feature #33553 [String] a new component for object-oriented strings management with an abstract unit system (nicolas-grekas, hhamon, gharlan)
This PR was merged into the 5.0-dev branch. Discussion ---------- [String] a new component for object-oriented strings management with an abstract unit system | Q | A | ------------- | --- | Branch? | master | Bug fix? | no | New feature? | yes | Deprecations? | no | Tickets | - | License | MIT | Doc PR | - This is a reboot of #22184 (thanks @hhamon for working on it) and a generalization of my previous work on the topic ([patchwork/utf8](https://github.com/tchwork/utf8)). Unlike existing libraries (including `patchwork/utf8`), this component provides a unified API for the 3 unit systems of strings: bytes, code points and grapheme clusters. The unified API is defined by the `AbstractString` class. It has 2 direct child classes: `BinaryString` and `AbstractUnicodeString`, itself extended by `Utf8String` and `GraphemeString`. All objects are immutable and provide clear edge-case semantics, using exceptions and/or (nullable) types! Two helper functions are provided to create such strings: ```php new GraphemeString('foo') == u('foo'); // when dealing with Unicode, prefer grapheme units new BinaryString('foo') == b('foo'); ``` `GraphemeString` is the most linguistic-friendly variant of them, which means it's the one ppl should use most of the time *when dealing with written text*. Future ideas: - improve tests - add more docblocks (only where they'd add value!) - consider adding more methods in the string API (`is*()?`, `*Encode()`?, etc.) - first class Emoji support - merge the Inflector component into this one - use `width()` to improve `truncate()` and `wordwrap()` - move method `slug()` to a dedicated locale-aware service class - propose your ideas (send PRs after merge) Out of (current) scope: - what [intl](https://php.net/intl) provides (collations, transliterations, confusables, segmentation, etc) Here is the unified API I'm proposing in this PR, borrowed from looking at many existing libraries, but also Java, Python, JavaScript and Go. ```php function __construct(string $string = ''); static function unwrap(array $values): array static function wrap(array $values): array function after($needle, bool $includeNeedle = false, int $offset = 0): self; function afterLast($needle, bool $includeNeedle = false, int $offset = 0): self; function append(string ...$suffix): self; function before($needle, bool $includeNeedle = false, int $offset = 0): self; function beforeLast($needle, bool $includeNeedle = false, int $offset = 0): self; function camel(): self; function chunk(int $length = 1): array; function collapseWhitespace(): self function endsWith($suffix): bool; function ensureEnd(string $suffix): self; function ensureStart(string $prefix): self; function equalsTo($string): bool; function folded(): self; function ignoreCase(): self; function indexOf($needle, int $offset = 0): ?int; function indexOfLast($needle, int $offset = 0): ?int; function isEmpty(): bool; function join(array $strings): self; function jsonSerialize(): string; function length(): int; function lower(): self; function match(string $pattern, int $flags = 0, int $offset = 0): array; function padBoth(int $length, string $padStr = ' '): self; function padEnd(int $length, string $padStr = ' '): self; function padStart(int $length, string $padStr = ' '): self; function prepend(string ...$prefix): self; function repeat(int $multiplier): self; function replace(string $from, string $to): self; function replaceMatches(string $fromPattern, $to): self; function slice(int $start = 0, int $length = null): self; function snake(): self; function splice(string $replacement, int $start = 0, int $length = null): self; function split(string $delimiter, int $limit = null, int $flags = null): array; function startsWith($prefix): bool; function title(bool $allWords = false): self; function toBinary(string $toEncoding = null): BinaryString; function toGrapheme(): GraphemeString; function toUtf8(): Utf8String; function trim(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): self; function trimEnd(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): self; function trimStart(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): self; function truncate(int $length, string $ellipsis = ''): self; function upper(): self; function width(bool $ignoreAnsiDecoration = true): int; function wordwrap(int $width = 75, string $break = "\n", bool $cut = false): self; function __clone(); function __toString(): string; ``` `AbstractUnicodeString` adds these: ```php static function fromCodePoints(int ...$codes): self; function ascii(array $rules = []): self; function codePoint(int $index = 0): ?int; function folded(bool $compat = true): parent; function normalize(int $form = self::NFC): self; function slug(string $separator = '-'): self; ``` and `BinaryString`: ```php static function fromRandom(int $length = 16): self; function byteCode(int $index = 0): ?int; function isUtf8(): bool; function toUtf8(string $fromEncoding = null): Utf8String; function toGrapheme(string $fromEncoding = null): GraphemeString; ``` Case insensitive operations are done with the `ignoreCase()` method. e.g. `b('abc')->ignoreCase()->indexOf('B')` will return `1`. For reference, CLDR transliterations (used in the `ascii()` method) are defined here: https://github.com/unicode-org/cldr/tree/master/common/transforms Commits -------dd8745aced[String] add more tests82a00956bc[String] add tests012e92a772[String] a new component for object-oriented strings management with an abstract unit system
This commit is contained in:
Fabien Potencier
commit
5d154fb304
|
|
@ -270,7 +270,7 @@ install:
|
|||
(cd src/Symfony/Component/HttpFoundation; mv composer.bak composer.json)
|
||||
COMPONENTS=$(git diff --name-only src/ | grep composer.json || true)
|
||||
|
||||
if [[ $COMPONENTS && $LEGACY && $TRAVIS_PULL_REQUEST != false ]]; then
|
||||
if [[ $COMPONENTS && $LEGACY && $TRAVIS_BRANCH != master && $TRAVIS_PULL_REQUEST != false ]]; then
|
||||
export FLIP='🙃'
|
||||
SYMFONY_VERSION=$(echo $SYMFONY_VERSION | awk '{print $1 - 1}')
|
||||
echo -e "\\n\\e[33;1mChecking out Symfony $SYMFONY_VERSION and running tests with patched components as deps\\e[0m"
|
||||
|
|
|
|||
|
|
@ -27,8 +27,10 @@
|
|||
"psr/log": "~1.0",
|
||||
"symfony/contracts": "^1.1.7|^2",
|
||||
"symfony/polyfill-ctype": "~1.8",
|
||||
"symfony/polyfill-intl-grapheme": "~1.0",
|
||||
"symfony/polyfill-intl-icu": "~1.0",
|
||||
"symfony/polyfill-intl-idn": "^1.10",
|
||||
"symfony/polyfill-intl-normalizer": "~1.0",
|
||||
