catch (\ValueError $e) {
|
||||
if (!\function_exists('iconv')) {
|
||||
throw new InvalidArgumentException($e->getMessage(), $e->getCode(), $e);
|
||||
}
|
||||
|
||||
$b->string = iconv('UTF-8', $toEncoding, $this->string);
|
||||
}
|
||||
|
||||
return $b;
|
||||
}
|
||||
|
||||
public function toCodePointString(): CodePointString
|
||||
{
|
||||
return new CodePointString($this->string);
|
||||
}
|
||||
|
||||
public function toString(): string
|
||||
{
|
||||
return $this->string;
|
||||
}
|
||||
|
||||
public function toUnicodeString(): UnicodeString
|
||||
{
|
||||
return new UnicodeString($this->string);
|
||||
}
|
||||
|
||||
abstract public function trim(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): static;
|
||||
|
||||
abstract public function trimEnd(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): static;
|
||||
|
||||
/**
|
||||
* @param string|string[] $prefix
|
||||
*/
|
||||
public function trimPrefix($prefix): static
|
||||
{
|
||||
if (\is_array($prefix) || $prefix instanceof \Traversable) { // don't use is_iterable(), it's slow
|
||||
foreach ($prefix as $s) {
|
||||
$t = $this->trimPrefix($s);
|
||||
|
||||
if ($t->string !== $this->string) {
|
||||
return $t;
|
||||
}
|
||||
}
|
||||
|
||||
return clone $this;
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
|
||||
if ($prefix instanceof self) {
|
||||
$prefix = $prefix->string;
|
||||
} else {
|
||||
$prefix = (string) $prefix;
|
||||
}
|
||||
|
||||
if ('' !== $prefix && \strlen($this->string) >= \strlen($prefix) && 0 === substr_compare($this->string, $prefix, 0, \strlen($prefix), $this->ignoreCase)) {
|
||||
$str->string = substr($this->string, \strlen($prefix));
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
abstract public function trimStart(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): static;
|
||||
|
||||
/**
|
||||
* @param string|string[] $suffix
|
||||
*/
|
||||
public function trimSuffix($suffix): static
|
||||
{
|
||||
if (\is_array($suffix) || $suffix instanceof \Traversable) { // don't use is_iterable(), it's slow
|
||||
foreach ($suffix as $s) {
|
||||
$t = $this->trimSuffix($s);
|
||||
|
||||
if ($t->string !== $this->string) {
|
||||
return $t;
|
||||
}
|
||||
}
|
||||
|
||||
return clone $this;
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
|
||||
if ($suffix instanceof self) {
|
||||
$suffix = $suffix->string;
|
||||
} else {
|
||||
$suffix = (string) $suffix;
|
||||
}
|
||||
|
||||
if ('' !== $suffix && \strlen($this->string) >= \strlen($suffix) && 0 === substr_compare($this->string, $suffix, -\strlen($suffix), null, $this->ignoreCase)) {
|
||||
$str->string = substr($this->string, 0, -\strlen($suffix));
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function truncate(int $length, string $ellipsis = '', bool|TruncateMode $cut = TruncateMode::Char): static
|
||||
{
|
||||
$stringLength = $this->length();
|
||||
|
||||
if ($stringLength <= $length) {
|
||||
return clone $this;
|
||||
}
|
||||
|
||||
$ellipsisLength = '' !== $ellipsis ? (new static($ellipsis))->length() : 0;
|
||||
|
||||
if ($length < $ellipsisLength) {
|
||||
$ellipsisLength = 0;
|
||||
}
|
||||
|
||||
$desiredLength = $length;
|
||||
if (TruncateMode::WordAfter === $cut || !$cut) {
|
||||
if (null === $length = $this->indexOf([' ', "\r", "\n", "\t"], ($length ?: 1) - 1)) {
|
||||
return clone $this;
|
||||
}
|
||||
|
||||
$length += $ellipsisLength;
|
||||
} elseif (TruncateMode::WordBefore === $cut && null !== $this->indexOf([' ', "\r", "\n", "\t"], ($length ?: 1) - 1)) {
|
||||
$length += $ellipsisLength;
|
||||
}
|
||||
|
||||
$str = $this->slice(0, $length - $ellipsisLength);
|
||||
|
||||
if (TruncateMode::WordBefore === $cut) {
|
||||
if (0 === $ellipsisLength && $desiredLength === $this->indexOf([' ', "\r", "\n", "\t"], $length)) {
|
||||
return $str;
|
||||
}
|
||||
|
||||
$str = $str->beforeLast([' ', "\r", "\n", "\t"]);
|
||||
}
|
||||
|
||||
return $ellipsisLength ? $str->trimEnd()->append($ellipsis) : $str;
|
||||
}
|
||||
|
||||
abstract public function upper(): static;
|
||||
|
||||
/**
|
||||
* Returns the printable length on a terminal.
|
||||
*/
|
||||
abstract public function width(bool $ignoreAnsiDecoration = true): int;
|
||||
|
||||
public function wordwrap(int $width = 75, string $break = "\n", bool $cut = false): static
|
||||
{
|
||||
$lines = '' !== $break ? $this->split($break) : [clone $this];
|
||||
$chars = [];
|
||||
$mask = '';
|
||||
|
||||
if (1 === \count($lines) && '' === $lines[0]->string) {
|
||||
return $lines[0];
|
||||
}
|
||||
|
||||
foreach ($lines as $i => $line) {
|
||||
if ($i) {
|
||||
$chars[] = $break;
|
||||
$mask .= '#';
|
||||
}
|
||||
|
||||
foreach ($line->chunk() as $char) {
|
||||
$chars[] = $char->string;
|
||||
$mask .= ' ' === $char->string ? ' ' : '?';
|
||||
}
|
||||
}
|
||||
|
||||
$string = '';
|
||||
$j = 0;
|
||||
$b = $i = -1;
|
||||
$mask = wordwrap($mask, $width, '#', $cut);
|
||||
|
||||
while (false !== $b = strpos($mask, '#', $b + 1)) {
|
||||
for (++$i; $i < $b; ++$i) {
|
||||
$string .= $chars[$j];
|
||||
unset($chars[$j++]);
|
||||
}
|
||||
|
||||
if ($break === $chars[$j] || ' ' === $chars[$j]) {
|
||||
unset($chars[$j++]);
|
||||
}
|
||||
|
||||
$string .= $break;
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$str->string = $string.implode('', $chars);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function __sleep(): array
|
||||
{
|
||||
return ['string'];
|
||||
}
|
||||
|
||||
public function __clone()
|
||||
{
|
||||
$this->ignoreCase = false;
|
||||
}
|
||||
|
||||
public function __toString(): string
|
||||
{
|
||||
return $this->string;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,664 @@
|
||||
<?php
|
||||
|
||||
/*
|
||||
* This file is part of the Symfony package.
|
||||
*
|
||||
* (c) Fabien Potencier <fabien@symfony.com>
|
||||
*
|
||||
* For the full copyright and license information, please view the LICENSE
|
||||
* file that was distributed with this source code.
|
||||
*/
|
||||
|
||||
namespace Symfony\Component\String;
|
||||
|
||||
use Symfony\Component\String\Exception\ExceptionInterface;
|
||||
use Symfony\Component\String\Exception\InvalidArgumentException;
|
||||
use Symfony\Component\String\Exception\RuntimeException;
|
||||
|
||||
/**
|
||||
* Represents a string of abstract Unicode characters.
|
||||
*
|
||||
* Unicode defines 3 types of "characters" (bytes, code points and grapheme clusters).
|
||||
* This class is the abstract type to use as a type-hint when the logic you want to
|
||||
* implement is Unicode-aware but doesn't care about code points vs grapheme clusters.
|
||||
*
|
||||
* @author Nicolas Grekas <p@tchwork.com>
|
||||
*
|
||||
* @throws ExceptionInterface
|
||||
*/
|
||||
abstract class AbstractUnicodeString extends AbstractString
|
||||
{
|
||||
public const NFC = \Normalizer::NFC;
|
||||
public const NFD = \Normalizer::NFD;
|
||||
public const NFKC = \Normalizer::NFKC;
|
||||
public const NFKD = \Normalizer::NFKD;
|
||||
|
||||
// all ASCII letters sorted by typical frequency of occurrence
|
||||
private const ASCII = "\x20\x65\x69\x61\x73\x6E\x74\x72\x6F\x6C\x75\x64\x5D\x5B\x63\x6D\x70\x27\x0A\x67\x7C\x68\x76\x2E\x66\x62\x2C\x3A\x3D\x2D\x71\x31\x30\x43\x32\x2A\x79\x78\x29\x28\x4C\x39\x41\x53\x2F\x50\x22\x45\x6A\x4D\x49\x6B\x33\x3E\x35\x54\x3C\x44\x34\x7D\x42\x7B\x38\x46\x77\x52\x36\x37\x55\x47\x4E\x3B\x4A\x7A\x56\x23\x48\x4F\x57\x5F\x26\x21\x4B\x3F\x58\x51\x25\x59\x5C\x09\x5A\x2B\x7E\x5E\x24\x40\x60\x7F\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0B\x0C\x0D\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F";
|
||||
|
||||
// the subset of folded case mappings that is not in lower case mappings
|
||||
private const FOLD_FROM = ['İ', 'µ', 'ſ', "\xCD\x85", 'ς', 'ϐ', 'ϑ', 'ϕ', 'ϖ', 'ϰ', 'ϱ', 'ϵ', 'ẛ', "\xE1\xBE\xBE", 'ß', 'ʼn', 'ǰ', 'ΐ', 'ΰ', 'և', 'ẖ', 'ẗ', 'ẘ', 'ẙ', 'ẚ', 'ẞ', 'ὐ', 'ὒ', 'ὔ', 'ὖ', 'ᾀ', 'ᾁ', 'ᾂ', 'ᾃ', 'ᾄ', 'ᾅ', 'ᾆ', 'ᾇ', 'ᾈ', 'ᾉ', 'ᾊ', 'ᾋ', 'ᾌ', 'ᾍ', 'ᾎ', 'ᾏ', 'ᾐ', 'ᾑ', 'ᾒ', 'ᾓ', 'ᾔ', 'ᾕ', 'ᾖ', 'ᾗ', 'ᾘ', 'ᾙ', 'ᾚ', 'ᾛ', 'ᾜ', 'ᾝ', 'ᾞ', 'ᾟ', 'ᾠ', 'ᾡ', 'ᾢ', 'ᾣ', 'ᾤ', 'ᾥ', 'ᾦ', 'ᾧ', 'ᾨ', 'ᾩ', 'ᾪ', 'ᾫ', 'ᾬ', 'ᾭ', 'ᾮ', 'ᾯ', 'ᾲ', 'ᾳ', 'ᾴ', 'ᾶ', 'ᾷ', 'ᾼ', 'ῂ', 'ῃ', 'ῄ', 'ῆ', 'ῇ', 'ῌ', 'ῒ', 'ῖ', 'ῗ', 'ῢ', 'ῤ', 'ῦ', 'ῧ', 'ῲ', 'ῳ', 'ῴ', 'ῶ', 'ῷ', 'ῼ', 'ff', 'fi', 'fl', 'ffi', 'ffl', 'ſt', 'st', 'ﬓ', 'ﬔ', 'ﬕ', 'ﬖ', 'ﬗ'];
|
||||
private const FOLD_TO = ['i̇', 'μ', 's', 'ι', 'σ', 'β', 'θ', 'φ', 'π', 'κ', 'ρ', 'ε', 'ṡ', 'ι', 'ss', 'ʼn', 'ǰ', 'ΐ', 'ΰ', 'եւ', 'ẖ', 'ẗ', 'ẘ', 'ẙ', 'aʾ', 'ss', 'ὐ', 'ὒ', 'ὔ', 'ὖ', 'ἀι', 'ἁι', 'ἂι', 'ἃι', 'ἄι', 'ἅι', 'ἆι', 'ἇι', 'ἀι', 'ἁι', 'ἂι', 'ἃι', 'ἄι', 'ἅι', 'ἆι', 'ἇι', 'ἠι', 'ἡι', 'ἢι', 'ἣι', 'ἤι', 'ἥι', 'ἦι', 'ἧι', 'ἠι', 'ἡι', 'ἢι', 'ἣι', 'ἤι', 'ἥι', 'ἦι', 'ἧι', 'ὠι', 'ὡι', 'ὢι', 'ὣι', 'ὤι', 'ὥι', 'ὦι', 'ὧι', 'ὠι', 'ὡι', 'ὢι', 'ὣι', 'ὤι', 'ὥι', 'ὦι', 'ὧι', 'ὰι', 'αι', 'άι', 'ᾶ', 'ᾶι', 'αι', 'ὴι', 'ηι', 'ήι', 'ῆ', 'ῆι', 'ηι', 'ῒ', 'ῖ', 'ῗ', 'ῢ', 'ῤ', 'ῦ', 'ῧ', 'ὼι', 'ωι', 'ώι', 'ῶ', 'ῶι', 'ωι', 'ff', 'fi', 'fl', 'ffi', 'ffl', 'st', 'st', 'մն', 'մե', 'մի', 'վն', 'մխ'];
|
||||
|
||||
// the subset of https://github.com/unicode-org/cldr/blob/master/common/transforms/Latin-ASCII.xml that is not in NFKD
|
||||
private const TRANSLIT_FROM = ['Æ', 'Ð', 'Ø', 'Þ', 'ß', 'æ', 'ð', 'ø', 'þ', 'Đ', 'đ', 'Ħ', 'ħ', 'ı', 'ĸ', 'Ŀ', 'ŀ', 'Ł', 'ł', 'ʼn', 'Ŋ', 'ŋ', 'Œ', 'œ', 'Ŧ', 'ŧ', 'ƀ', 'Ɓ', 'Ƃ', 'ƃ', 'Ƈ', 'ƈ', 'Ɖ', 'Ɗ', 'Ƌ', 'ƌ', 'Ɛ', 'Ƒ', 'ƒ', 'Ɠ', 'ƕ', 'Ɩ', 'Ɨ', 'Ƙ', 'ƙ', 'ƚ', 'Ɲ', 'ƞ', 'Ƣ', 'ƣ', 'Ƥ', 'ƥ', 'ƫ', 'Ƭ', 'ƭ', 'Ʈ', 'Ʋ', 'Ƴ', 'ƴ', 'Ƶ', 'ƶ', 'DŽ', 'Dž', 'dž', 'Ǥ', 'ǥ', 'ȡ', 'Ȥ', 'ȥ', 'ȴ', 'ȵ', 'ȶ', 'ȷ', 'ȸ', 'ȹ', 'Ⱥ', 'Ȼ', 'ȼ', 'Ƚ', 'Ⱦ', 'ȿ', 'ɀ', 'Ƀ', 'Ʉ', 'Ɇ', 'ɇ', 'Ɉ', 'ɉ', 'Ɍ', 'ɍ', 'Ɏ', 'ɏ', 'ɓ', 'ɕ', 'ɖ', 'ɗ', 'ɛ', 'ɟ', 'ɠ', 'ɡ', 'ɢ', 'ɦ', 'ɧ', 'ɨ', 'ɪ', 'ɫ', 'ɬ', 'ɭ', 'ɱ', 'ɲ', 'ɳ', 'ɴ', 'ɶ', 'ɼ', 'ɽ', 'ɾ', 'ʀ', 'ʂ', 'ʈ', 'ʉ', 'ʋ', 'ʏ', 'ʐ', 'ʑ', 'ʙ', 'ʛ', 'ʜ', 'ʝ', 'ʟ', 'ʠ', 'ʣ', 'ʥ', 'ʦ', 'ʪ', 'ʫ', 'ᴀ', 'ᴁ', 'ᴃ', 'ᴄ', 'ᴅ', 'ᴆ', 'ᴇ', 'ᴊ', 'ᴋ', 'ᴌ', 'ᴍ', 'ᴏ', 'ᴘ', 'ᴛ', 'ᴜ', 'ᴠ', 'ᴡ', 'ᴢ', 'ᵫ', 'ᵬ', 'ᵭ', 'ᵮ', 'ᵯ', 'ᵰ', 'ᵱ', 'ᵲ', 'ᵳ', 'ᵴ', 'ᵵ', 'ᵶ', 'ᵺ', 'ᵻ', 'ᵽ', 'ᵾ', 'ᶀ', 'ᶁ', 'ᶂ', 'ᶃ', 'ᶄ', 'ᶅ', 'ᶆ', 'ᶇ', 'ᶈ', 'ᶉ', 'ᶊ', 'ᶌ', 'ᶍ', 'ᶎ', 'ᶏ', 'ᶑ', 'ᶒ', 'ᶓ', 'ᶖ', 'ᶙ', 'ẚ', 'ẜ', 'ẝ', 'ẞ', 'Ỻ', 'ỻ', 'Ỽ', 'ỽ', 'Ỿ', 'ỿ', '©', '®', '₠', '₢', '₣', '₤', '₧', '₺', '₹', 'ℌ', '℞', '㎧', '㎮', '㏆', '㏗', '㏞', '㏟', '¼', '½', '¾', '⅓', '⅔', '⅕', '⅖', '⅗', '⅘', '⅙', '⅚', '⅛', '⅜', '⅝', '⅞', '⅟', '〇', '‘', '’', '‚', '‛', '“', '”', '„', '‟', '′', '″', '〝', '〞', '«', '»', '‹', '›', '‐', '‑', '‒', '–', '—', '―', '︱', '︲', '﹘', '‖', '⁄', '⁅', '⁆', '⁎', '、', '。', '〈', '〉', '《', '》', '〔', '〕', '〘', '〙', '〚', '〛', '︑', '︒', '︹', '︺', '︽', '︾', '︿', '﹀', '﹑', '﹝', '﹞', '｟', '｠', '｡', '､', '×', '÷', '−', '∕', '∖', '∣', '∥', '≪', '≫', '⦅', '⦆'];
|
||||