"symfony/polyfill-mbstring": "~1.0",
|
||||
"symfony/polyfill-php73": "^1.11"
|
||||
},
|
||||
|
|
@ -82,6 +84,7 @@
|
|||
"symfony/sendgrid-mailer": "self.version",
|
||||
"symfony/serializer": "self.version",
|
||||
"symfony/stopwatch": "self.version",
|
||||
"symfony/string": "self.version",
|
||||
"symfony/templating": "self.version",
|
||||
"symfony/translation": "self.version",
|
||||
"symfony/twig-bridge": "self.version",
|
||||
|
|
@ -144,7 +147,10 @@
|
|||
]
|
||||
},
|
||||
"autoload-dev": {
|
||||
"files": [ "src/Symfony/Component/VarDumper/Resources/functions/dump.php" ]
|
||||
"files": [
|
||||
"src/Symfony/Component/String/Resources/functions.php",
|
||||
"src/Symfony/Component/VarDumper/Resources/functions/dump.php"
|
||||
]
|
||||
},
|
||||
"repositories": [
|
||||
{
|
||||
|
|
|
|||
|
|
@ -0,0 +1,2 @@
|
|||
/Tests export-ignore
|
||||
/phpunit.xml.dist export-ignore
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
composer.lock
|
||||
phpunit.xml
|
||||
vendor/
|
||||
|
|
@ -0,0 +1,689 @@
|
|||
<?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
|
||||
*
|
||||
* @experimental in 5.0
|
||||
*/
|
||||
abstract class AbstractString implements \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 = '';
|
||||
protected $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 => $v) {
|
||||
++$i;
|
||||
|
||||
if (\is_string($k) && '' !== $k && $k !== $j = (string) new static($k)) {
|
||||
$keys = $keys ?? array_keys($values);
|
||||
array_splice($keys, $i, 1, [$j]);
|
||||
}
|
||||
|
||||
if (\is_string($v)) {
|
||||
$values[$k] = new static($v);
|
||||
} elseif (\is_array($v) && $values[$k] !== $v = static::wrap($v)) {
|
||||
$values[$k] = $v;
|
||||
}
|
||||
}
|
||||
|
||||
return null !== $keys ? array_combine($keys, $values) : $values;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $needle
|
||||
*
|
||||
* @return static
|
||||
*/
|
||||
public function after($needle, bool $includeNeedle = false, int $offset = 0): self
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = '';
|
||||
$i = \PHP_INT_MAX;
|
||||
|
||||
foreach ((array) $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[] $needle
|
||||
*
|
||||
* @return static
|
||||
*/
|
||||
public function afterLast($needle, bool $includeNeedle = false, int $offset = 0): self
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = '';
|
||||
$i = null;
|
||||
|
||||
foreach ((array) $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);
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function append(string ...$suffix): self;
|
||||
|
||||
/**
|
||||
* @param string|string[] $needle
|
||||
*
|
||||
* @return static
|
||||
*/
|
||||
public function before($needle, bool $includeNeedle = false, int $offset = 0): self
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = '';
|
||||
$i = \PHP_INT_MAX;
|
||||
|
||||
foreach ((array) $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[] $needle
|
||||
*
|
||||
* @return static
|
||||
*/
|
||||
public function beforeLast($needle, bool $includeNeedle = false, int $offset = 0): self
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = '';
|
||||
$i = null;
|
||||
|
||||
foreach ((array) $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 static
|
||||
*/
|
||||
abstract public function camel(): self;
|
||||
|
||||
/**
|
||||
* @return static[]
|
||||
*/
|
||||
abstract public function chunk(int $length = 1): array;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public function collapseWhitespace(): self
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = trim(preg_replace('/(?:\s{2,}+|[^\S ])/', ' ', $str->string));
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $suffix
|
||||
*/
|
||||
public function endsWith($suffix): bool
|
||||
{
|
||||
if (!\is_array($suffix) && !$suffix instanceof \Traversable) {
|
||||
throw new \TypeError(sprintf('Method "%s()" must be overridden by class "%s" to deal with non-iterable values.', __FUNCTION__, \get_class($this)));
|
||||
}
|
||||
|
||||
foreach ($suffix as $s) {
|
||||
if ($this->endsWith((string) $s)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public function ensureEnd(string $suffix): self
|
||||
{
|
||||
if (!$this->endsWith($suffix)) {
|
||||
return $this->append($suffix);
|
||||
}
|
||||
|
||||
$suffix = preg_quote($suffix);
|
||||
$regex = '{('.$suffix.')(?:'.$suffix.')++$}D';
|
||||
|
||||
return $this->replaceMatches($regex.($this->ignoreCase ? 'i' : ''), '$1');
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public function ensureStart(string $prefix): self
|
||||
{
|
||||
$prefix = new static($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): bool
|
||||
{
|
||||
if (!\is_array($string) && !$string instanceof \Traversable) {
|
||||
throw new \TypeError(sprintf('Method "%s()" must be overridden by class "%s" to deal with non-iterable values.', __FUNCTION__, \get_class($this)));
|
||||
}
|
||||
|
||||
foreach ($string as $s) {
|
||||
if ($this->equalsTo((string) $s)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function folded(): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public function ignoreCase(): self
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->ignoreCase = true;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string|string[] $needle
|
||||
*/
|
||||
public function indexOf($needle, int $offset = 0): ?int
|
||||
{
|
||||
if (!\is_array($needle) && !$needle instanceof \Traversable) {
|
||||
throw new \TypeError(sprintf('Method "%s()" must be overridden by class "%s" to deal with non-iterable values.', __FUNCTION__, \get_class($this)));
|
||||
}
|
||||
|
||||
$i = \PHP_INT_MAX;
|
||||
|
||||
foreach ($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[] $needle
|
||||
*/
|
||||
public function indexOfLast($needle, int $offset = 0): ?int
|
||||
{
|
||||
if (!\is_array($needle) && !$needle instanceof \Traversable) {
|
||||
throw new \TypeError(sprintf('Method "%s()" must be overridden by class "%s" to deal with non-iterable values.', __FUNCTION__, \get_class($this)));
|
||||
}
|
||||
|
||||
$i = null;
|
||||
|
||||
foreach ($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;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function join(array $strings): self;
|
||||
|
||||
public function jsonSerialize(): string
|
||||
{
|
||||
return $this->string;
|
||||
}
|
||||
|
||||
abstract public function length(): int;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function lower(): self;
|
||||
|
||||
/**
|
||||
* Matches the string using a regular expression.
|
||||
*
|
||||
* Pass PREG_PATTERN_ORDER or PREG_SET_ORDER as $flags to get all occurrences matching the pattern.