private const TRANSLIT_TO = ['AE', 'D', 'O', 'TH', 'ss', 'ae', 'd', 'o', 'th', 'D', 'd', 'H', 'h', 'i', 'q', 'L', 'l', 'L', 'l', '\'n', 'N', 'n', 'OE', 'oe', 'T', 't', 'b', 'B', 'B', 'b', 'C', 'c', 'D', 'D', 'D', 'd', 'E', 'F', 'f', 'G', 'hv', 'I', 'I', 'K', 'k', 'l', 'N', 'n', 'OI', 'oi', 'P', 'p', 't', 'T', 't', 'T', 'V', 'Y', 'y', 'Z', 'z', 'DZ', 'Dz', 'dz', 'G', 'g', 'd', 'Z', 'z', 'l', 'n', 't', 'j', 'db', 'qp', 'A', 'C', 'c', 'L', 'T', 's', 'z', 'B', 'U', 'E', 'e', 'J', 'j', 'R', 'r', 'Y', 'y', 'b', 'c', 'd', 'd', 'e', 'j', 'g', 'g', 'G', 'h', 'h', 'i', 'I', 'l', 'l', 'l', 'm', 'n', 'n', 'N', 'OE', 'r', 'r', 'r', 'R', 's', 't', 'u', 'v', 'Y', 'z', 'z', 'B', 'G', 'H', 'j', 'L', 'q', 'dz', 'dz', 'ts', 'ls', 'lz', 'A', 'AE', 'B', 'C', 'D', 'D', 'E', 'J', 'K', 'L', 'M', 'O', 'P', 'T', 'U', 'V', 'W', 'Z', 'ue', 'b', 'd', 'f', 'm', 'n', 'p', 'r', 'r', 's', 't', 'z', 'th', 'I', 'p', 'U', 'b', 'd', 'f', 'g', 'k', 'l', 'm', 'n', 'p', 'r', 's', 'v', 'x', 'z', 'a', 'd', 'e', 'e', 'i', 'u', 'a', 's', 's', 'SS', 'LL', 'll', 'V', 'v', 'Y', 'y', '(C)', '(R)', 'CE', 'Cr', 'Fr.', 'L.', 'Pts', 'TL', 'Rs', 'x', 'Rx', 'm/s', 'rad/s', 'C/kg', 'pH', 'V/m', 'A/m', ' 1/4', ' 1/2', ' 3/4', ' 1/3', ' 2/3', ' 1/5', ' 2/5', ' 3/5', ' 4/5', ' 1/6', ' 5/6', ' 1/8', ' 3/8', ' 5/8', ' 7/8', ' 1/', '0', '\'', '\'', ',', '\'', '"', '"', ',,', '"', '\'', '"', '"', '"', '<<', '>>', '<', '>', '-', '-', '-', '-', '-', '-', '-', '-', '-', '||', '/', '[', ']', '*', ',', '.', '<', '>', '<<', '>>', '[', ']', '[', ']', '[', ']', ',', '.', '[', ']', '<<', '>>', '<', '>', ',', '[', ']', '((', '))', '.', ',', '*', '/', '-', '/', '\\', '|', '||', '<<', '>>', '((', '))'];
|
||||
|
||||
private static array $transliterators = [];
|
||||
private static array $tableZero;
|
||||
private static array $tableWide;
|
||||
|
||||
public static function fromCodePoints(int ...$codes): static
|
||||
{
|
||||
$string = '';
|
||||
|
||||
foreach ($codes as $code) {
|
||||
if (0x80 > $code %= 0x200000) {
|
||||
$string .= \chr($code);
|
||||
} elseif (0x800 > $code) {
|
||||
$string .= \chr(0xC0 | $code >> 6).\chr(0x80 | $code & 0x3F);
|
||||
} elseif (0x10000 > $code) {
|
||||
$string .= \chr(0xE0 | $code >> 12).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F);
|
||||
} else {
|
||||
$string .= \chr(0xF0 | $code >> 18).\chr(0x80 | $code >> 12 & 0x3F).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F);
|
||||
}
|
||||
}
|
||||
|
||||
return new static($string);
|
||||
}
|
||||
|
||||
/**
|
||||
* Generic UTF-8 to ASCII transliteration.
|
||||
*
|
||||
* Install the intl extension for best results.
|
||||
*
|
||||
* @param string[]|\Transliterator[]|\Closure[] $rules See "*-Latin" rules from Transliterator::listIDs()
|
||||
*/
|
||||
public function ascii(array $rules = []): self
|
||||
{
|
||||
$str = clone $this;
|
||||
$s = $str->string;
|
||||
$str->string = '';
|
||||
|
||||
array_unshift($rules, 'nfd');
|
||||
$rules[] = 'latin-ascii';
|
||||
|
||||
if (\function_exists('transliterator_transliterate')) {
|
||||
$rules[] = 'any-latin/bgn';
|
||||
}
|
||||
|
||||
$rules[] = 'nfkd';
|
||||
$rules[] = '[:nonspacing mark:] remove';
|
||||
|
||||
while (\strlen($s) - 1 > $i = strspn($s, self::ASCII)) {
|
||||
if (0 < --$i) {
|
||||
$str->string .= substr($s, 0, $i);
|
||||
$s = substr($s, $i);
|
||||
}
|
||||
|
||||
if (!$rule = array_shift($rules)) {
|
||||
$rules = []; // An empty rule interrupts the next ones
|
||||
}
|
||||
|
||||
if ($rule instanceof \Transliterator) {
|
||||
$s = $rule->transliterate($s);
|
||||
} elseif ($rule instanceof \Closure) {
|
||||
$s = $rule($s);
|
||||
} elseif ($rule) {
|
||||
if ('nfd' === $rule = strtolower($rule)) {
|
||||
normalizer_is_normalized($s, self::NFD) ?: $s = normalizer_normalize($s, self::NFD);
|
||||
} elseif ('nfkd' === $rule) {
|
||||
normalizer_is_normalized($s, self::NFKD) ?: $s = normalizer_normalize($s, self::NFKD);
|
||||
} elseif ('[:nonspacing mark:] remove' === $rule) {
|
||||
$s = preg_replace('/\p{Mn}++/u', '', $s);
|
||||
} elseif ('latin-ascii' === $rule) {
|
||||
$s = str_replace(self::TRANSLIT_FROM, self::TRANSLIT_TO, $s);
|
||||
} elseif ('de-ascii' === $rule) {
|
||||
$s = preg_replace("/([AUO])\u{0308}(?=\p{Ll})/u", '$1e', $s);
|
||||
$s = str_replace(["a\u{0308}", "o\u{0308}", "u\u{0308}", "A\u{0308}", "O\u{0308}", "U\u{0308}"], ['ae', 'oe', 'ue', 'AE', 'OE', 'UE'], $s);
|
||||
} elseif (\function_exists('transliterator_transliterate')) {
|
||||
if (null === $transliterator = self::$transliterators[$rule] ??= \Transliterator::create($rule)) {
|
||||
if ('any-latin/bgn' === $rule) {
|
||||
$rule = 'any-latin';
|
||||
$transliterator = self::$transliterators[$rule] ??= \Transliterator::create($rule);
|
||||
}
|
||||
|
||||
if (null === $transliterator) {
|
||||
throw new InvalidArgumentException(\sprintf('Unknown transliteration rule "%s".', $rule));
|
||||
}
|
||||
|
||||
self::$transliterators['any-latin/bgn'] = $transliterator;
|
||||
}
|
||||
|
||||
$s = $transliterator->transliterate($s);
|
||||
}
|
||||
} elseif (!\function_exists('iconv')) {
|
||||
$s = preg_replace('/[^\x00-\x7F]/u', '?', $s);
|
||||
} else {
|
||||
$s = @preg_replace_callback('/[^\x00-\x7F]/u', static function ($c) {
|
||||
$c = (string) iconv('UTF-8', 'ASCII//TRANSLIT', $c[0]);
|
||||
|
||||
if ('' === $c && '' === iconv('UTF-8', 'ASCII//TRANSLIT', '²')) {
|
||||
throw new \LogicException(\sprintf('"%s" requires a translit-able iconv implementation, try installing "gnu-libiconv" if you\'re using Alpine Linux.', static::class));
|
||||
}
|
||||
|
||||
return 1 < \strlen($c) ? ltrim($c, '\'`"^~') : ('' !== $c ? $c : '?');
|
||||
}, $s);
|
||||
}
|
||||
}
|
||||
|
||||
$str->string .= $s;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function camel(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = str_replace(' ', '', preg_replace_callback('/\b.(?!\p{Lu})/u', static function ($m) {
|
||||
static $i = 0;
|
||||
|
||||
return 1 === ++$i ? ('İ' === $m[0] ? 'i̇' : mb_strtolower($m[0], 'UTF-8')) : mb_convert_case($m[0], \MB_CASE_TITLE, 'UTF-8');
|
||||
}, preg_replace('/[^\pL0-9]++/u', ' ', $this->string)));
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return int[]
|
||||
*/
|
||||
public function codePointsAt(int $offset): array
|
||||
{
|
||||
$str = $this->slice($offset, 1);
|
||||
|
||||
if ('' === $str->string) {
|
||||
return [];
|
||||
}
|
||||
|
||||
$codePoints = [];
|
||||
|
||||
foreach (preg_split('//u', $str->string, -1, \PREG_SPLIT_NO_EMPTY) as $c) {
|
||||
$codePoints[] = mb_ord($c, 'UTF-8');
|
||||
}
|
||||
|
||||
return $codePoints;
|
||||
}
|
||||
|
||||
public function folded(bool $compat = true): static
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
if (!$compat || !\defined('Normalizer::NFKC_CF')) {
|
||||
$str->string = normalizer_normalize($str->string, $compat ? \Normalizer::NFKC : \Normalizer::NFC);
|
||||
$str->string = mb_strtolower(str_replace(self::FOLD_FROM, self::FOLD_TO, $str->string), 'UTF-8');
|
||||
} else {
|
||||
$str->string = normalizer_normalize($str->string, \Normalizer::NFKC_CF);
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function join(array $strings, ?string $lastGlue = null): static
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
$tail = null !== $lastGlue && 1 < \count($strings) ? $lastGlue.array_pop($strings) : '';
|
||||
$str->string = implode($this->string, $strings).$tail;
|
||||
|
||||
if (!preg_match('//u', $str->string)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function lower(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = mb_strtolower(str_replace('İ', 'i̇', $str->string), 'UTF-8');
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string $locale In the format language_region (e.g. tr_TR)
|
||||
*/
|
||||
public function localeLower(string $locale): static
|
||||
{
|
||||
if (null !== $transliterator = $this->getLocaleTransliterator($locale, 'Lower')) {
|
||||
$str = clone $this;
|
||||
$str->string = $transliterator->transliterate($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
return $this->lower();
|
||||
}
|
||||
|
||||
public function match(string $regexp, int $flags = 0, int $offset = 0): array
|
||||
{
|
||||
$match = ((\PREG_PATTERN_ORDER | \PREG_SET_ORDER) & $flags) ? 'preg_match_all' : 'preg_match';
|
||||
|
||||
if ($this->ignoreCase) {
|
||||
$regexp .= 'i';
|
||||
}
|
||||
|
||||
set_error_handler(static fn ($t, $m) => throw new InvalidArgumentException($m));
|
||||
|
||||
try {
|
||||
if (false === $match($regexp.'u', $this->string, $matches, $flags | \PREG_UNMATCHED_AS_NULL, $offset)) {
|
||||
throw new RuntimeException('Matching failed with error: '.preg_last_error_msg());
|
||||
}
|
||||
} finally {
|
||||
restore_error_handler();
|
||||
}
|
||||
|
||||
return $matches;
|
||||
}
|
||||
|
||||
public function normalize(int $form = self::NFC): static
|
||||
{
|
||||
if (!\in_array($form, [self::NFC, self::NFD, self::NFKC, self::NFKD])) {
|
||||
throw new InvalidArgumentException('Unsupported normalization form.');
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
normalizer_is_normalized($str->string, $form) ?: $str->string = normalizer_normalize($str->string, $form);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function padBoth(int $length, string $padStr = ' '): static
|
||||
{
|
||||
if ('' === $padStr || !preg_match('//u', $padStr)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
$pad = clone $this;
|
||||
$pad->string = $padStr;
|
||||
|
||||
return $this->pad($length, $pad, \STR_PAD_BOTH);
|
||||
}
|
||||
|
||||
public function padEnd(int $length, string $padStr = ' '): static
|
||||
{
|
||||
if ('' === $padStr || !preg_match('//u', $padStr)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
$pad = clone $this;
|
||||
$pad->string = $padStr;
|
||||
|
||||
return $this->pad($length, $pad, \STR_PAD_RIGHT);
|
||||
}
|
||||
|
||||
public function padStart(int $length, string $padStr = ' '): static
|
||||
{
|
||||
if ('' === $padStr || !preg_match('//u', $padStr)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
$pad = clone $this;
|
||||
$pad->string = $padStr;
|
||||
|
||||
return $this->pad($length, $pad, \STR_PAD_LEFT);
|
||||
}
|
||||
|
||||
public function replaceMatches(string $fromRegexp, string|callable $to): static
|
||||
{
|
||||
if ($this->ignoreCase) {
|
||||
$fromRegexp .= 'i';
|
||||
}
|
||||
|
||||
if (\is_array($to) || $to instanceof \Closure) {
|
||||
$replace = 'preg_replace_callback';
|
||||
$to = static function (array $m) use ($to): string {
|
||||
$to = $to($m);
|
||||
|
||||
if ('' !== $to && (!\is_string($to) || !preg_match('//u', $to))) {
|
||||
throw new InvalidArgumentException('Replace callback must return a valid UTF-8 string.');
|
||||
}
|
||||
|
||||
return $to;
|
||||
};
|
||||
} elseif ('' !== $to && !preg_match('//u', $to)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
} else {
|
||||
$replace = 'preg_replace';
|
||||
}
|
||||
|
||||
set_error_handler(static fn ($t, $m) => throw new InvalidArgumentException($m));
|
||||
|
||||
try {
|
||||
if (null === $string = $replace($fromRegexp.'u', $to, $this->string)) {
|
||||
$lastError = preg_last_error();
|
||||
|
||||
foreach (get_defined_constants(true)['pcre'] as $k => $v) {
|
||||
if ($lastError === $v && str_ends_with($k, '_ERROR')) {
|
||||
throw new RuntimeException('Matching failed with '.$k.'.');
|
||||
}
|
||||
}
|
||||
|
||||
throw new RuntimeException('Matching failed with unknown error code.');
|
||||
}
|
||||
} finally {
|
||||
restore_error_handler();
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$str->string = $string;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function reverse(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = implode('', array_reverse(preg_split('/(\X)/u', $str->string, -1, \PREG_SPLIT_DELIM_CAPTURE | \PREG_SPLIT_NO_EMPTY)));
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function snake(): static
|
||||
{
|
||||
$str = $this->camel();
|
||||
$str->string = mb_strtolower(preg_replace(['/(\p{Lu}+)(\p{Lu}\p{Ll})/u', '/([\p{Ll}0-9])(\p{Lu})/u'], '\1_\2', $str->string), 'UTF-8');
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function title(bool $allWords = false): static
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
$limit = $allWords ? -1 : 1;
|
||||
|
||||
$str->string = preg_replace_callback('/\b./u', static fn (array $m): string => mb_convert_case($m[0], \MB_CASE_TITLE, 'UTF-8'), $str->string, $limit);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string $locale In the format language_region (e.g. tr_TR)
|
||||
*/
|
||||
public function localeTitle(string $locale): static
|
||||
{
|
||||
if (null !== $transliterator = $this->getLocaleTransliterator($locale, 'Title')) {
|
||||
$str = clone $this;
|
||||
$str->string = $transliterator->transliterate($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
return $this->title();
|
||||
}
|
||||
|
||||
public function trim(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): static
|
||||
{
|
||||
if (" \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}" !== $chars && !preg_match('//u', $chars)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 chars.');
|
||||
}
|
||||
$chars = preg_quote($chars);
|
||||
|
||||
$str = clone $this;
|
||||
$str->string = preg_replace("{^[$chars]++|[$chars]++$}uD", '', $str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function trimEnd(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): static
|
||||
{
|
||||
if (" \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}" !== $chars && !preg_match('//u', $chars)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 chars.');
|
||||
}
|
||||
$chars = preg_quote($chars);
|
||||
|
||||
$str = clone $this;
|
||||
$str->string = preg_replace("{[$chars]++$}uD", '', $str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function trimPrefix($prefix): static
|
||||
{
|
||||
if (!$this->ignoreCase) {
|
||||
return parent::trimPrefix($prefix);
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
|
||||
if ($prefix instanceof \Traversable) {
|
||||
$prefix = iterator_to_array($prefix, false);
|
||||
} elseif ($prefix instanceof parent) {
|
||||
$prefix = $prefix->string;
|
||||
}
|
||||
|
||||
$prefix = implode('|', array_map('preg_quote', (array) $prefix));
|
||||
$str->string = preg_replace("{^(?:$prefix)}iuD", '', $this->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function trimStart(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): static
|
||||
{
|
||||
if (" \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}" !== $chars && !preg_match('//u', $chars)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 chars.');
|
||||
}
|
||||
$chars = preg_quote($chars);
|
||||
|
||||
$str = clone $this;
|
||||
$str->string = preg_replace("{^[$chars]++}uD", '', $str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function trimSuffix($suffix): static
|
||||
{
|
||||
if (!$this->ignoreCase) {
|
||||
return parent::trimSuffix($suffix);
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
|
||||
if ($suffix instanceof \Traversable) {
|
||||
$suffix = iterator_to_array($suffix, false);
|
||||
} elseif ($suffix instanceof parent) {
|
||||
$suffix = $suffix->string;
|
||||
}
|
||||
|
||||
$suffix = implode('|', array_map('preg_quote', (array) $suffix));
|
||||
$str->string = preg_replace("{(?:$suffix)$}iuD", '', $this->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function upper(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = mb_strtoupper($str->string, 'UTF-8');
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string $locale In the format language_region (e.g. tr_TR)
|
||||
*/
|
||||
public function localeUpper(string $locale): static
|
||||
{
|
||||
if (null !== $transliterator = $this->getLocaleTransliterator($locale, 'Upper')) {
|
||||
$str = clone $this;
|
||||
$str->string = $transliterator->transliterate($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
return $this->upper();
|
||||
}
|
||||
|
||||
public function width(bool $ignoreAnsiDecoration = true): int
|
||||
{
|
||||
$width = 0;
|
||||
$s = str_replace(["\x00", "\x05", "\x07"], '', $this->string);
|
||||
|
||||
if (str_contains($s, "\r")) {
|
||||
$s = str_replace(["\r\n", "\r"], "\n", $s);
|
||||
}
|
||||
|
||||
if (!$ignoreAnsiDecoration) {
|
||||
$s = preg_replace('/[\p{Cc}\x7F]++/u', '', $s);
|
||||
}
|
||||
|
||||
foreach (explode("\n", $s) as $s) {
|
||||
if ($ignoreAnsiDecoration) {
|
||||
$s = preg_replace('/(?:\x1B(?:
|
||||
\[ [\x30-\x3F]*+ [\x20-\x2F]*+ [\x40-\x7E]
|
||||
| [P\]X^_] .*? \x1B\\\\
|
||||
| [\x41-\x7E]
|
||||
)|[\p{Cc}\x7F]++)/xu', '', $s);
|
||||
}
|
||||
|
||||
$lineWidth = $this->wcswidth($s);
|
||||
|
||||
if ($lineWidth > $width) {
|
||||
$width = $lineWidth;
|
||||
}
|
||||
}
|
||||
|
||||
return $width;
|
||||
}
|
||||
|
||||
private function pad(int $len, self $pad, int $type): static
|
||||
{
|
||||
$sLen = $this->length();
|
||||
|
||||
if ($len <= $sLen) {
|
||||
return clone $this;
|
||||
}
|
||||
|
||||
$padLen = $pad->length();
|
||||
$freeLen = $len - $sLen;
|
||||
$len = $freeLen % $padLen;
|
||||
|
||||
switch ($type) {
|
||||
case \STR_PAD_RIGHT:
|
||||
return $this->append(str_repeat($pad->string, intdiv($freeLen, $padLen)).($len ? $pad->slice(0, $len) : ''));
|
||||
|
||||
case \STR_PAD_LEFT:
|
||||
return $this->prepend(str_repeat($pad->string, intdiv($freeLen, $padLen)).($len ? $pad->slice(0, $len) : ''));
|
||||
|
||||
case \STR_PAD_BOTH:
|
||||
$freeLen /= 2;
|
||||
|
||||
$rightLen = ceil($freeLen);
|
||||
$len = $rightLen % $padLen;
|
||||
$str = $this->append(str_repeat($pad->string, intdiv($rightLen, $padLen)).($len ? $pad->slice(0, $len) : ''));
|
||||
|
||||
$leftLen = floor($freeLen);
|
||||
$len = $leftLen % $padLen;
|
||||
|
||||
return $str->prepend(str_repeat($pad->string, intdiv($leftLen, $padLen)).($len ? $pad->slice(0, $len) : ''));
|
||||
|
||||
default:
|
||||
throw new InvalidArgumentException('Invalid padding type.');
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Based on https://github.com/jquast/wcwidth, a Python implementation of https://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c.
|
||||
*/
|
||||
private function wcswidth(string $string): int
|
||||
{
|
||||
$width = 0;
|
||||
|
||||
foreach (preg_split('//u', $string, -1, \PREG_SPLIT_NO_EMPTY) as $c) {
|
||||
$codePoint = mb_ord($c, 'UTF-8');
|
||||
|
||||
if (0 === $codePoint // NULL
|
||||
|| 0x034F === $codePoint // COMBINING GRAPHEME JOINER
|
||||
|| (0x200B <= $codePoint && 0x200F >= $codePoint) // ZERO WIDTH SPACE to RIGHT-TO-LEFT MARK
|
||||
|| 0x2028 === $codePoint // LINE SEPARATOR
|
||||
|| 0x2029 === $codePoint // PARAGRAPH SEPARATOR
|
||||
|| (0x202A <= $codePoint && 0x202E >= $codePoint) // LEFT-TO-RIGHT EMBEDDING to RIGHT-TO-LEFT OVERRIDE
|
||||
|| (0x2060 <= $codePoint && 0x2063 >= $codePoint) // WORD JOINER to INVISIBLE SEPARATOR
|
||||
) {
|
||||
continue;
|
||||
}
|
||||
|
||||
// Non printable characters
|
||||
if (32 > $codePoint // C0 control characters
|
||||
|| (0x07F <= $codePoint && 0x0A0 > $codePoint) // C1 control characters and DEL
|
||||
) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
self::$tableZero ??= require __DIR__.'/Resources/data/wcswidth_table_zero.php';
|
||||
|
||||
if ($codePoint >= self::$tableZero[0][0] && $codePoint <= self::$tableZero[$ubound = \count(self::$tableZero) - 1][1]) {
|
||||
$lbound = 0;
|
||||
while ($ubound >= $lbound) {
|
||||
$mid = floor(($lbound + $ubound) / 2);
|
||||
|
||||
if ($codePoint > self::$tableZero[$mid][1]) {
|
||||
$lbound = $mid + 1;
|
||||
} elseif ($codePoint < self::$tableZero[$mid][0]) {
|
||||
$ubound = $mid - 1;
|
||||
} else {
|
||||
continue 2;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
self::$tableWide ??= require __DIR__.'/Resources/data/wcswidth_table_wide.php';
|
||||
|
||||
if ($codePoint >= self::$tableWide[0][0] && $codePoint <= self::$tableWide[$ubound = \count(self::$tableWide) - 1][1]) {
|
||||
$lbound = 0;
|
||||
while ($ubound >= $lbound) {
|
||||
$mid = floor(($lbound + $ubound) / 2);
|
||||
|
||||
if ($codePoint > self::$tableWide[$mid][1]) {
|
||||
$lbound = $mid + 1;
|
||||
} elseif ($codePoint < self::$tableWide[$mid][0]) {
|
||||
$ubound = $mid - 1;
|
||||
} else {
|
||||
$width += 2;
|
||||
|
||||
continue 2;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
++$width;
|
||||
}
|
||||
|
||||
return $width;
|
||||
}
|
||||
|
||||
private function getLocaleTransliterator(string $locale, string $id): ?\Transliterator
|
||||
{
|
||||
$rule = $locale.'-'.$id;
|
||||
if (\array_key_exists($rule, self::$transliterators)) {
|
||||
return self::$transliterators[$rule];
|
||||
}
|
||||
|
||||
if (null !== $transliterator = self::$transliterators[$rule] = \Transliterator::create($rule)) {
|
||||
return $transliterator;
|
||||
}
|
||||
|
||||
// Try to find a parent locale (nl_BE -> nl)
|
||||
if (false === $i = strpos($locale, '_')) {
|
||||
return null;
|
||||
}
|
||||
|
||||
$parentRule = substr_replace($locale, '-'.$id, $i);
|
||||
|
||||
// Parent locale was already cached, return and store as current locale
|
||||
if (\array_key_exists($parentRule, self::$transliterators)) {
|
||||
return self::$transliterators[$rule] = self::$transliterators[$parentRule];
|
||||
}
|
||||
|
||||
// Create transliterator based on parent locale and cache the result on both initial and parent locale values
|
||||
$transliterator = \Transliterator::create($parentRule);
|
||||
|
||||
return self::$transliterators[$rule] = self::$transliterators[$parentRule] = $transliterator;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,490 @@
|
||||
<?php
|
||||
|
||||
/*
|
||||
* This file is part of the Symfony package.