|
||||
*
|
||||
* @return array All matches in a multi-dimensional array ordered according to flags
|
||||
*/
|
||||
abstract public function match(string $pattern, int $flags = 0, int $offset = 0): array;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function padBoth(int $length, string $padStr = ' '): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function padEnd(int $length, string $padStr = ' '): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function padStart(int $length, string $padStr = ' '): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function prepend(string ...$prefix): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public function repeat(int $multiplier): self
|
||||
{
|
||||
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;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function replace(string $from, string $to): self;
|
||||
|
||||
/**
|
||||
* @param string|callable $to
|
||||
*
|
||||
* @return static
|
||||
*/
|
||||
abstract public function replaceMatches(string $fromPattern, $to): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function slice(int $start = 0, int $length = null): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function snake(): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function splice(string $replacement, int $start = 0, int $length = null): self;
|
||||
|
||||
/**
|
||||
* @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) {
|
||||
$delimiter .= 'i';
|
||||
}
|
||||
|
||||
set_error_handler(static function ($t, $m) { throw new InvalidArgumentException($m); });
|
||||
|
||||
try {
|
||||
if (false === $chunks = preg_split($delimiter, $this->string, $limit, $flags)) {
|
||||
$lastError = preg_last_error();
|
||||
|
||||
foreach (get_defined_constants(true)['pcre'] as $k => $v) {
|
||||
if ($lastError === $v && '_ERROR' === substr($k, -6)) {
|
||||
throw new RuntimeException('Splitting failed with '.$k.'.');
|
||||
}
|
||||
}
|
||||
|
||||
throw new RuntimeException('Splitting failed with unknown error code.');
|
||||
}
|
||||
} 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[] $prefix
|
||||
*/
|
||||
public function startsWith($prefix): bool
|
||||
{
|
||||
if (!\is_array($prefix) && !$prefix instanceof \Traversable) {
|
||||
throw new \TypeError(sprintf('Method "%s()" must be overridden by class "%s" to deal with non-iterable values.', __FUNCTION__, \get_class($this)));
|
||||
}
|
||||
|
||||
foreach ($prefix as $prefix) {
|
||||
if ($this->startsWith((string) $prefix)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function title(bool $allWords = false): self;
|
||||
|
||||
public function toBinary(string $toEncoding = null): BinaryString
|
||||
{
|
||||
$b = new BinaryString();
|
||||
|
||||
$toEncoding = \in_array($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 $b;
|
||||
}
|
||||
|
||||
set_error_handler(static function ($t, $m) { throw new InvalidArgumentException($m); });
|
||||
|
||||
try {
|
||||
try {
|
||||
$b->string = mb_convert_encoding($this->string, $toEncoding, 'UTF-8');
|
||||
} catch (InvalidArgumentException $e) {
|
||||
if (!\function_exists('iconv')) {
|
||||
throw $e;
|
||||
}
|
||||
|
||||
$b->string = iconv('UTF-8', $toEncoding, $this->string);
|
||||
}
|
||||
} finally {
|
||||
restore_error_handler();
|
||||
}
|
||||
|
||||
return $b;
|
||||
}
|
||||
|
||||
public function toGrapheme(): GraphemeString
|
||||
{
|
||||
return new GraphemeString($this->string);
|
||||
}
|
||||
|
||||
public function toUtf8(): Utf8String
|
||||
{
|
||||
return new Utf8String($this->string);
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function trim(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function trimEnd(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function trimStart(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): self;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public function truncate(int $length, string $ellipsis = ''): self
|
||||
{
|
||||
$stringLength = $this->length();
|
||||
|
||||
if ($stringLength <= $length) {
|
||||
return clone $this;
|
||||
}
|
||||
|
||||
$ellipsisLength = '' !== $ellipsis ? (new static($ellipsis))->length() : 0;
|
||||
|
||||
if ($length < $ellipsisLength) {
|
||||
$ellipsisLength = 0;
|
||||
}
|
||||
|
||||
$str = $this->slice(0, $length - $ellipsisLength);
|
||||
|
||||
return $ellipsisLength ? $str->trimEnd()->append($ellipsis) : $str;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
abstract public function upper(): self;
|
||||
|
||||
abstract public function width(bool $ignoreAnsiDecoration = true): int;
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public function wordwrap(int $width = 75, string $break = "\n", bool $cut = false): self
|
||||
{
|
||||
$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 __clone()
|
||||
{
|
||||
$this->ignoreCase = false;
|
||||
}
|
||||
|
||||
public function __toString(): string
|
||||
{
|
||||
return $this->string;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,472 @@
|
|||
<?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
|
||||
*
|
||||
* @experimental in 5.0
|
||||
*/
|
||||
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;
|
||||
|
||||
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";
|
||||
private const FOLD_FROM = ['İ', 'µ', 'ſ', "\xCD\x85", 'ς', 'ϐ', 'ϑ', 'ϕ', 'ϖ', 'ϰ', 'ϱ', 'ϵ', 'ẛ', "\xE1\xBE\xBE", 'ß', 'İ', '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', 'ΐ', 'ῖ', 'ῗ', 'ῢ', 'ΰ', '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', 'i̇', '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', 'ΐ', 'ῖ', 'ῗ', 'ῢ', 'ΰ', 'ῤ', 'ῦ', 'ῧ', 'ὼι', 'ωι', 'ώι', 'ῶ', 'ῶι', 'ωι', 'ff', 'fi', 'fl', 'ffi', 'ffl', 'st', 'st', 'մն', 'մե', 'մի', 'վն', 'մխ'];
|
||||
private const UPPER_FROM = ['ß', 'ff', 'fi', 'fl', 'ffi', 'ffl', 'ſt', 'st', 'և', 'ﬓ', 'ﬔ', 'ﬕ', 'ﬖ', 'ﬗ', 'ʼn', 'ΐ', 'ΰ', 'ǰ', 'ẖ', 'ẗ', 'ẘ', 'ẙ', 'ẚ', 'ὐ', 'ὒ', 'ὔ', 'ὖ', 'ᾶ', 'ῆ', 'ῒ', 'ΐ', 'ῖ', 'ῗ', 'ῢ', 'ΰ', 'ῤ', 'ῦ', 'ῧ', 'ῶ
|
||||
'];
|
||||
private const UPPER_TO = ['SS', 'FF', 'FI', 'FL', 'FFI', 'FFL', 'ST', 'ST', 'ԵՒ', 'ՄՆ', 'ՄԵ', 'ՄԻ', 'ՎՆ', 'ՄԽ', 'ʼN', 'Ϊ́', 'Ϋ́', 'J̌', 'H̱', 'T̈', 'W̊', 'Y̊', 'Aʾ', 'Υ̓', 'Υ̓̀', 'Υ̓́', 'Υ̓͂', 'Α͂', 'Η͂', 'Ϊ̀', 'Ϊ́', 'Ι͂', 'Ϊ͂', 'Ϋ̀', 'Ϋ́', 'Ρ̓', 'Υ͂', 'Ϋ͂', 'Ω͂'];
|
||||
private const TRANSLIT_FROM = ['Ð', 'Ø', 'Þ', 'ð', 'ø', 'þ', 'Đ', 'đ', 'Ħ', 'ħ', 'ı', 'ĸ', 'Ŋ', 'ŋ', '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', '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', 'ẜ', 'ẝ', 'ẞ', 'Ỻ', 'ỻ', 'Ỽ', 'ỽ', 'Ỿ', 'ỿ', '₠', '₢', '₣', '₤', '₧', '₹', '℞', '〇', '′', '〝', '〞', '‖', '⁅', '⁆', '⁎', '、', '。', '〈', '〉', '《', '》', '〔', '〕', '〘', '〙', '〚', '〛', '︑', '︒', '︹', '︺', '︽', '︾', '︿', '﹀', '÷', '∥', '⦅', '⦆'];
|
||||
private const TRANSLIT_TO = ['D', 'O', 'TH', 'd', 'o', 'th', 'D', 'd', 'H', 'h', 'i', 'q', 'N', 'n', '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', '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', 's', 's', 'SS', 'LL', 'll', 'V', 'v', 'Y', 'y', 'CE', 'Cr', 'Fr.', 'L.', 'Pts', 'Rs', 'Rx', '0', '\'', '"', '"', '||', '[', ']', '*', ',', '.', '<', '>', '<<', '>>', '[', ']', '[', ']', '[', ']', ',', '.', '[', ']', '<<', '>>', '<', '>', '/', '||', '((', '))'];
|
||||
|
||||
private static $transliterators = [];
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public static function fromCodePoints(int ...$codes): self
|
||||
{
|
||||
$string = '';
|
||||
|
||||
foreach ($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[] $rules See "*-Latin" rules from Transliterator::listIDs()
|
||||
*/
|
||||
public function ascii(array $rules = []): self
|
||||
{
|
||||
$str = clone $this;
|
||||
$s = $str->string;
|
||||
$str->string = '';
|
||||
$step = 0;
|
||||
|
||||
if (\function_exists('transliterator_transliterate')) {
|
||||
$rules[] = '[:nonspacing mark:] remove';
|
||||
$rules[] = 'any-latin';
|
||||
}
|
||||
|
||||
while (\strlen($s) !== $i = strspn($s, self::ASCII)) {
|
||||
if (0 !== $i) {
|
||||
$str->string .= substr($s, 0, $i);
|
||||
$s = substr($s, $i);
|
||||
}
|
||||
|
||||
if (1 === ++$step) {
|
||||
if (!normalizer_is_normalized($s, self::NFKD)) {
|
||||
$s = normalizer_normalize($s, self::NFKD);
|
||||
}
|
||||
} elseif (2 === $step) {