|
||||
*
|
||||
* (c) Fabien Potencier <fabien@symfony.com>
|
||||
*
|
||||
* For the full copyright and license information, please view the LICENSE
|
||||
* file that was distributed with this source code.
|
||||
*/
|
||||
|
||||
namespace Symfony\Component\String;
|
||||
|
||||
use Random\Randomizer;
|
||||
use Symfony\Component\String\Exception\ExceptionInterface;
|
||||
use Symfony\Component\String\Exception\InvalidArgumentException;
|
||||
use Symfony\Component\String\Exception\RuntimeException;
|
||||
|
||||
/**
|
||||
* Represents a binary-safe string of bytes.
|
||||
*
|
||||
* @author Nicolas Grekas <p@tchwork.com>
|
||||
* @author Hugo Hamon <hugohamon@neuf.fr>
|
||||
*
|
||||
* @throws ExceptionInterface
|
||||
*/
|
||||
class ByteString extends AbstractString
|
||||
{
|
||||
private const ALPHABET_ALPHANUMERIC = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz';
|
||||
|
||||
public function __construct(string $string = '')
|
||||
{
|
||||
$this->string = $string;
|
||||
}
|
||||
|
||||
/*
|
||||
* The following method was derived from code of the Hack Standard Library (v4.40 - 2020-05-03)
|
||||
*
|
||||
* https://github.com/hhvm/hsl/blob/80a42c02f036f72a42f0415e80d6b847f4bf62d5/src/random/private.php#L16
|
||||
*
|
||||
* Code subject to the MIT license (https://github.com/hhvm/hsl/blob/master/LICENSE).
|
||||
*
|
||||
* Copyright (c) 2004-2020, Facebook, Inc. (https://www.facebook.com/)
|
||||
*/
|
||||
|
||||
public static function fromRandom(int $length = 16, ?string $alphabet = null): self
|
||||
{
|
||||
if ($length <= 0) {
|
||||
throw new InvalidArgumentException(\sprintf('A strictly positive length is expected, "%d" given.', $length));
|
||||
}
|
||||
|
||||
$alphabet ??= self::ALPHABET_ALPHANUMERIC;
|
||||
$alphabetSize = \strlen($alphabet);
|
||||
$bits = (int) ceil(log($alphabetSize, 2.0));
|
||||
if ($bits <= 0 || $bits > 56) {
|
||||
throw new InvalidArgumentException('The length of the alphabet must in the [2^1, 2^56] range.');
|
||||
}
|
||||
|
||||
if (\PHP_VERSION_ID >= 80300) {
|
||||
return new static((new Randomizer())->getBytesFromString($alphabet, $length));
|
||||
}
|
||||
|
||||
$ret = '';
|
||||
while ($length > 0) {
|
||||
$urandomLength = (int) ceil(2 * $length * $bits / 8.0);
|
||||
$data = random_bytes($urandomLength);
|
||||
$unpackedData = 0;
|
||||
$unpackedBits = 0;
|
||||
for ($i = 0; $i < $urandomLength && $length > 0; ++$i) {
|
||||
// Unpack 8 bits
|
||||
$unpackedData = ($unpackedData << 8) | \ord($data[$i]);
|
||||
$unpackedBits += 8;
|
||||
|
||||
// While we have enough bits to select a character from the alphabet, keep
|
||||
// consuming the random data
|
||||
for (; $unpackedBits >= $bits && $length > 0; $unpackedBits -= $bits) {
|
||||
$index = ($unpackedData & ((1 << $bits) - 1));
|
||||
$unpackedData >>= $bits;
|
||||
// Unfortunately, the alphabet size is not necessarily a power of two.
|
||||
// Worst case, it is 2^k + 1, which means we need (k+1) bits and we
|
||||
// have around a 50% chance of missing as k gets larger
|
||||
if ($index < $alphabetSize) {
|
||||
$ret .= $alphabet[$index];
|
||||
--$length;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return new static($ret);
|
||||
}
|
||||
|
||||
public function bytesAt(int $offset): array
|
||||
{
|
||||
$str = $this->string[$offset] ?? '';
|
||||
|
||||
return '' === $str ? [] : [\ord($str)];
|
||||
}
|
||||
|
||||
public function append(string ...$suffix): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string .= 1 >= \count($suffix) ? ($suffix[0] ?? '') : implode('', $suffix);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function camel(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
$parts = explode(' ', trim(ucwords(preg_replace('/[^a-zA-Z0-9\x7f-\xff]++/', ' ', $this->string))));
|
||||
$parts[0] = 1 !== \strlen($parts[0]) && ctype_upper($parts[0]) ? $parts[0] : lcfirst($parts[0]);
|
||||
$str->string = implode('', $parts);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function chunk(int $length = 1): array
|
||||
{
|
||||
if (1 > $length) {
|
||||
throw new InvalidArgumentException('The chunk length must be greater than zero.');
|
||||
}
|
||||
|
||||
if ('' === $this->string) {
|
||||
return [];
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$chunks = [];
|
||||
|
||||
foreach (str_split($this->string, $length) as $chunk) {
|
||||
$str->string = $chunk;
|
||||
$chunks[] = clone $str;
|
||||
}
|
||||
|
||||
return $chunks;
|
||||
}
|
||||
|
||||
public function endsWith(string|iterable|AbstractString $suffix): bool
|
||||
{
|
||||
if ($suffix instanceof AbstractString) {
|
||||
$suffix = $suffix->string;
|
||||
} elseif (!\is_string($suffix)) {
|
||||
return parent::endsWith($suffix);
|
||||
}
|
||||
|
||||
return '' !== $suffix && \strlen($this->string) >= \strlen($suffix) && 0 === substr_compare($this->string, $suffix, -\strlen($suffix), null, $this->ignoreCase);
|
||||
}
|
||||
|
||||
public function equalsTo(string|iterable|AbstractString $string): bool
|
||||
{
|
||||
if ($string instanceof AbstractString) {
|
||||
$string = $string->string;
|
||||
} elseif (!\is_string($string)) {
|
||||
return parent::equalsTo($string);
|
||||
}
|
||||
|
||||
if ('' !== $string && $this->ignoreCase) {
|
||||
return 0 === strcasecmp($string, $this->string);
|
||||
}
|
||||
|
||||
return $string === $this->string;
|
||||
}
|
||||
|
||||
public function folded(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = strtolower($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function indexOf(string|iterable|AbstractString $needle, int $offset = 0): ?int
|
||||
{
|
||||
if ($needle instanceof AbstractString) {
|
||||
$needle = $needle->string;
|
||||
} elseif (!\is_string($needle)) {
|
||||
return parent::indexOf($needle, $offset);
|
||||
}
|
||||
|
||||
if ('' === $needle) {
|
||||
return null;
|
||||
}
|
||||
|
||||
$i = $this->ignoreCase ? stripos($this->string, $needle, $offset) : strpos($this->string, $needle, $offset);
|
||||
|
||||
return false === $i ? null : $i;
|
||||
}
|
||||
|
||||
public function indexOfLast(string|iterable|AbstractString $needle, int $offset = 0): ?int
|
||||
{
|
||||
if ($needle instanceof AbstractString) {
|
||||
$needle = $needle->string;
|
||||
} elseif (!\is_string($needle)) {
|
||||
return parent::indexOfLast($needle, $offset);
|
||||
}
|
||||
|
||||
if ('' === $needle) {
|
||||
return null;
|
||||
}
|
||||
|
||||
$i = $this->ignoreCase ? strripos($this->string, $needle, $offset) : strrpos($this->string, $needle, $offset);
|
||||
|
||||
return false === $i ? null : $i;
|
||||
}
|
||||
|
||||
public function isUtf8(): bool
|
||||
{
|
||||
return '' === $this->string || preg_match('//u', $this->string);
|
||||
}
|
||||
|
||||
public function join(array $strings, ?string $lastGlue = null): static
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
$tail = null !== $lastGlue && 1 < \count($strings) ? $lastGlue.array_pop($strings) : '';
|
||||
$str->string = implode($this->string, $strings).$tail;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function length(): int
|
||||
{
|
||||
return \strlen($this->string);
|
||||
}
|
||||
|
||||
public function lower(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = strtolower($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function match(string $regexp, int $flags = 0, int $offset = 0): array
|
||||
{
|
||||
$match = ((\PREG_PATTERN_ORDER | \PREG_SET_ORDER) & $flags) ? 'preg_match_all' : 'preg_match';
|
||||
|
||||
if ($this->ignoreCase) {
|
||||
$regexp .= 'i';
|
||||
}
|
||||
|
||||
set_error_handler(static fn ($t, $m) => throw new InvalidArgumentException($m));
|
||||
|
||||
try {
|
||||
if (false === $match($regexp, $this->string, $matches, $flags | \PREG_UNMATCHED_AS_NULL, $offset)) {
|
||||
throw new RuntimeException('Matching failed with error: '.preg_last_error_msg());
|
||||
}
|
||||
} finally {
|
||||
restore_error_handler();
|
||||
}
|
||||
|
||||
return $matches;
|
||||
}
|
||||
|
||||
public function padBoth(int $length, string $padStr = ' '): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = str_pad($this->string, $length, $padStr, \STR_PAD_BOTH);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function padEnd(int $length, string $padStr = ' '): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = str_pad($this->string, $length, $padStr, \STR_PAD_RIGHT);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function padStart(int $length, string $padStr = ' '): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = str_pad($this->string, $length, $padStr, \STR_PAD_LEFT);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function prepend(string ...$prefix): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = (1 >= \count($prefix) ? ($prefix[0] ?? '') : implode('', $prefix)).$str->string;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function replace(string $from, string $to): static
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
if ('' !== $from) {
|
||||
$str->string = $this->ignoreCase ? str_ireplace($from, $to, $this->string) : str_replace($from, $to, $this->string);
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function replaceMatches(string $fromRegexp, string|callable $to): static
|
||||
{
|
||||
if ($this->ignoreCase) {
|
||||
$fromRegexp .= 'i';
|
||||
}
|
||||
|
||||
$replace = \is_array($to) || $to instanceof \Closure ? 'preg_replace_callback' : 'preg_replace';
|
||||
|
||||
set_error_handler(static fn ($t, $m) => throw new InvalidArgumentException($m));
|
||||
|
||||
try {
|
||||
if (null === $string = $replace($fromRegexp, $to, $this->string)) {
|
||||
$lastError = preg_last_error();
|
||||
|
||||
foreach (get_defined_constants(true)['pcre'] as $k => $v) {
|
||||
if ($lastError === $v && str_ends_with($k, '_ERROR')) {
|
||||
throw new RuntimeException('Matching failed with '.$k.'.');
|
||||
}
|
||||
}
|
||||
|
||||
throw new RuntimeException('Matching failed with unknown error code.');
|
||||
}
|
||||
} finally {
|
||||
restore_error_handler();
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$str->string = $string;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function reverse(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = strrev($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function slice(int $start = 0, ?int $length = null): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = substr($this->string, $start, $length ?? \PHP_INT_MAX);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function snake(): static
|
||||
{
|
||||
$str = $this->camel();
|
||||
$str->string = strtolower(preg_replace(['/([A-Z]+)([A-Z][a-z])/', '/([a-z\d])([A-Z])/'], '\1_\2', $str->string));
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function splice(string $replacement, int $start = 0, ?int $length = null): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = substr_replace($this->string, $replacement, $start, $length ?? \PHP_INT_MAX);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function split(string $delimiter, ?int $limit = null, ?int $flags = null): array