|
||||
$s = str_replace(self::TRANSLIT_FROM, self::TRANSLIT_TO, $s);
|
||||
} elseif (3 === $step && '' !== $rule = strtolower(array_shift($rules))) {
|
||||
$step = 2;
|
||||
|
||||
if ('[:nonspacing mark:] remove' === $rule) {
|
||||
$s = preg_replace('/\p{Mn}++/u', '', $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[$rule] ?? self::$transliterators[$rule] = \Transliterator::create($rule)) {
|
||||
throw new InvalidArgumentException(sprintf('Unknown transliteration rule "%s".', $rule));
|
||||
}
|
||||
|
||||
$s = $transliterator->transliterate($s);
|
||||
}
|
||||
} elseif (!\function_exists('iconv')) {
|
||||
$s = preg_replace('/[^\x00-\x7F]/u', '?', $s);
|
||||
} elseif (\ICONV_IMPL === 'glibc') {
|
||||
$s = iconv('UTF-8', 'ASCII//TRANSLIT', $s);
|
||||
} else {
|
||||
$s = preg_replace_callback('/[^\x00-\x7F]/u', static function ($c) {
|
||||
$c = iconv('UTF-8', 'ASCII//IGNORE//TRANSLIT', $c[0]);
|
||||
|
||||
return 1 < \strlen($c) ? ltrim($c, '\'`"^~') : (\strlen($c) ? $c : '?');
|
||||
}, $s);
|
||||
}
|
||||
}
|
||||
|
||||
$str->string .= $s;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function camel(): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = str_replace(' ', '', preg_replace_callback('/\b./u', static function ($m) use (&$i) {
|
||||
return 1 === ++$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;
|
||||
}
|
||||
|
||||
public function codePoint(int $offset = 0): ?int
|
||||
{
|
||||
$str = $offset ? $this->slice($offset, 1) : $this;
|
||||
|
||||
return '' === $str->string ? null : mb_ord($str->string);
|
||||
}
|
||||
|
||||
public function folded(bool $compat = true): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
if (!$compat || \PHP_VERSION_ID < 70300 || !\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, $this->string), 'UTF-8');
|
||||
} else {
|
||||
$str->string = normalizer_normalize($str->string, \Normalizer::NFKC_CF);
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function join(array $strings): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = implode($this->string, $strings);
|
||||
|
||||
if (!preg_match('//u', $str->string)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function lower(): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = mb_strtolower(str_replace('İ', 'i̇', $str->string), 'UTF-8');
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function match(string $pattern, int $flags = 0, int $offset = 0): array
|
||||
{
|
||||
$match = ((\PREG_PATTERN_ORDER | \PREG_SET_ORDER) & $flags) ? 'preg_match_all' : 'preg_match';
|
||||
|
||||
if ($this->ignoreCase) {
|
||||
$pattern .= 'i';
|
||||
}
|
||||
|
||||
set_error_handler(static function ($t, $m) { throw new InvalidArgumentException($m); });
|
||||
|
||||
try {
|
||||
if (false === $match($pattern.'u', $this->string, $matches, $flags | PREG_UNMATCHED_AS_NULL, $offset)) {
|
||||
$lastError = preg_last_error();
|
||||
|
||||
foreach (get_defined_constants(true)['pcre'] as $k => $v) {
|
||||
if ($lastError === $v && '_ERROR' === substr($k, -6)) {
|
||||
throw new RuntimeException('Matching failed with '.$k.'.');
|
||||
}
|
||||
}
|
||||
|
||||
throw new RuntimeException('Matching failed with unknown error code.');
|
||||
}
|
||||
} finally {
|
||||
restore_error_handler();
|
||||
}
|
||||
|
||||
return $matches;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public function normalize(int $form = self::NFC): self
|
||||
{
|
||||
if (!\in_array($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 = ' '): parent
|
||||
{
|
||||
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 = ' '): parent
|
||||
{
|
||||
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 = ' '): parent
|
||||
{
|
||||
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 $fromPattern, $to): parent
|
||||
{
|
||||
if ($this->ignoreCase) {
|
||||
$fromPattern .= 'i';
|
||||
}
|
||||
|
||||
if (\is_array($to) || $to instanceof \Closure) {
|
||||
if (!\is_callable($to)) {
|
||||
throw new \TypeError(sprintf('Argument 2 passed to %s::replaceMatches() must be callable, array given.', \get_class($this)));
|
||||
}
|
||||
|
||||
$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 {
|
||||
$replace = 'preg_replace';
|
||||
}
|
||||
|
||||
set_error_handler(static function ($t, $m) { throw new InvalidArgumentException($m); });
|
||||
|
||||
try {
|
||||
if (null === $string = $replace($fromPattern.'u', $to, $this->string)) {
|
||||
$lastError = preg_last_error();
|
||||
|
||||
foreach (get_defined_constants(true)['pcre'] as $k => $v) {
|
||||
if ($lastError === $v && '_ERROR' === substr($k, -6)) {
|
||||
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;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public function slug(string $separator = '-'): self
|
||||
{
|
||||
return $this
|
||||
->ascii()
|
||||
->replace('@', $separator.'at'.$separator)
|
||||
->replaceMatches('/[^A-Za-z0-9]++/', $separator)
|
||||
->trim($separator);
|
||||
}
|
||||
|
||||
public function snake(): parent
|
||||
{
|
||||
$str = $this->camel()->title();
|
||||
$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): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
if ($allWords) {
|
||||
$str->string = preg_replace_callback('/\b./u', static function ($m) {
|
||||
return mb_convert_case($m[0], MB_CASE_TITLE, 'UTF-8');
|
||||
}, $str->string);
|
||||
} else {
|
||||
$firstChar = mb_substr($str->string, 0, 1, 'UTF-8');
|
||||
$str->string = mb_convert_case($firstChar, MB_CASE_TITLE, 'UTF-8').substr($str->string, \strlen($firstChar));
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function trim(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): parent
|
||||
{
|
||||
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}"): parent
|
||||
{
|
||||
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 trimStart(string $chars = " \t\n\r\0\x0B\x0C\u{A0}\u{FEFF}"): parent
|
||||
{
|
||||
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 upper(): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = mb_strtoupper($str->string, 'UTF-8');
|
||||
|
||||
if (\PHP_VERSION_ID < 70300) {
|
||||
$str->string = str_replace(self::UPPER_FROM, self::UPPER_TO, $str->string);
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function width(bool $ignoreAnsiDecoration = true): int
|
||||
{
|
||||
$width = 0;
|
||||
$s = str_replace(["\x00", "\x05", "\x07"], '', $this->string);
|
||||
|
||||
if (false !== strpos($s, "\r")) {
|
||||
$s = str_replace(["\r\n", "\r"], "\n", $s);
|
||||
}
|
||||
|
||||
foreach (explode("\n", $s) as $s) {
|
||||
if ($ignoreAnsiDecoration) {
|
||||
$s = preg_replace('/\x1B(?:
|
||||
\[ [\x30-\x3F]*+ [\x20-\x2F]*+ [0x40-\x7E]
|
||||
| [P\]X^_] .*? \x1B\\\\
|
||||
| [\x41-\x7E]
|
||||
)/x', '', $s);
|
||||
}
|
||||
|
||||
$w = substr_count($s, "\xAD") - substr_count($s, "\x08");
|
||||
$s = preg_replace('/[\x00\x05\x07\p{Mn}\p{Me}\p{Cf}\x{1160}-\x{11FF}\x{200B}]+/u', '', $s);
|
||||
$s = preg_replace('/[\x{1100}-\x{115F}\x{2329}\x{232A}\x{2E80}-\x{303E}\x{3040}-\x{A4CF}\x{AC00}-\x{D7A3}\x{F900}-\x{FAFF}\x{FE10}-\x{FE19}\x{FE30}-\x{FE6F}\x{FF00}-\x{FF60}\x{FFE0}-\x{FFE6}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}]/u', '', $s, -1, $wide);
|
||||
|
||||
if ($width < $w += mb_strlen($s, 'UTF-8') + ($wide << 1)) {
|
||||
$width = $w;
|
||||
}
|
||||
}
|
||||
|
||||
return $width;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
private function pad(int $len, self $pad, int $type): parent
|
||||
{
|
||||
$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, $freeLen / $padLen).($len ? $pad->slice(0, $len) : ''));
|
||||
|
||||
case STR_PAD_LEFT:
|
||||
return $this->prepend(str_repeat($pad->string, $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, $rightLen / $padLen).($len ? $pad->slice(0, $len) : ''));
|
||||
|
||||
$leftLen = floor($freeLen);
|
||||
$len = $leftLen % $padLen;
|
||||
|
||||
return $str->prepend(str_repeat($pad->string, $leftLen / $padLen).($len ? $pad->slice(0, $len) : ''));
|
||||
|
||||
default:
|
||||
throw new InvalidArgumentException('Invalid padding type.');
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,475 @@
|
|||
<?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 binary-safe string of bytes.