|
||||
{
|
||||
if (1 > $limit ??= \PHP_INT_MAX) {
|
||||
throw new InvalidArgumentException('Split limit must be a positive integer.');
|
||||
}
|
||||
|
||||
if ('' === $delimiter) {
|
||||
throw new InvalidArgumentException('Split delimiter is empty.');
|
||||
}
|
||||
|
||||
if (null !== $flags) {
|
||||
return parent::split($delimiter, $limit, $flags);
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$chunks = $this->ignoreCase
|
||||
? preg_split('{'.preg_quote($delimiter).'}iD', $this->string, $limit)
|
||||
: explode($delimiter, $this->string, $limit);
|
||||
|
||||
foreach ($chunks as &$chunk) {
|
||||
$str->string = $chunk;
|
||||
$chunk = clone $str;
|
||||
}
|
||||
|
||||
return $chunks;
|
||||
}
|
||||
|
||||
public function startsWith(string|iterable|AbstractString $prefix): bool
|
||||
{
|
||||
if ($prefix instanceof AbstractString) {
|
||||
$prefix = $prefix->string;
|
||||
} elseif (!\is_string($prefix)) {
|
||||
return parent::startsWith($prefix);
|
||||
}
|
||||
|
||||
return '' !== $prefix && 0 === ($this->ignoreCase ? strncasecmp($this->string, $prefix, \strlen($prefix)) : strncmp($this->string, $prefix, \strlen($prefix)));
|
||||
}
|
||||
|
||||
public function title(bool $allWords = false): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = $allWords ? ucwords($str->string) : ucfirst($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function toUnicodeString(?string $fromEncoding = null): UnicodeString
|
||||
{
|
||||
return new UnicodeString($this->toCodePointString($fromEncoding)->string);
|
||||
}
|
||||
|
||||
public function toCodePointString(?string $fromEncoding = null): CodePointString
|
||||
{
|
||||
$u = new CodePointString();
|
||||
|
||||
if (\in_array($fromEncoding, [null, 'utf8', 'utf-8', 'UTF8', 'UTF-8'], true) && preg_match('//u', $this->string)) {
|
||||
$u->string = $this->string;
|
||||
|
||||
return $u;
|
||||
}
|
||||
|
||||
set_error_handler(static fn ($t, $m) => throw new InvalidArgumentException($m));
|
||||
|
||||
try {
|
||||
try {
|
||||
$validEncoding = false !== mb_detect_encoding($this->string, $fromEncoding ?? 'Windows-1252', true);
|
||||
} catch (InvalidArgumentException $e) {
|
||||
if (!\function_exists('iconv')) {
|
||||
throw $e;
|
||||
}
|
||||
|
||||
$u->string = iconv($fromEncoding ?? 'Windows-1252', 'UTF-8', $this->string);
|
||||
|
||||
return $u;
|
||||
}
|
||||
} finally {
|
||||
restore_error_handler();
|
||||
}
|
||||
|
||||
if (!$validEncoding) {
|
||||
throw new InvalidArgumentException(\sprintf('Invalid "%s" string.', $fromEncoding ?? 'Windows-1252'));
|
||||
}
|
||||
|
||||
$u->string = mb_convert_encoding($this->string, 'UTF-8', $fromEncoding ?? 'Windows-1252');
|
||||
|
||||
return $u;
|
||||
}
|
||||
|
||||
public function trim(string $chars = " \t\n\r\0\x0B\x0C"): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = trim($str->string, $chars);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function trimEnd(string $chars = " \t\n\r\0\x0B\x0C"): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = rtrim($str->string, $chars);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function trimStart(string $chars = " \t\n\r\0\x0B\x0C"): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = ltrim($str->string, $chars);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function upper(): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = strtoupper($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function width(bool $ignoreAnsiDecoration = true): int
|
||||
{
|
||||
$string = preg_match('//u', $this->string) ? $this->string : preg_replace('/[\x80-\xFF]/', '?', $this->string);
|
||||
|
||||
return (new CodePointString($string))->width($ignoreAnsiDecoration);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,51 @@
|
||||
CHANGELOG
|
||||
=========
|
||||
|
||||
7.2
|
||||
---
|
||||
|
||||
* Add `TruncateMode` enum to handle more truncate methods
|
||||
* Add the `AbstractString::kebab()` method
|
||||
|
||||
7.1
|
||||
---
|
||||
|
||||
* Add `localeLower()`, `localeUpper()`, `localeTitle()` methods to `AbstractUnicodeString`
|
||||
|
||||
6.2
|
||||
---
|
||||
|
||||
* Add support for emoji in `AsciiSlugger`
|
||||
|
||||
5.4
|
||||
---
|
||||
|
||||
* Add `trimSuffix()` and `trimPrefix()` methods
|
||||
|
||||
5.3
|
||||
---
|
||||
|
||||
* Made `AsciiSlugger` fallback to parent locale's symbolsMap
|
||||
|
||||
5.2.0
|
||||
-----
|
||||
|
||||
* added a `FrenchInflector` class
|
||||
|
||||
5.1.0
|
||||
-----
|
||||
|
||||
* added the `AbstractString::reverse()` method
|
||||
* made `AbstractString::width()` follow POSIX.1-2001
|
||||
* added `LazyString` which provides memoizing stringable objects
|
||||
* The component is not marked as `@experimental` anymore
|
||||
* added the `s()` helper method to get either an `UnicodeString` or `ByteString` instance,
|
||||
depending of the input string UTF-8 compliancy
|
||||
* added `$cut` parameter to `Symfony\Component\String\AbstractString::truncate()`
|
||||
* added `AbstractString::containsAny()`
|
||||
* allow passing a string of custom characters to `ByteString::fromRandom()`
|
||||
|
||||
5.0.0
|
||||
-----
|
||||
|
||||
* added the component as experimental
|
||||
@@ -0,0 +1,586 @@
|
||||
<?php
|
||||
|
||||
/*
|
||||
* This file is part of the Symfony package.
|
||||
*
|
||||
* (c) Fabien Potencier <fabien@symfony.com>
|
||||
*
|
||||
* For the full copyright and license information, please view the LICENSE
|
||||
* file that was distributed with this source code.
|
||||
*/
|
||||
|
||||
namespace Symfony\Component\String\Inflector;
|
||||
|
||||
final class EnglishInflector implements InflectorInterface
|
||||
{
|
||||
/**
|
||||
* Map English plural to singular suffixes.
|
||||
*
|
||||
* @see http://english-zone.com/spelling/plurals.html
|
||||
*/
|
||||
private const PLURAL_MAP = [
|
||||
// First entry: plural suffix, reversed
|
||||
// Second entry: length of plural suffix
|
||||
// Third entry: Whether the suffix may succeed a vowel
|
||||
// Fourth entry: Whether the suffix may succeed a consonant
|
||||
// Fifth entry: singular suffix, normal
|
||||
|
||||
// bacteria (bacterium)
|
||||
['airetcab', 8, true, true, 'bacterium'],
|
||||
|
||||
// corpora (corpus)
|
||||
['aroproc', 7, true, true, 'corpus'],
|
||||
|
||||
// criteria (criterion)
|
||||
['airetirc', 8, true, true, 'criterion'],
|
||||
|
||||
// curricula (curriculum)
|
||||
['alucirruc', 9, true, true, 'curriculum'],
|
||||
|
||||
// quora (quorum)
|
||||
['arouq', 5, true, true, 'quorum'],
|
||||
|
||||
// genera (genus)
|
||||
['areneg', 6, true, true, 'genus'],
|
||||
|
||||
// media (medium)
|
||||
['aidem', 5, true, true, 'medium'],
|
||||
|
||||
// memoranda (memorandum)
|
||||
['adnaromem', 9, true, true, 'memorandum'],
|
||||
|
||||
// phenomena (phenomenon)
|
||||
['anemonehp', 9, true, true, 'phenomenon'],
|
||||
|
||||
// strata (stratum)
|
||||
['atarts', 6, true, true, 'stratum'],
|
||||
|
||||
// nebulae (nebula)
|
||||
['ea', 2, true, true, 'a'],
|
||||
|
||||
// services (service)
|
||||
['secivres', 8, true, true, 'service'],
|
||||
|
||||
// mice (mouse), lice (louse)
|
||||
['eci', 3, false, true, 'ouse'],
|
||||
|
||||
// geese (goose)
|
||||
['esee', 4, false, true, 'oose'],
|
||||
|
||||
// fungi (fungus), alumni (alumnus), syllabi (syllabus), radii (radius)
|
||||
['i', 1, true, true, 'us'],
|
||||
|
||||
// men (man), women (woman)
|
||||
['nem', 3, true, true, 'man'],
|
||||
|
||||
// children (child)
|
||||
['nerdlihc', 8, true, true, 'child'],
|
||||
|
||||
// oxen (ox)
|
||||
['nexo', 4, false, false, 'ox'],
|
||||
|
||||
// indices (index), appendices (appendix), prices (price)
|
||||
['seci', 4, false, true, ['ex', 'ix', 'ice']],
|
||||
|
||||
// codes (code)
|
||||
['sedoc', 5, false, true, 'code'],
|
||||
|
||||
// selfies (selfie)
|
||||
['seifles', 7, true, true, 'selfie'],
|
||||
|
||||
// zombies (zombie)
|
||||
['seibmoz', 7, true, true, 'zombie'],
|
||||
|
||||
// movies (movie)
|
||||
['seivom', 6, true, true, 'movie'],
|
||||
|
||||
// names (name)
|
||||
['seman', 5, true, false, 'name'],
|
||||
|
||||
// conspectuses (conspectus), prospectuses (prospectus)
|
||||
['sesutcep', 8, true, true, 'pectus'],
|
||||
|
||||
// feet (foot)
|
||||
['teef', 4, true, true, 'foot'],
|
||||
|
||||
// geese (goose)
|
||||
['eseeg', 5, true, true, 'goose'],
|
||||
|
||||
// teeth (tooth)
|
||||
['hteet', 5, true, true, 'tooth'],
|
||||
|
||||
// news (news)
|
||||
['swen', 4, true, true, 'news'],
|
||||
|
||||
// series (series)
|
||||
['seires', 6, true, true, 'series'],
|
||||
|
||||
// babies (baby)
|
||||
['sei', 3, false, true, 'y'],
|
||||
|
||||
// accesses (access), addresses (address), kisses (kiss)
|
||||
['sess', 4, true, false, 'ss'],
|
||||
|
||||
// statuses (status)
|
||||
['sesutats', 8, true, true, 'status'],
|
||||
|
||||
// article (articles), ancle (ancles)
|
||||
['sel', 3, true, true, 'le'],
|
||||
|
||||
// analyses (analysis), ellipses (ellipsis), fungi (fungus),
|
||||
// neuroses (neurosis), theses (thesis), emphases (emphasis),
|
||||
// oases (oasis), crises (crisis), houses (house), bases (base),
|
||||
// atlases (atlas)
|
||||
['ses', 3, true, true, ['s', 'se', 'sis']],
|
||||
|
||||
// objectives (objective), alternative (alternatives)
|
||||
['sevit', 5, true, true, 'tive'],
|
||||
|
||||
// drives (drive)
|
||||
['sevird', 6, false, true, 'drive'],
|
||||
|
||||
// lives (life), wives (wife)
|
||||
['sevi', 4, false, true, 'ife'],
|
||||
|
||||
// moves (move)
|
||||
['sevom', 5, true, true, 'move'],
|
||||
|
||||
// hooves (hoof), dwarves (dwarf), elves (elf), leaves (leaf), caves (cave), staves (staff)
|
||||
['sev', 3, true, true, ['f', 've', 'ff']],
|
||||
|
||||
// axes (axis), axes (ax), axes (axe)
|
||||
['sexa', 4, false, false, ['ax', 'axe', 'axis']],
|
||||
|
||||
// indexes (index), matrixes (matrix)
|
||||
['sex', 3, true, false, 'x'],
|
||||
|
||||
// quizzes (quiz)
|
||||
['sezz', 4, true, false, 'z'],
|
||||
|
||||
// bureaus (bureau)
|
||||
['suae', 4, false, true, 'eau'],
|
||||
|
||||
// fees (fee), trees (tree), employees (employee)
|
||||
['see', 3, true, true, 'ee'],
|
||||
|
||||
// edges (edge)
|
||||
['segd', 4, true, true, 'dge'],
|
||||
|
||||
// roses (rose), garages (garage), cassettes (cassette),
|
||||
// waltzes (waltz), heroes (hero), bushes (bush), arches (arch),
|
||||
// shoes (shoe)
|
||||
['se', 2, true, true, ['', 'e']],
|
||||
|
||||
// status (status)
|
||||
['sutats', 6, true, true, 'status'],
|
||||
|
||||
// tags (tag)
|
||||
['s', 1, true, true, ''],
|
||||
|
||||
// chateaux (chateau)
|
||||
['xuae', 4, false, true, 'eau'],
|
||||
|
||||
// people (person)
|
||||
['elpoep', 6, true, true, 'person'],
|
||||
];
|
||||
|
||||
/**
|
||||
* Map English singular to plural suffixes.