|
||||
*
|
||||
* @author Nicolas Grekas <p@tchwork.com>
|
||||
* @author Hugo Hamon <hugohamon@neuf.fr>
|
||||
*
|
||||
* @throws ExceptionInterface
|
||||
*
|
||||
* @experimental in 5.0
|
||||
*/
|
||||
class BinaryString extends AbstractString
|
||||
{
|
||||
public function __construct(string $string = '')
|
||||
{
|
||||
$this->string = $string;
|
||||
}
|
||||
|
||||
public static function fromRandom(int $length = 16): self
|
||||
{
|
||||
$string = '';
|
||||
|
||||
do {
|
||||
$string .= str_replace(['/', '+', '='], '', base64_encode(random_bytes($length)));
|
||||
} while (\strlen($string) < $length);
|
||||
|
||||
return new static(substr($string, 0, $length));
|
||||
}
|
||||
|
||||
public function byteCode(int $offset = 0): ?int
|
||||
{
|
||||
$str = $offset ? $this->slice($offset, 1) : $this;
|
||||
|
||||
return '' === $str->string ? null : \ord($str->string);
|
||||
}
|
||||
|
||||
public function append(string ...$suffix): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string .= 1 >= \count($suffix) ? ($suffix[0] ?? '') : implode('', $suffix);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function camel(): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = lcfirst(str_replace(' ', '', ucwords(preg_replace('/[^a-zA-Z0-9\x7f-\xff]++/', ' ', $this->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 [];
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$chunks = [];
|
||||
|
||||
foreach (str_split($this->string, $length) as $chunk) {
|
||||
$str->string = $chunk;
|
||||
$chunks[] = clone $str;
|
||||
}
|
||||
|
||||
return $chunks;
|
||||
}
|
||||
|
||||
public function endsWith($suffix): bool
|
||||
{
|
||||
if ($suffix instanceof parent) {
|
||||
$suffix = $suffix->string;
|
||||
} elseif (\is_array($suffix) || $suffix instanceof \Traversable) {
|
||||
return parent::endsWith($suffix);
|
||||
} else {
|
||||
$suffix = (string) $suffix;
|
||||
}
|
||||
|
||||
return \strlen($this->string) - \strlen($suffix) === ($this->ignoreCase ? strripos($this->string, $suffix) : strrpos($this->string, $suffix));
|
||||
}
|
||||
|
||||
public function equalsTo($string): bool
|
||||
{
|
||||
if ($string instanceof parent) {
|
||||
$string = $string->string;
|
||||
} elseif (\is_array($string) || $string instanceof \Traversable) {
|
||||
return parent::equalsTo($string);
|
||||
} else {
|
||||
$string = (string) $string;
|
||||
}
|
||||
|
||||
if ('' !== $string && $this->ignoreCase) {
|
||||
return 0 === strcasecmp($string, $this->string);
|
||||
}
|
||||
|
||||
return $string === $this->string;
|
||||
}
|
||||
|
||||
public function folded(): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = strtolower($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function indexOf($needle, int $offset = 0): ?int
|
||||
{
|
||||
if ($needle instanceof parent) {
|
||||
$needle = $needle->string;
|
||||
} elseif (\is_array($needle) || $needle instanceof \Traversable) {
|
||||
return parent::indexOf($needle, $offset);
|
||||
} else {
|
||||
$needle = (string) $needle;
|
||||
}
|
||||
|
||||
if ('' === $needle) {
|
||||
return null;
|
||||
}
|
||||
|
||||
$i = $this->ignoreCase ? stripos($this->string, $needle, $offset) : strpos($this->string, $needle, $offset);
|
||||
|
||||
return false === $i ? null : $i;
|
||||
}
|
||||
|
||||
public function indexOfLast($needle, int $offset = 0): ?int
|
||||
{
|
||||
if ($needle instanceof parent) {
|
||||
$needle = $needle->string;
|
||||
} elseif (\is_array($needle) || $needle instanceof \Traversable) {
|
||||
return parent::indexOfLast($needle, $offset);
|
||||
} else {
|
||||
$needle = (string) $needle;
|
||||
}
|
||||
|
||||
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): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = implode($str->string, $strings);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function length(): int
|
||||
{
|
||||
return \strlen($this->string);
|
||||
}
|
||||
|
||||
public function lower(): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = strtolower($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function match(string $pattern, int $flags = 0, int $offset = 0): array
|
||||
{
|
||||
$match = ((\PREG_PATTERN_ORDER | \PREG_SET_ORDER) & $flags) ? 'preg_match_all' : 'preg_match';
|
||||
|
||||
if ($this->ignoreCase) {
|
||||
$pattern .= 'i';
|
||||
}
|
||||
|
||||
set_error_handler(static function ($t, $m) { throw new InvalidArgumentException($m); });
|
||||
|
||||
try {
|
||||
if (false === $match($pattern, $this->string, $matches, $flags | PREG_UNMATCHED_AS_NULL, $offset)) {
|
||||
$lastError = preg_last_error();
|
||||
|
||||
foreach (get_defined_constants(true)['pcre'] as $k => $v) {
|
||||
if ($lastError === $v && '_ERROR' === substr($k, -6)) {
|
||||
throw new RuntimeException('Matching failed with '.$k.'.');
|
||||
}
|
||||
}
|
||||
|
||||
throw new RuntimeException('Matching failed with unknown error code.');
|
||||
}
|
||||
} finally {
|
||||
restore_error_handler();
|
||||
}
|
||||
|
||||
return $matches;
|
||||
}
|
||||
|
||||
public function padBoth(int $length, string $padStr = ' '): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = str_pad($this->string, $length, $padStr, STR_PAD_BOTH);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function padEnd(int $length, string $padStr = ' '): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = str_pad($this->string, $length, $padStr, STR_PAD_RIGHT);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function padStart(int $length, string $padStr = ' '): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = str_pad($this->string, $length, $padStr, STR_PAD_LEFT);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function prepend(string ...$prefix): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = (1 >= \count($prefix) ? ($prefix[0] ?? '') : implode('', $prefix)).$str->string;
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function replace(string $from, string $to): parent
|
||||
{
|
||||
$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 $fromPattern, $to): parent
|
||||
{
|
||||
if ($this->ignoreCase) {
|
||||
$fromPattern .= 'i';
|
||||
}
|
||||
|
||||
if (\is_array($to)) {
|
||||
if (!\is_callable($to)) {
|
||||
throw new \TypeError(sprintf('Argument 2 passed to %s::replaceMatches() must be callable, array given.', \get_class($this)));
|
||||
}
|
||||
|
||||
$replace = 'preg_replace_callback';
|
||||
} else {
|
||||
$replace = $to instanceof \Closure ? 'preg_replace_callback' : 'preg_replace';
|
||||
}
|
||||
|
||||
set_error_handler(static function ($t, $m) { throw new InvalidArgumentException($m); });
|
||||
|
||||
try {
|
||||
if (null === $string = $replace($fromPattern, $to, $this->string)) {