|
||||
*
|
||||
* @see http://english-zone.com/spelling/plurals.html
|
||||
*/
|
||||
private const SINGULAR_MAP = [
|
||||
// First entry: singular suffix, reversed
|
||||
// Second entry: length of singular suffix
|
||||
// Third entry: Whether the suffix may succeed a vowel
|
||||
// Fourth entry: Whether the suffix may succeed a consonant
|
||||
// Fifth entry: plural suffix, normal
|
||||
|
||||
// axes (axis)
|
||||
['sixa', 4, false, false, 'axes'],
|
||||
|
||||
// criterion (criteria)
|
||||
['airetirc', 8, false, false, 'criterion'],
|
||||
|
||||
// nebulae (nebula)
|
||||
['aluben', 6, false, false, 'nebulae'],
|
||||
|
||||
// children (child)
|
||||
['dlihc', 5, true, true, 'children'],
|
||||
|
||||
// prices (price)
|
||||
['eci', 3, false, true, 'ices'],
|
||||
|
||||
// services (service)
|
||||
['ecivres', 7, true, true, 'services'],
|
||||
|
||||
// lives (life), wives (wife)
|
||||
['efi', 3, false, true, 'ives'],
|
||||
|
||||
// selfies (selfie)
|
||||
['eifles', 6, true, true, 'selfies'],
|
||||
|
||||
// movies (movie)
|
||||
['eivom', 5, true, true, 'movies'],
|
||||
|
||||
// lice (louse)
|
||||
['esuol', 5, false, true, 'lice'],
|
||||
|
||||
// mice (mouse)
|
||||
['esuom', 5, false, true, 'mice'],
|
||||
|
||||
// geese (goose)
|
||||
['esoo', 4, false, true, 'eese'],
|
||||
|
||||
// houses (house), bases (base)
|
||||
['es', 2, true, true, 'ses'],
|
||||
|
||||
// geese (goose)
|
||||
['esoog', 5, true, true, 'geese'],
|
||||
|
||||
// caves (cave)
|
||||
['ev', 2, true, true, 'ves'],
|
||||
|
||||
// drives (drive)
|
||||
['evird', 5, false, true, 'drives'],
|
||||
|
||||
// objectives (objective), alternative (alternatives)
|
||||
['evit', 4, true, true, 'tives'],
|
||||
|
||||
// moves (move)
|
||||
['evom', 4, true, true, 'moves'],
|
||||
|
||||
// staves (staff)
|
||||
['ffats', 5, true, true, 'staves'],
|
||||
|
||||
// hooves (hoof), dwarves (dwarf), elves (elf), leaves (leaf)
|
||||
['ff', 2, true, true, 'ffs'],
|
||||
|
||||
// hooves (hoof), dwarves (dwarf), elves (elf), leaves (leaf)
|
||||
['f', 1, true, true, ['fs', 'ves']],
|
||||
|
||||
// arches (arch)
|
||||
['hc', 2, true, true, 'ches'],
|
||||
|
||||
// bushes (bush)
|
||||
['hs', 2, true, true, 'shes'],
|
||||
|
||||
// teeth (tooth)
|
||||
['htoot', 5, true, true, 'teeth'],
|
||||
|
||||
// albums (album)
|
||||
['mubla', 5, true, true, 'albums'],
|
||||
|
||||
// quorums (quorum)
|
||||
['murouq', 6, true, true, ['quora', 'quorums']],
|
||||
|
||||
// bacteria (bacterium), curricula (curriculum), media (medium), memoranda (memorandum), phenomena (phenomenon), strata (stratum)
|
||||
['mu', 2, true, true, 'a'],
|
||||
|
||||
// men (man), women (woman)
|
||||
['nam', 3, true, true, 'men'],
|
||||
|
||||
// people (person)
|
||||
['nosrep', 6, true, true, ['persons', 'people']],
|
||||
|
||||
// criteria (criterion)
|
||||
['noiretirc', 9, true, true, 'criteria'],
|
||||
|
||||
// phenomena (phenomenon)
|
||||
['nonemonehp', 10, true, true, 'phenomena'],
|
||||
|
||||
// echoes (echo)
|
||||
['ohce', 4, true, true, 'echoes'],
|
||||
|
||||
// heroes (hero)
|
||||
['oreh', 4, true, true, 'heroes'],
|
||||
|
||||
// atlases (atlas)
|
||||
['salta', 5, true, true, 'atlases'],
|
||||
|
||||
// aliases (alias)
|
||||
['saila', 5, true, true, 'aliases'],
|
||||
|
||||
// irises (iris)
|
||||
['siri', 4, true, true, 'irises'],
|
||||
|
||||
// analyses (analysis), ellipses (ellipsis), neuroses (neurosis)
|
||||
// theses (thesis), emphases (emphasis), oases (oasis),
|
||||
// crises (crisis)
|
||||
['sis', 3, true, true, 'ses'],
|
||||
|
||||
// accesses (access), addresses (address), kisses (kiss)
|
||||
['ss', 2, true, false, 'sses'],
|
||||
|
||||
// syllabi (syllabus)
|
||||
['suballys', 8, true, true, 'syllabi'],
|
||||
|
||||
// buses (bus)
|
||||
['sub', 3, true, true, 'buses'],
|
||||
|
||||
// circuses (circus)
|
||||
['suc', 3, true, true, 'cuses'],
|
||||
|
||||
// hippocampi (hippocampus)
|
||||
['supmacoppih', 11, false, false, 'hippocampi'],
|
||||
|
||||
// campuses (campus)
|
||||
['sup', 3, true, true, 'puses'],
|
||||
|
||||
// status (status)
|
||||
['sutats', 6, true, true, ['status', 'statuses']],
|
||||
|
||||
// conspectuses (conspectus), prospectuses (prospectus)
|
||||
['sutcep', 6, true, true, 'pectuses'],
|
||||
|
||||
// fungi (fungus), alumni (alumnus), syllabi (syllabus), radii (radius)
|
||||
['su', 2, true, true, 'i'],
|
||||
|
||||
// news (news)
|
||||
['swen', 4, true, true, 'news'],
|
||||
|
||||
// feet (foot)
|
||||
['toof', 4, true, true, 'feet'],
|
||||
|
||||
// chateaux (chateau), bureaus (bureau)
|
||||
['uae', 3, false, true, ['eaus', 'eaux']],
|
||||
|
||||
// oxen (ox)
|
||||
['xo', 2, false, false, 'oxen'],
|
||||
|
||||
// hoaxes (hoax)
|
||||
['xaoh', 4, true, false, 'hoaxes'],
|
||||
|
||||
// indices (index)
|
||||
['xedni', 5, false, true, ['indicies', 'indexes']],
|
||||
|
||||
// fax (faxes, faxxes)
|
||||
['xaf', 3, true, true, ['faxes', 'faxxes']],
|
||||
|
||||
// boxes (box)
|
||||
['xo', 2, false, true, 'oxes'],
|
||||
|
||||
// indexes (index), matrixes (matrix), appendices (appendix)
|
||||
['x', 1, true, false, ['ces', 'xes']],
|
||||
|
||||
// babies (baby)
|
||||
['y', 1, false, true, 'ies'],
|
||||
|
||||
// quizzes (quiz)
|
||||
['ziuq', 4, true, false, 'quizzes'],
|
||||
|
||||
// waltzes (waltz)
|
||||
['z', 1, true, true, 'zes'],
|
||||
];
|
||||
|
||||
/**
|
||||
* A list of words which should not be inflected, reversed.
|
||||
*/
|
||||
private const UNINFLECTED = [
|
||||
'',
|
||||
|
||||
// data
|
||||
'atad',
|
||||
|
||||
// deer
|
||||
'reed',
|
||||
|
||||
// equipment
|
||||
'tnempiuqe',
|
||||
|
||||
// feedback
|
||||
'kcabdeef',
|
||||
|
||||
// fish
|
||||
'hsif',
|
||||
|
||||
// health
|
||||
'htlaeh',
|
||||
|
||||
// history
|
||||
'yrotsih',
|
||||
|
||||
// info
|
||||
'ofni',
|
||||
|
||||
// information
|
||||
'noitamrofni',
|
||||
|
||||
// money
|
||||
'yenom',
|
||||
|
||||
// moose
|
||||
'esoom',
|
||||
|
||||
// series
|
||||
'seires',
|
||||
|
||||
// sheep
|
||||
'peehs',
|
||||
|
||||
// species
|
||||
'seiceps',
|
||||
|
||||
// traffic
|
||||
'ciffart',
|
||||
|
||||
// aircraft
|
||||
'tfarcria',
|
||||
|
||||
// hardware
|
||||
'erawdrah',
|
||||
];
|
||||
|
||||
public function singularize(string $plural): array
|
||||
{
|
||||
$pluralRev = strrev($plural);
|
||||
$lowerPluralRev = strtolower($pluralRev);
|
||||
$pluralLength = \strlen($lowerPluralRev);
|
||||
|
||||
// Check if the word is one which is not inflected, return early if so
|
||||
if (\in_array($lowerPluralRev, self::UNINFLECTED, true)) {
|
||||
return [$plural];
|
||||
}
|
||||
|
||||
// The outer loop iterates over the entries of the plural table
|
||||
// The inner loop $j iterates over the characters of the plural suffix
|
||||
// in the plural table to compare them with the characters of the actual
|
||||
// given plural suffix
|
||||
foreach (self::PLURAL_MAP as $map) {
|
||||
$suffix = $map[0];
|
||||
$suffixLength = $map[1];
|
||||
$j = 0;
|
||||
|
||||
// Compare characters in the plural table and of the suffix of the
|
||||
// given plural one by one
|
||||
while ($suffix[$j] === $lowerPluralRev[$j]) {
|
||||
// Let $j point to the next character
|
||||
++$j;
|
||||
|
||||
// Successfully compared the last character
|
||||
// Add an entry with the singular suffix to the singular array
|
||||
if ($j === $suffixLength) {
|
||||
// Is there any character preceding the suffix in the plural string?
|
||||
if ($j < $pluralLength) {
|
||||
$nextIsVowel = str_contains('aeiou', $lowerPluralRev[$j]);
|
||||
|
||||
if (!$map[2] && $nextIsVowel) {
|
||||
// suffix may not succeed a vowel but next char is one
|
||||
break;
|
||||
}
|
||||
|
||||
if (!$map[3] && !$nextIsVowel) {
|
||||
// suffix may not succeed a consonant but next char is one
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
$newBase = substr($plural, 0, $pluralLength - $suffixLength);
|
||||
$newSuffix = $map[4];
|
||||
|
||||
// Check whether the first character in the plural suffix
|
||||
// is uppercased. If yes, uppercase the first character in
|
||||
// the singular suffix too
|
||||
$firstUpper = ctype_upper($pluralRev[$j - 1]);
|
||||
|
||||
if (\is_array($newSuffix)) {
|
||||
$singulars = [];
|
||||
|
||||
foreach ($newSuffix as $newSuffixEntry) {
|
||||
$singulars[] = $newBase.($firstUpper ? ucfirst($newSuffixEntry) : $newSuffixEntry);
|
||||
}
|
||||
|
||||
return $singulars;
|
||||
}
|
||||
|
||||
return [$newBase.($firstUpper ? ucfirst($newSuffix) : $newSuffix)];
|
||||
}
|
||||
|
||||
// Suffix is longer than word
|
||||
if ($j === $pluralLength) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Assume that plural and singular is identical
|
||||
return [$plural];
|
||||
}
|
||||
|
||||
public function pluralize(string $singular): array
|
||||
{
|
||||
$singularRev = strrev($singular);
|
||||
$lowerSingularRev = strtolower($singularRev);
|
||||
$singularLength = \strlen($lowerSingularRev);
|
||||
|
||||
// Check if the word is one which is not inflected, return early if so
|
||||
if (\in_array($lowerSingularRev, self::UNINFLECTED, true)) {
|
||||
return [$singular];
|
||||
}
|
||||
|
||||
// The outer loop iterates over the entries of the singular table
|
||||
// The inner loop $j iterates over the characters of the singular suffix
|
||||
// in the singular table to compare them with the characters of the actual
|
||||
// given singular suffix
|
||||
foreach (self::SINGULAR_MAP as $map) {
|
||||
$suffix = $map[0];
|
||||
$suffixLength = $map[1];
|
||||
$j = 0;
|
||||
|
||||
// Compare characters in the singular table and of the suffix of the
|
||||
// given plural one by one
|
||||
|
||||
while ($suffix[$j] === $lowerSingularRev[$j]) {
|
||||
// Let $j point to the next character
|
||||
++$j;
|
||||
|
||||
// Successfully compared the last character
|
||||
// Add an entry with the plural suffix to the plural array
|
||||
if ($j === $suffixLength) {
|
||||
// Is there any character preceding the suffix in the plural string?
|
||||
if ($j < $singularLength) {
|
||||
$nextIsVowel = str_contains('aeiou', $lowerSingularRev[$j]);
|
||||
|
||||
if (!$map[2] && $nextIsVowel) {
|
||||
// suffix may not succeed a vowel but next char is one
|
||||
break;
|
||||
}
|
||||
|
||||
if (!$map[3] && !$nextIsVowel) {
|
||||
// suffix may not succeed a consonant but next char is one
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
$newBase = substr($singular, 0, $singularLength - $suffixLength);
|
||||
$newSuffix = $map[4];
|
||||
|
||||
// Check whether the first character in the singular suffix
|
||||
// is uppercased. If yes, uppercase the first character in
|
||||
// the singular suffix too
|
||||
$firstUpper = ctype_upper($singularRev[$j - 1]);
|
||||
|
||||
if (\is_array($newSuffix)) {
|
||||
$plurals = [];
|
||||
|
||||
foreach ($newSuffix as $newSuffixEntry) {
|
||||
$plurals[] = $newBase.($firstUpper ? ucfirst($newSuffixEntry) : $newSuffixEntry);
|
||||
}
|
||||
|
||||
return $plurals;
|
||||
}
|
||||
|
||||
return [$newBase.($firstUpper ? ucfirst($newSuffix) : $newSuffix)];
|
||||
}
|
||||
|
||||
// Suffix is longer than word
|
||||
if ($j === $singularLength) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Assume that plural is singular with a trailing `s`
|
||||
return [$singular.'s'];
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,145 @@
|
||||
<?php
|
||||
|
||||
/*
|
||||
* This file is part of the Symfony package.
|
||||
*
|
||||
* (c) Fabien Potencier <fabien@symfony.com>
|
||||
*
|
||||
* For the full copyright and license information, please view the LICENSE
|
||||
* file that was distributed with this source code.
|
||||
*/
|
||||
|
||||
namespace Symfony\Component\String;
|
||||
|
||||
/**
|
||||
* A string whose value is computed lazily by a callback.
|
||||
*
|
||||
* @author Nicolas Grekas <p@tchwork.com>
|
||||
*/
|
||||
class LazyString implements \Stringable, \JsonSerializable
|
||||
{
|
||||
private \Closure|string $value;
|
||||
|
||||
/**
|
||||
* @param callable|array $callback A callable or a [Closure, method] lazy-callable
|
||||
*/
|
||||
public static function fromCallable(callable|array $callback, mixed ...$arguments): static
|
||||
{
|
||||
if (\is_array($callback) && !\is_callable($callback) && !(($callback[0] ?? null) instanceof \Closure || 2 < \count($callback))) {
|
||||
throw new \TypeError(\sprintf('Argument 1 passed to "%s()" must be a callable or a [Closure, method] lazy-callable, "%s" given.', __METHOD__, '['.implode(', ', array_map('get_debug_type', $callback)).']'));
|
||||
}
|
||||
|
||||
$lazyString = new static();
|
||||
$lazyString->value = static function () use (&$callback, &$arguments): string {
|
||||
static $value;
|
||||
|
||||
if (null !== $arguments) {
|
||||
if (!\is_callable($callback)) {
|
||||
$callback[0] = $callback[0]();
|
||||
$callback[1] ??= '__invoke';
|
||||
}
|
||||
$value = $callback(...$arguments);
|
||||
$callback = !\is_scalar($value) && !$value instanceof \Stringable ? self::getPrettyName($callback) : 'callable';
|
||||
$arguments = null;
|
||||
}
|
||||
|
||||
return $value ?? '';
|
||||
};
|
||||
|
||||
return $lazyString;
|
||||
}
|
||||
|
||||
public static function fromStringable(string|int|float|bool|\Stringable $value): static
|
||||
{
|
||||
if (\is_object($value)) {
|
||||
return static::fromCallable($value->__toString(...));
|
||||
}
|
||||
|
||||
$lazyString = new static();
|
||||
$lazyString->value = (string) $value;
|
||||
|
||||
return $lazyString;
|
||||
}
|
||||
|
||||
/**
|
||||
* Tells whether the provided value can be cast to string.
|
||||
*/
|
||||
final public static function isStringable(mixed $value): bool
|
||||
{
|
||||
return \is_string($value) || $value instanceof \Stringable || \is_scalar($value);
|
||||
}
|
||||
|
||||
/**
|
||||
* Casts scalars and stringable objects to strings.
|
||||
*
|
||||
* @throws \TypeError When the provided value is not stringable
|
||||
*/
|
||||
final public static function resolve(\Stringable|string|int|float|bool $value): string
|
||||
{
|
||||
return $value;
|
||||
}
|
||||
|
||||
public function __toString(): string
|
||||
{
|
||||
if (\is_string($this->value)) {
|
||||
return $this->value;
|
||||
}
|
||||
|
||||
try {
|
||||
return $this->value = ($this->value)();
|
||||
} catch (\Throwable $e) {
|
||||
if (\TypeError::class === $e::class && __FILE__ === $e->getFile()) {
|
||||
$type = explode(', ', $e->getMessage());
|
||||
$type = substr(array_pop($type), 0, -\strlen(' returned'));
|
||||
$r = new \ReflectionFunction($this->value);
|
||||
$callback = $r->getStaticVariables()['callback'];
|
||||
|
||||
$e = new \TypeError(\sprintf('Return value of %s() passed to %s::fromCallable() must be of the type string, %s returned.', $callback, static::class, $type));
|
||||
}
|
||||
|
||||
throw $e;
|
||||
}
|
||||
}
|
||||
|
||||
public function __sleep(): array
|
||||
{
|
||||
$this->__toString();
|
||||
|
||||
return ['value'];
|
||||
}
|
||||
|
||||
public function jsonSerialize(): string
|
||||
{
|
||||
return $this->__toString();
|
||||
}
|
||||
|
||||
private function __construct()
|
||||
{
|
||||
}
|
||||
|
||||
private static function getPrettyName(callable $callback): string
|
||||
{
|
||||
if (\is_string($callback)) {
|
||||
return $callback;
|
||||
}
|
||||
|
||||
if (\is_array($callback)) {
|
||||
$class = \is_object($callback[0]) ? get_debug_type($callback[0]) : $callback[0];
|
||||
$method = $callback[1];
|
||||
} elseif ($callback instanceof \Closure) {
|
||||
$r = new \ReflectionFunction($callback);
|
||||
|
||||
if ($r->isAnonymous() || !$class = $r->getClosureCalledClass()) {
|
||||
return $r->name;
|
||||
}
|
||||
|
||||
$class = $class->name;
|
||||
$method = $r->name;
|
||||
} else {
|
||||
$class = get_debug_type($callback);
|
||||
$method = '__invoke';
|
||||
}
|
||||
|
||||
return $class.'::'.$method;
|
||||
}
|
||||
}
|
||||
+1175
File diff suppressed because it is too large
Load Diff
+1459
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,207 @@
|
||||
<?php
|
||||
|
||||
/*
|
||||
* This file is part of the Symfony package.
|
||||
*
|
||||
* (c) Fabien Potencier <fabien@symfony.com>
|
||||
*
|
||||
* For the full copyright and license information, please view the LICENSE
|
||||
* file that was distributed with this source code.
|
||||
*/
|
||||
|
||||
namespace Symfony\Component\String\Slugger;
|
||||
|
||||
use Symfony\Component\Emoji\EmojiTransliterator;
|
||||
use Symfony\Component\String\AbstractUnicodeString;
|
||||
use Symfony\Component\String\UnicodeString;
|
||||
use Symfony\Contracts\Translation\LocaleAwareInterface;
|
||||
|
||||
if (!interface_exists(LocaleAwareInterface::class)) {
|
||||
throw new \LogicException('You cannot use the "Symfony\Component\String\Slugger\AsciiSlugger" as the "symfony/translation-contracts" package is not installed. Try running "composer require symfony/translation-contracts".');
|
||||
}
|
||||
|
||||
/**
|
||||
* @author Titouan Galopin <galopintitouan@gmail.com>
|
||||
*/
|
||||
class AsciiSlugger implements SluggerInterface, LocaleAwareInterface
|
||||
{
|
||||
private const LOCALE_TO_TRANSLITERATOR_ID = [
|
||||
'am' => 'Amharic-Latin',
|
||||
'ar' => 'Arabic-Latin',
|
||||
'az' => 'Azerbaijani-Latin',
|
||||
'be' => 'Belarusian-Latin',
|
||||
'bg' => 'Bulgarian-Latin',
|
||||
'bn' => 'Bengali-Latin',
|
||||
'de' => 'de-ASCII',
|
||||
'el' => 'Greek-Latin',
|
||||
'fa' => 'Persian-Latin',
|
||||
'he' => 'Hebrew-Latin',
|
||||
'hy' => 'Armenian-Latin',
|
||||
'ka' => 'Georgian-Latin',
|
||||
'kk' => 'Kazakh-Latin',
|
||||
'ky' => 'Kirghiz-Latin',
|
||||
'ko' => 'Korean-Latin',
|
||||
'mk' => 'Macedonian-Latin',
|
||||
'mn' => 'Mongolian-Latin',
|
||||
'or' => 'Oriya-Latin',
|
||||
'ps' => 'Pashto-Latin',
|
||||
'ru' => 'Russian-Latin',
|
||||
'sr' => 'Serbian-Latin',
|
||||
'sr_Cyrl' => 'Serbian-Latin',
|
||||
'th' => 'Thai-Latin',
|
||||
'tk' => 'Turkmen-Latin',
|
||||
'uk' => 'Ukrainian-Latin',
|
||||
'uz' => 'Uzbek-Latin',
|
||||
'zh' => 'Han-Latin',
|
||||
];
|
||||
|
||||
private \Closure|array $symbolsMap = [
|
||||
'en' => ['@' => 'at', '&' => 'and'],
|
||||
];
|
||||
private bool|string $emoji = false;
|
||||
|
||||
/**
|
||||
* Cache of transliterators per locale.
|
||||
*
|
||||
* @var \Transliterator[]
|
||||
*/
|
||||
private array $transliterators = [];
|
||||
|
||||
public function __construct(
|
||||
private ?string $defaultLocale = null,
|
||||
array|\Closure|null $symbolsMap = null,
|
||||
) {
|
||||
$this->symbolsMap = $symbolsMap ?? $this->symbolsMap;
|
||||
}
|
||||
|
||||
public function setLocale(string $locale): void
|
||||
{
|
||||
$this->defaultLocale = $locale;
|
||||
}
|
||||
|
||||
public function getLocale(): string
|
||||
{
|
||||
return $this->defaultLocale;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param bool|string $emoji true will use the same locale,
|
||||
* false will disable emoji,
|
||||
* and a string to use a specific locale
|
||||
*/
|
||||
public function withEmoji(bool|string $emoji = true): static
|
||||
{
|
||||
if (false !== $emoji && !class_exists(EmojiTransliterator::class)) {
|
||||
throw new \LogicException(\sprintf('You cannot use the "%s()" method as the "symfony/emoji" package is not installed. Try running "composer require symfony/emoji".', __METHOD__));
|
||||
}
|
||||
|
||||
$new = clone $this;
|
||||
$new->emoji = $emoji;
|
||||
|
||||
return $new;
|
||||
}
|
||||
|
||||
public function slug(string $string, string $separator = '-', ?string $locale = null): AbstractUnicodeString
|
||||
{
|
||||
$locale ??= $this->defaultLocale;
|
||||
|
||||
$transliterator = [];
|
||||
if ($locale && ('de' === $locale || str_starts_with($locale, 'de_'))) {
|
||||
// Use the shortcut for German in UnicodeString::ascii() if possible (faster and no requirement on intl)
|
||||
$transliterator = ['de-ASCII'];
|
||||
} elseif (\function_exists('transliterator_transliterate') && $locale) {
|
||||
$transliterator = (array) $this->createTransliterator($locale);
|
||||
}
|
||||
|
||||
if ($emojiTransliterator = $this->createEmojiTransliterator($locale)) {
|
||||
$transliterator[] = $emojiTransliterator;
|
||||
}
|
||||
|
||||
if ($this->symbolsMap instanceof \Closure) {
|
||||
// If the symbols map is passed as a closure, there is no need to fallback to the parent locale
|
||||
// as the closure can just provide substitutions for all locales of interest.
|
||||
$symbolsMap = $this->symbolsMap;
|
||||
array_unshift($transliterator, static fn ($s) => $symbolsMap($s, $locale));
|
||||
}
|
||||
|
||||
$unicodeString = (new UnicodeString($string))->ascii($transliterator);
|
||||
|
||||
if (\is_array($this->symbolsMap)) {
|
||||
$map = null;
|
||||
if (isset($this->symbolsMap[$locale])) {
|
||||
$map = $this->symbolsMap[$locale];
|
||||
} else {
|
||||
$parent = self::getParentLocale($locale);
|
||||
if ($parent && isset($this->symbolsMap[$parent])) {
|
||||
$map = $this->symbolsMap[$parent];
|
||||
}
|
||||
}
|
||||
if ($map) {
|
||||
foreach ($map as $char => $replace) {
|
||||
$unicodeString = $unicodeString->replace($char, ' '.$replace.' ');
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return $unicodeString
|
||||
->replaceMatches('/[^A-Za-z0-9]++/', $separator)
|
||||
->trim($separator)
|
||||
;
|
||||
}
|
||||
|
||||
private function createTransliterator(string $locale): ?\Transliterator
|
||||
{
|
||||
if (\array_key_exists($locale, $this->transliterators)) {
|
||||
return $this->transliterators[$locale];
|
||||
}
|
||||
|
||||
// Exact locale supported, cache and return
|
||||
if ($id = self::LOCALE_TO_TRANSLITERATOR_ID[$locale] ?? null) {
|
||||
return $this->transliterators[$locale] = \Transliterator::create($id.'/BGN') ?? \Transliterator::create($id);
|
||||
}
|
||||
|
||||
// Locale not supported and no parent, fallback to any-latin
|
||||
if (!$parent = self::getParentLocale($locale)) {
|
||||
return $this->transliterators[$locale] = null;
|
||||
}
|
||||
|
||||
// Try to use the parent locale (ie. try "de" for "de_AT") and cache both locales
|
||||
if ($id = self::LOCALE_TO_TRANSLITERATOR_ID[$parent] ?? null) {
|
||||
$transliterator = \Transliterator::create($id.'/BGN') ?? \Transliterator::create($id);
|
||||
}
|
||||
|
||||
return $this->transliterators[$locale] = $this->transliterators[$parent] = $transliterator ?? null;
|
||||
}
|
||||
|
||||
private function createEmojiTransliterator(?string $locale): ?EmojiTransliterator
|
||||
{
|
||||
if (\is_string($this->emoji)) {
|
||||
$locale = $this->emoji;
|
||||
} elseif (!$this->emoji) {
|
||||
return null;
|
||||
}
|
||||
|
||||
while (null !== $locale) {
|
||||
try {
|
||||
return EmojiTransliterator::create("emoji-$locale");
|
||||
} catch (\IntlException) {
|
||||
$locale = self::getParentLocale($locale);
|
||||
}
|
||||
}
|
||||
|
||||
return null;
|
||||
}
|
||||
|
||||
private static function getParentLocale(?string $locale): ?string
|
||||
{
|
||||
if (!$locale) {
|
||||
return null;
|
||||
}
|
||||
if (false === $str = strrchr($locale, '_')) {
|
||||
// no parent locale
|
||||
return null;
|
||||
}
|
||||
|
||||
return substr($locale, 0, -\strlen($str));
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,382 @@
|
||||
<?php
|
||||
|
||||
/*
|
||||
* This file is part of the Symfony package.
|
||||
*
|
||||
* (c) Fabien Potencier <fabien@symfony.com>
|
||||
*
|
||||
* For the full copyright and license information, please view the LICENSE
|
||||
* file that was distributed with this source code.
|
||||
*/
|
||||
|
||||
namespace Symfony\Component\String;
|
||||
|
||||
use Symfony\Component\String\Exception\ExceptionInterface;
|
||||
use Symfony\Component\String\Exception\InvalidArgumentException;
|
||||
|
||||
/**
|
||||
* Represents a string of Unicode grapheme clusters encoded as UTF-8.
|
||||
*
|
||||
* A letter followed by combining characters (accents typically) form what Unicode defines
|
||||
* as a grapheme cluster: a character as humans mean it in written texts. This class knows
|
||||
* about the concept and won't split a letter apart from its combining accents. It also
|
||||
* ensures all string comparisons happen on their canonically-composed representation,
|
||||
* ignoring e.g. the order in which accents are listed when a letter has many of them.