|
||||
$lastError = preg_last_error();
|
||||
|
||||
foreach (get_defined_constants(true)['pcre'] as $k => $v) {
|
||||
if ($lastError === $v && '_ERROR' === substr($k, -6)) {
|
||||
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 slice(int $start = 0, int $length = null): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = (string) substr($this->string, $start, $length ?? \PHP_INT_MAX);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function snake(): parent
|
||||
{
|
||||
$str = $this->camel()->title();
|
||||
$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): parent
|
||||
{
|
||||
$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 = $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 $chunks;
|
||||
}
|
||||
|
||||
public function startsWith($prefix): bool
|
||||
{
|
||||
if ($prefix instanceof parent) {
|
||||
$prefix = $prefix->string;
|
||||
} elseif (!\is_string($prefix)) {
|
||||
return parent::startsWith($prefix);
|
||||
}
|
||||
|
||||
return '' !== $prefix && 0 === ($this->ignoreCase ? stripos($this->string, $prefix) : strpos($this->string, $prefix));
|
||||
}
|
||||
|
||||
public function title(bool $allWords = false): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = $allWords ? ucwords($str->string) : ucfirst($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function toGrapheme(string $fromEncoding = null): GraphemeString
|
||||
{
|
||||
return new GraphemeString($this->toUtf8($fromEncoding)->string);
|
||||
}
|
||||
|
||||
public function toUtf8(string $fromEncoding = null): Utf8String
|
||||
{
|
||||
$u = new Utf8String();
|
||||
|
||||
if (\in_array($fromEncoding, [null, 'utf8', 'utf-8', 'UTF8', 'UTF-8'], true) && preg_match('//u', $this->string)) {
|
||||
$u->string = $this->string;
|
||||
|
||||
return $u;
|
||||
}
|
||||
|
||||
set_error_handler(static function ($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"): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = trim($str->string, $chars);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function trimEnd(string $chars = " \t\n\r\0\x0B\x0C"): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = rtrim($str->string, $chars);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function trimStart(string $chars = " \t\n\r\0\x0B\x0C"): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = ltrim($str->string, $chars);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function upper(): parent
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = strtoupper($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function width(bool $ignoreAnsiDecoration = true): int
|
||||
{
|
||||
$width = 0;
|
||||
$s = str_replace(["\x00", "\x05", "\x07"], '', $this->string);
|
||||
|
||||
if (false !== strpos($s, "\r")) {
|
||||
$s = str_replace(["\r\n", "\r"], "\n", $s);
|
||||
}
|
||||
|
||||
foreach (explode("\n", $s) as $s) {
|
||||
if ($ignoreAnsiDecoration) {
|
||||
$s = preg_replace('/\x1B(?:
|
||||
\[ [\x30-\x3F]*+ [\x20-\x2F]*+ [0x40-\x7E]
|
||||
| [P\]X^_] .*? \x1B\\\\
|
||||
| [\x41-\x7E]
|
||||
)/x', '', $s);
|
||||
}
|
||||
|
||||
$w = substr_count($s, "\xAD") - substr_count($s, "\x08");
|
||||
|
||||
if ($width < $w += \strlen($s)) {
|
||||
$width = $w;
|
||||
}
|
||||
}
|
||||
|
||||
return $width;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,7 @@
|
|||
CHANGELOG
|
||||
=========
|
||||
|
||||
5.0.0
|
||||
-----
|
||||
|
||||
* added the component as experimental
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
<?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\Exception;
|
||||
|
||||
/**
|
||||
* @experimental in 5.0
|
||||
*/
|
||||
interface ExceptionInterface extends \Throwable
|
||||
{
|
||||
}
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
<?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\Exception;
|
||||
|
||||
/**
|
||||
* @experimental in 5.0
|
||||
*/
|
||||
class InvalidArgumentException extends \InvalidArgumentException implements ExceptionInterface
|
||||
{
|
||||
}
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
<?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\Exception;
|
||||
|
||||
/**
|
||||
* @experimental in 5.0
|
||||
*/
|
||||
class RuntimeException extends \RuntimeException implements ExceptionInterface
|
||||
{
|
||||
}
|
||||
|
|
@ -0,0 +1,346 @@
|
|||
<?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) forms 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
|
||||
*
|
||||
* @experimental in 5.0
|
||||
*/
|
||||
class GraphemeString extends AbstractUnicodeString
|
||||
{
|
||||
public function __construct(string $string = '')
|
||||
{
|
||||
$this->string = normalizer_is_normalized($string) ? $string : normalizer_normalize($string);
|
||||
|
||||
if (false === $this->string) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
}
|
||||
|
||||
public function append(string ...$suffix): AbstractString
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = $this->string.(1 >= \count($suffix) ? ($suffix[0] ?? '') : implode('', $suffix));
|
||||
normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);
|
||||
|
||||
if (false === $str->string) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 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.'})/us';
|
||||
|
||||
$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 $chunks;
|
||||
}
|
||||
|
||||
public function endsWith($suffix): bool
|
||||
{
|
||||
if ($suffix instanceof AbstractString) {
|
||||
$suffix = $suffix->string;
|
||||
} elseif (\is_array($suffix) || $suffix instanceof \Traversable) {
|
||||
return parent::endsWith($suffix);
|
||||
} else {
|
||||
$suffix = (string) $suffix;
|
||||
}
|
||||
|
||||
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
|
||||
normalizer_is_normalized($suffix, $form) ?: $suffix = normalizer_normalize($suffix, $form);
|
||||
|
||||
if ('' === $suffix || false === $suffix || false === $i = $this->ignoreCase ? grapheme_strripos($this->string, $suffix) : grapheme_strrpos($this->string, $suffix)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return grapheme_strlen($this->string) - grapheme_strlen($suffix) === $i;
|
||||
}
|
||||
|
||||
public function equalsTo($string): bool
|
||||
{
|
||||
if ($string instanceof AbstractString) {
|
||||
$string = $string->string;
|
||||
} elseif (\is_array($string) || $string instanceof \Traversable) {
|
||||
return parent::equalsTo($string);
|
||||
} else {
|
||||
$string = (string) $string;
|
||||
}
|
||||
|
||||
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
|
||||
normalizer_is_normalized($string, $form) ?: $string = normalizer_normalize($string, $form);
|
||||
|
||||
if ('' !== $string && false !== $string && $this->ignoreCase) {