|
||||
*
|
||||
* @see https://unicode.org/reports/tr15/
|
||||
*
|
||||
* @author Nicolas Grekas <p@tchwork.com>
|
||||
* @author Hugo Hamon <hugohamon@neuf.fr>
|
||||
*
|
||||
* @throws ExceptionInterface
|
||||
*/
|
||||
class UnicodeString extends AbstractUnicodeString
|
||||
{
|
||||
public function __construct(string $string = '')
|
||||
{
|
||||
if ('' === $string || normalizer_is_normalized($this->string = $string)) {
|
||||
return;
|
||||
}
|
||||
|
||||
if (false === $string = normalizer_normalize($string)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
$this->string = $string;
|
||||
}
|
||||
|
||||
public function append(string ...$suffix): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = $this->string.(1 >= \count($suffix) ? ($suffix[0] ?? '') : implode('', $suffix));
|
||||
|
||||
if (normalizer_is_normalized($str->string)) {
|
||||
return $str;
|
||||
}
|
||||
|
||||
if (false === $string = normalizer_normalize($str->string)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
$str->string = $string;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function chunk(int $length = 1): array
|
||||
{
|
||||
if (1 > $length) {
|
||||
throw new InvalidArgumentException('The chunk length must be greater than zero.');
|
||||
}
|
||||
|
||||
if ('' === $this->string) {
|
||||
return [];
|
||||
}
|
||||
|
||||
$rx = '/(';
|
||||
while (65535 < $length) {
|
||||
$rx .= '\X{65535}';
|
||||
$length -= 65535;
|
||||
}
|
||||
$rx .= '\X{'.$length.'})/u';
|
||||
|
||||
$str = clone $this;
|
||||
$chunks = [];
|
||||
|
||||
foreach (preg_split($rx, $this->string, -1, \PREG_SPLIT_DELIM_CAPTURE | \PREG_SPLIT_NO_EMPTY) as $chunk) {
|
||||
$str->string = $chunk;
|
||||
$chunks[] = clone $str;
|
||||
}
|
||||
|
||||
return $chunks;
|
||||
}
|
||||
|
||||
public function endsWith(string|iterable|AbstractString $suffix): bool
|
||||
{
|
||||
if ($suffix instanceof AbstractString) {
|
||||
$suffix = $suffix->string;
|
||||
} elseif (!\is_string($suffix)) {
|
||||
return parent::endsWith($suffix);
|
||||
}
|
||||
|
||||
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
|
||||
normalizer_is_normalized($suffix, $form) ?: $suffix = normalizer_normalize($suffix, $form);
|
||||
|
||||
if ('' === $suffix || false === $suffix) {
|
||||
return false;
|
||||
}
|
||||
|
||||
if ($this->ignoreCase) {
|
||||
return 0 === mb_stripos(grapheme_extract($this->string, \strlen($suffix), \GRAPHEME_EXTR_MAXBYTES, \strlen($this->string) - \strlen($suffix)), $suffix, 0, 'UTF-8');
|
||||
}
|
||||
|
||||
return $suffix === grapheme_extract($this->string, \strlen($suffix), \GRAPHEME_EXTR_MAXBYTES, \strlen($this->string) - \strlen($suffix));
|
||||
}
|
||||
|
||||
public function equalsTo(string|iterable|AbstractString $string): bool
|
||||
{
|
||||
if ($string instanceof AbstractString) {
|
||||
$string = $string->string;
|
||||
} elseif (!\is_string($string)) {
|
||||
return parent::equalsTo($string);
|
||||
}
|
||||
|
||||
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
|
||||
normalizer_is_normalized($string, $form) ?: $string = normalizer_normalize($string, $form);
|
||||
|
||||
if ('' !== $string && false !== $string && $this->ignoreCase) {
|
||||
return \strlen($string) === \strlen($this->string) && 0 === mb_stripos($this->string, $string, 0, 'UTF-8');
|
||||
}
|
||||
|
||||
return $string === $this->string;
|
||||
}
|
||||
|
||||
public function indexOf(string|iterable|AbstractString $needle, int $offset = 0): ?int
|
||||
{
|
||||
if ($needle instanceof AbstractString) {
|
||||
$needle = $needle->string;
|
||||
} elseif (!\is_string($needle)) {
|
||||
return parent::indexOf($needle, $offset);
|
||||
}
|
||||
|
||||
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
|
||||
normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form);
|
||||
|
||||
if ('' === $needle || false === $needle) {
|
||||
return null;
|
||||
}
|
||||
|
||||
try {
|
||||
$i = $this->ignoreCase ? grapheme_stripos($this->string, $needle, $offset) : grapheme_strpos($this->string, $needle, $offset);
|
||||
} catch (\ValueError) {
|
||||
return null;
|
||||
}
|
||||
|
||||
return false === $i ? null : $i;
|
||||
}
|
||||
|
||||
public function indexOfLast(string|iterable|AbstractString $needle, int $offset = 0): ?int
|
||||
{
|
||||
if ($needle instanceof AbstractString) {
|
||||
$needle = $needle->string;
|
||||
} elseif (!\is_string($needle)) {
|
||||
return parent::indexOfLast($needle, $offset);
|
||||
}
|
||||
|
||||
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
|
||||
normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form);
|
||||
|
||||
if ('' === $needle || false === $needle) {
|
||||
return null;
|
||||
}
|
||||
|
||||
$string = $this->string;
|
||||
|
||||
if (0 > $offset) {
|
||||
// workaround https://bugs.php.net/74264
|
||||
if (0 > $offset += grapheme_strlen($needle)) {
|
||||
$string = grapheme_substr($string, 0, $offset);
|
||||
}
|
||||
$offset = 0;
|
||||
}
|
||||
|
||||
$i = $this->ignoreCase ? grapheme_strripos($string, $needle, $offset) : grapheme_strrpos($string, $needle, $offset);
|
||||
|
||||
return false === $i ? null : $i;
|
||||
}
|
||||
|
||||
public function join(array $strings, ?string $lastGlue = null): static
|
||||
{
|
||||
$str = parent::join($strings, $lastGlue);
|
||||
normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function length(): int
|
||||
{
|
||||
return grapheme_strlen($this->string);
|
||||
}
|
||||
|
||||
public function normalize(int $form = self::NFC): static
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
if (\in_array($form, [self::NFC, self::NFKC], true)) {
|
||||
normalizer_is_normalized($str->string, $form) ?: $str->string = normalizer_normalize($str->string, $form);
|
||||
} elseif (!\in_array($form, [self::NFD, self::NFKD], true)) {
|
||||
throw new InvalidArgumentException('Unsupported normalization form.');
|
||||
} elseif (!normalizer_is_normalized($str->string, $form)) {
|
||||
$str->string = normalizer_normalize($str->string, $form);
|
||||
$str->ignoreCase = null;
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function prepend(string ...$prefix): static
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = (1 >= \count($prefix) ? ($prefix[0] ?? '') : implode('', $prefix)).$this->string;
|
||||
|
||||
if (normalizer_is_normalized($str->string)) {
|
||||
return $str;
|
||||
}
|
||||
|
||||
if (false === $string = normalizer_normalize($str->string)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
$str->string = $string;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function replace(string $from, string $to): static
|
||||
{
|
||||
$str = clone $this;
|
||||
normalizer_is_normalized($from) ?: $from = normalizer_normalize($from);
|
||||
|
||||
if ('' !== $from && false !== $from) {
|
||||
$tail = $str->string;
|
||||
$result = '';
|
||||
$indexOf = $this->ignoreCase ? 'grapheme_stripos' : 'grapheme_strpos';
|
||||
|
||||
while ('' !== $tail && false !== $i = $indexOf($tail, $from)) {
|
||||
$slice = grapheme_substr($tail, 0, $i);
|
||||
$result .= $slice.$to;
|
||||
$tail = substr($tail, \strlen($slice) + \strlen($from));
|
||||
}
|
||||
|
||||
$str->string = $result.$tail;
|
||||
|
||||
if (normalizer_is_normalized($str->string)) {
|
||||
return $str;
|
||||
}
|
||||
|
||||
if (false === $string = normalizer_normalize($str->string)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
$str->string = $string;
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function replaceMatches(string $fromRegexp, string|callable $to): static
|
||||
{
|
||||
$str = parent::replaceMatches($fromRegexp, $to);
|
||||
normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function slice(int $start = 0, ?int $length = null): static
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
$str->string = (string) grapheme_substr($this->string, $start, $length ?? 2147483647);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function splice(string $replacement, int $start = 0, ?int $length = null): static
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
$start = $start ? \strlen(grapheme_substr($this->string, 0, $start)) : 0;
|
||||
$length = $length ? \strlen(grapheme_substr($this->string, $start, $length)) : $length;
|
||||
$str->string = substr_replace($this->string, $replacement, $start, $length ?? 2147483647);
|
||||
|
||||
if (normalizer_is_normalized($str->string)) {
|
||||
return $str;
|
||||
}
|
||||
|
||||
if (false === $string = normalizer_normalize($str->string)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
$str->string = $string;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function split(string $delimiter, ?int $limit = null, ?int $flags = null): array
|
||||
{
|
||||
if (1 > $limit ??= 2147483647) {
|
||||
throw new InvalidArgumentException('Split limit must be a positive integer.');
|
||||
}
|
||||
|
||||
if ('' === $delimiter) {
|
||||
throw new InvalidArgumentException('Split delimiter is empty.');
|
||||
}
|
||||
|
||||
if (null !== $flags) {
|
||||
return parent::split($delimiter.'u', $limit, $flags);
|
||||
}
|
||||
|
||||
normalizer_is_normalized($delimiter) ?: $delimiter = normalizer_normalize($delimiter);
|
||||
|
||||
if (false === $delimiter) {
|
||||
throw new InvalidArgumentException('Split delimiter is not a valid UTF-8 string.');
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$tail = $this->string;
|
||||
$chunks = [];
|
||||
$indexOf = $this->ignoreCase ? 'grapheme_stripos' : 'grapheme_strpos';
|
||||
|
||||
while (1 < $limit && false !== $i = $indexOf($tail, $delimiter)) {
|
||||
$str->string = grapheme_substr($tail, 0, $i);
|
||||
$chunks[] = clone $str;
|
||||
$tail = substr($tail, \strlen($str->string) + \strlen($delimiter));
|
||||
--$limit;
|
||||
}
|
||||
|
||||
$str->string = $tail;
|
||||
$chunks[] = clone $str;
|
||||
|
||||
return $chunks;
|
||||
}
|
||||
|
||||
public function startsWith(string|iterable|AbstractString $prefix): bool
|
||||
{
|
||||
if ($prefix instanceof AbstractString) {
|
||||
$prefix = $prefix->string;
|
||||
} elseif (!\is_string($prefix)) {
|
||||
return parent::startsWith($prefix);
|
||||
}
|
||||
|
||||
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
|
||||
normalizer_is_normalized($prefix, $form) ?: $prefix = normalizer_normalize($prefix, $form);
|
||||
|
||||
if ('' === $prefix || false === $prefix) {
|
||||
return false;
|
||||
}
|
||||
|
||||
if ($this->ignoreCase) {
|
||||
return 0 === mb_stripos(grapheme_extract($this->string, \strlen($prefix), \GRAPHEME_EXTR_MAXBYTES), $prefix, 0, 'UTF-8');
|
||||
}
|
||||
|
||||
return $prefix === grapheme_extract($this->string, \strlen($prefix), \GRAPHEME_EXTR_MAXBYTES);
|
||||
}
|
||||
|
||||
public function __wakeup(): void
|
||||
{
|
||||
if (!\is_string($this->string)) {
|
||||
throw new \BadMethodCallException('Cannot unserialize '.__CLASS__);
|
||||
}
|
||||
|
||||
normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string);
|
||||
}
|
||||
|
||||
public function __clone()
|
||||
{
|
||||
if (null === $this->ignoreCase) {
|
||||
normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string);
|
||||
}
|
||||
|
||||
$this->ignoreCase = false;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"name": "symfony/string",
|
||||
"type": "library",
|
||||
"description": "Provides an object-oriented API to strings and deals with bytes, UTF-8 code points and grapheme clusters in a unified way",
|
||||
"keywords": ["string", "utf8", "utf-8", "grapheme", "i18n", "unicode"],
|
||||
"homepage": "https://symfony.com",
|
||||
"license": "MIT",
|
||||
"authors": [
|
||||
{
|
||||
"name": "Nicolas Grekas",
|
||||
"email": "p@tchwork.com"
|
||||
},
|
||||
{
|
||||
"name": "Symfony Community",
|
||||
"homepage": "https://symfony.com/contributors"
|
||||
}
|
||||
],
|
||||
"require": {
|
||||
"php": ">=8.2",
|
||||
"symfony/polyfill-ctype": "~1.8",
|
||||
"symfony/polyfill-intl-grapheme": "~1.0",
|
||||
"symfony/polyfill-intl-normalizer": "~1.0",
|
||||
"symfony/polyfill-mbstring": "~1.0"
|
||||
},
|
||||
"require-dev": {
|
||||
"symfony/error-handler": "^6.4|^7.0",
|
||||
"symfony/emoji": "^7.1",
|
||||
"symfony/http-client": "^6.4|^7.0",
|
||||
"symfony/intl": "^6.4|^7.0",
|
||||
"symfony/translation-contracts": "^2.5|^3.0",
|
||||
"symfony/var-exporter": "^6.4|^7.0"
|
||||
},
|
||||
"conflict": {
|
||||
"symfony/translation-contracts": "<2.5"
|
||||
},
|
||||
"autoload": {
|
||||
"psr-4": { "Symfony\\Component\\String\\": "" },
|
||||
"files": [ "Resources/functions.php" ],
|
||||
"exclude-from-classmap": [
|
||||
"/Tests/"
|
||||
]
|
||||
},
|
||||
"minimum-stability": "dev"
|
||||
}
|
||||
Reference in New Issue
Block a user