|
||||
return grapheme_strlen($string) === grapheme_strlen($this->string) && 0 === grapheme_stripos($this->string, $string);
|
||||
}
|
||||
|
||||
return $string === $this->string;
|
||||
}
|
||||
|
||||
public function indexOf($needle, int $offset = 0): ?int
|
||||
{
|
||||
if ($needle instanceof AbstractString) {
|
||||
$needle = $needle->string;
|
||||
} elseif (\is_array($needle) || $needle instanceof \Traversable) {
|
||||
return parent::indexOf($needle, $offset);
|
||||
} else {
|
||||
$needle = (string) $needle;
|
||||
}
|
||||
|
||||
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
|
||||
normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form);
|
||||
|
||||
if ('' === $needle || false === $needle) {
|
||||
return null;
|
||||
}
|
||||
|
||||
$i = $this->ignoreCase ? grapheme_stripos($this->string, $needle, $offset) : grapheme_strpos($this->string, $needle, $offset);
|
||||
|
||||
return false === $i ? null : $i;
|
||||
}
|
||||
|
||||
public function indexOfLast($needle, int $offset = 0): ?int
|
||||
{
|
||||
if ($needle instanceof AbstractString) {
|
||||
$needle = $needle->string;
|
||||
} elseif (\is_array($needle) || $needle instanceof \Traversable) {
|
||||
return parent::indexOfLast($needle, $offset);
|
||||
} else {
|
||||
$needle = (string) $needle;
|
||||
}
|
||||
|
||||
$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): AbstractString
|
||||
{
|
||||
$str = parent::join($strings);
|
||||
normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function length(): int
|
||||
{
|
||||
return grapheme_strlen($this->string);
|
||||
}
|
||||
|
||||
/**
|
||||
* @return static
|
||||
*/
|
||||
public function normalize(int $form = self::NFC): parent
|
||||
{
|
||||
$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): AbstractString
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = (1 >= \count($prefix) ? ($prefix[0] ?? '') : implode('', $prefix)).$this->string;
|
||||
normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);
|
||||
|
||||
if (false === $str->string) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function replace(string $from, string $to): AbstractString
|
||||
{
|
||||
$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 (false !== $i = $indexOf($tail, $from)) {
|
||||
$slice = grapheme_substr($tail, 0, $i);
|
||||
$result .= $slice.$to;
|
||||
$tail = substr($tail, \strlen($slice) + \strlen($from));
|
||||
}
|
||||
|
||||
$str->string = $result .= $tail;
|
||||
normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);
|
||||
|
||||
if (false === $str->string) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function replaceMatches(string $fromPattern, $to): AbstractString
|
||||
{
|
||||
$str = parent::replaceMatches($fromPattern, $to);
|
||||
normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function slice(int $start = 0, int $length = null): AbstractString
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = (string) grapheme_substr($this->string, $start, $length ?? \PHP_INT_MAX);
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function splice(string $replacement, int $start = 0, int $length = null): AbstractString
|
||||
{
|
||||
$str = clone $this;
|
||||
$start = $start ? \strlen(grapheme_substr($this->string, 0, $start)) : 0;
|
||||
$length = $length ? \strlen(grapheme_substr($this->string, $start, $length ?? \PHP_INT_MAX)) : $length;
|
||||
$str->string = substr_replace($this->string, $replacement, $start, $length ?? \PHP_INT_MAX);
|
||||
normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);
|
||||
|
||||
if (false === $str->string) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function split(string $delimiter, int $limit = null, int $flags = null): array
|
||||
{
|
||||
if (1 > $limit = $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.'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 $chunks;
|
||||
}
|
||||
|
||||
public function startsWith($prefix): bool
|
||||
{
|
||||
if ($prefix instanceof AbstractString) {
|
||||
$prefix = $prefix->string;
|
||||
} elseif (\is_array($prefix) || $prefix instanceof \Traversable) {
|
||||
return parent::startsWith($prefix);
|
||||
} else {
|
||||
$prefix = (string) $prefix;
|
||||
}
|
||||
|
||||
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
|
||||
normalizer_is_normalized($prefix, $form) ?: $prefix = normalizer_normalize($prefix, $form);
|
||||
|
||||
return '' !== $prefix && false !== $prefix && 0 === ($this->ignoreCase ? grapheme_stripos($this->string, $prefix) : grapheme_strpos($this->string, $prefix));
|
||||
}
|
||||
|
||||
public function __clone()
|
||||
{
|
||||
if (null === $this->ignoreCase) {
|
||||
normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string);
|
||||
}
|
||||
|
||||
$this->ignoreCase = false;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
Copyright (c) 2019 Fabien Potencier
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is furnished
|
||||
to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
||||
THE SOFTWARE.
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
String Component
|
||||
================
|
||||
|
||||
The String component provides an object-oriented API to strings and deals
|
||||
with bytes, UTF-8 code points and grapheme clusters in a unified way.
|
||||
|
||||
**This component is experimental**.
|
||||
[Experimental features](https://symfony.com/doc/current/contributing/code/experimental.html)
|
||||
are not covered by Symfony's
|
||||
[Backward Compatibility Promise](https://symfony.com/doc/current/contributing/code/bc.html).
|
||||
|
||||
Resources
|
||||
---------
|
||||
|
||||
* [Documentation](https://symfony.com/doc/current/components/string.html)
|
||||
* [Contributing](https://symfony.com/doc/current/contributing/index.html)
|
||||
* [Report issues](https://github.com/symfony/symfony/issues) and
|
||||
[send Pull Requests](https://github.com/symfony/symfony/pulls)
|
||||
in the [main Symfony repository](https://github.com/symfony/symfony)
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
<?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;
|
||||
|
||||
/**
|
||||
* @experimental in 5.0
|
||||
*/
|
||||
function u(string $string = ''): GraphemeString
|
||||
{
|
||||
return new GraphemeString($string);
|
||||
}
|
||||
|
||||
/**
|
||||
* @experimental in 5.0
|
||||
*/
|
||||
function b(string $string = ''): BinaryString
|
||||
{
|
||||
return new BinaryString($string);
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,507 @@
|
|||
<?php
|
||||
|
||||
namespace Symfony\Component\String\Tests;
|
||||
|
||||
use Symfony\Component\String\Exception\InvalidArgumentException;
|
||||
|
||||
abstract class AbstractUtf8TestCase extends AbstractAsciiTestCase
|
||||
{
|
||||
public function testCreateFromStringWithInvalidUtf8Input()
|
||||
{
|
||||
$this->expectException(InvalidArgumentException::class);
|
||||
|
||||
static::createFromString("\xE9");
|
||||
}
|
||||
|
||||
public function provideCreateFromCodePoint(): array
|
||||
{
|
||||
return [
|
||||
['', []],
|
||||
['*', [42]],
|
||||
['AZ', [65, 90]],
|
||||
['€', [8364]],
|
||||
['€', [0x20ac]],
|
||||
['Ʃ', [425]],
|
||||
['Ʃ', [0x1a9]],
|
||||
['☢☎❄', [0x2622, 0x260E, 0x2744]],
|
||||
];
|
||||
}
|
||||
|
||||
public static function provideLength(): array
|
||||
{
|
||||
return [
|
||||
[1, 'a'],
|
||||
[1, 'ß'],
|
||||
[2, 'is'],
|
||||
[3, 'PHP'],
|
||||
[3, '한국어'],
|
||||
[4, 'Java'],
|
||||
[7, 'Symfony'],
|
||||
[10, 'pineapples'],
|
||||
[22, 'Symfony is super cool!'],
|
||||
];
|
||||
}
|
||||
|
||||
public static function provideIndexOf(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideIndexOf(),
|
||||
[
|
||||
[1, '한국어', '국', 0],
|
||||
[1, '한국어', '국', 1],
|
||||
[null, '한국어', '국', 2],
|
||||
[8, 'der Straße nach Paris', 'ß', 4],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideIndexOfIgnoreCase(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideIndexOfIgnoreCase(),
|
||||
[
|
||||
[3, 'DÉJÀ', 'À', 0],
|
||||
[3, 'DÉJÀ', 'à', 0],
|
||||
[1, 'DÉJÀ', 'É', 1],
|
||||
[1, 'DÉJÀ', 'é', 1],
|
||||
[1, 'aςσb', 'ΣΣ', 0],
|
||||
[16, 'der Straße nach Paris', 'Paris', 0],
|
||||
[8, 'der Straße nach Paris', 'ß', 4],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideIndexOfLast(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideIndexOfLast(),
|
||||
[
|
||||
[null, '한국어', '', 0],
|
||||
[1, '한국어', '국', 0],
|
||||
[5, '한국어어어어국국', '어', 0],
|
||||
// see https://bugs.php.net/bug.php?id=74264
|
||||
[15, 'abcdéf12é45abcdéf', 'é', 0],
|
||||
[8, 'abcdéf12é45abcdéf', 'é', -4],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideIndexOfLastIgnoreCase(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideIndexOfLastIgnoreCase(),
|
||||
[
|
||||
[null, '한국어', '', 0],
|
||||
[3, 'DÉJÀ', 'à', 0],
|
||||
[3, 'DÉJÀ', 'À', 0],
|
||||
[6, 'DÉJÀÀÀÀ', 'à', 0],
|
||||
[6, 'DÉJÀÀÀÀ', 'à', 3],
|
||||
[5, 'DÉJÀÀÀÀ', 'àà', 0],
|
||||
[2, 'DÉJÀÀÀÀ', 'jà', 0],
|
||||
[2, 'DÉJÀÀÀÀ', 'jà', -5],
|
||||
[6, 'DÉJÀÀÀÀ!', 'à', -2],
|
||||
// see https://bugs.php.net/bug.php?id=74264
|
||||
[5, 'DÉJÀÀÀÀ', 'à', -2],
|
||||
[15, 'abcdéf12é45abcdéf', 'é', 0],
|
||||
[8, 'abcdéf12é45abcdéf', 'é', -4],
|
||||
[1, 'aςσb', 'ΣΣ', 0],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideSplit(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideSplit(),
|
||||
[
|
||||
[
|
||||
'會|意|文|字|/|会|意|文|字',
|
||||
'|',
|
||||
[
|
||||
static::createFromString('會'),
|
||||
static::createFromString('意'),
|
||||
static::createFromString('文'),
|
||||
static::createFromString('字'),
|
||||
static::createFromString('/'),
|
||||
static::createFromString('会'),
|
||||
static::createFromString('意'),
|
||||
static::createFromString('文'),
|
||||
static::createFromString('字'),
|
||||
],
|
||||
null,
|
||||
],
|
||||
[
|
||||
'會|意|文|字|/|会|意|文|字',
|
||||
'|',
|
||||
[
|
||||
static::createFromString('會'),
|
||||
static::createFromString('意'),
|
||||
static::createFromString('文'),
|
||||
static::createFromString('字'),
|
||||
static::createFromString('/|会|意|文|字'),
|
||||
],
|
||||
5,
|
||||
],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideChunk(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideChunk(),
|
||||
[
|
||||
[
|
||||
'déjà',
|
||||
[
|
||||
static::createFromString('d'),
|
||||
static::createFromString('é'),
|
||||
static::createFromString('j'),
|
||||
static::createFromString('à'),
|
||||
],
|
||||
1,
|
||||
],
|
||||
[
|
||||
'déjà',
|
||||
[
|
||||
static::createFromString('dé'),
|
||||
static::createFromString('jà'),
|
||||
],
|
||||
2,
|
||||
],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public function testTrimWithInvalidUtf8CharList()
|
||||
{
|
||||
$this->expectException(InvalidArgumentException::class);
|
||||
|
||||
static::createFromString('Symfony')->trim("\xE9");
|
||||
}
|
||||
|
||||
public function testTrimStartWithInvalidUtf8CharList()
|
||||
{
|
||||
$this->expectException(InvalidArgumentException::class);
|
||||
|
||||
static::createFromString('Symfony')->trimStart("\xE9");
|
||||
}
|
||||
|
||||
public function testTrimEndWithInvalidUtf8CharList()
|
||||
{
|
||||
$this->expectException(InvalidArgumentException::class);
|
||||
|
||||
static::createFromString('Symfony')->trimEnd("\xE9");
|
||||
}
|
||||
|
||||
public static function provideLower(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideLower(),
|
||||
[
|
||||
// French
|
||||
['garçon', 'garçon'],
|
||||
['garçon', 'GARÇON'],
|
||||
["œuvre d'art", "Œuvre d'Art"],
|
||||
|
||||
// Spanish
|
||||
['el niño', 'El Niño'],
|
||||
|
||||
// Romanian
|
||||
['împărat', 'Împărat'],
|
||||
|
||||
// Random symbols
|
||||
['déjà σσς i̇iıi', 'DÉJÀ Σσς İIıi'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideUpper(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideUpper(),
|
||||
[
|
||||
// French
|
||||
['GARÇON', 'garçon'],
|
||||
['GARÇON', 'GARÇON'],
|
||||
["ŒUVRE D'ART", "Œuvre d'Art"],
|
||||
|
||||
// German
|
||||
['ÄUSSERST', 'äußerst'],
|
||||
|
||||
// Spanish
|
||||
['EL NIÑO', 'El Niño'],
|
||||
|
||||
// Romanian
|
||||
['ÎMPĂRAT', 'Împărat'],
|
||||
|
||||
// Random symbols
|
||||
['DÉJÀ ΣΣΣ İIII', 'Déjà Σσς İIıi'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideTitle(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideTitle(),
|
||||
[
|
||||
['Deja', 'deja', false],
|
||||
['Σσς', 'σσς', false],
|
||||
['DEJa', 'dEJa', false],
|
||||
['ΣσΣ', 'σσΣ', false],
|
||||
['Deja Σσς DEJa ΣσΣ', 'deja σσς dEJa σσΣ', true],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideSlice(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideSlice(),
|
||||
[
|
||||
['jà', 'déjà', 2, null],
|
||||
['jà', 'déjà', 2, null],
|
||||
['jà', 'déjà', -2, null],
|
||||
['jà', 'déjà', -2, 3],
|
||||
['', 'déjà', -1, 0],
|
||||
['', 'déjà', 1, -4],
|
||||
['j', 'déjà', -2, -1],
|
||||
['', 'déjà', -2, -2],
|
||||
['', 'déjà', 5, 0],
|
||||
['', 'déjà', -5, 0],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideAppend(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideAppend(),
|
||||
[
|
||||
[
|
||||
'Déjà Σσς',
|
||||
['Déjà', ' ', 'Σσς'],
|
||||
],
|
||||
[
|
||||
'Déjà Σσς İIıi',
|
||||
['Déjà', ' Σσς', ' İIıi'],
|
||||
],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public function testAppendInvalidUtf8String()
|
||||
{
|
||||
$this->expectException(InvalidArgumentException::class);
|
||||
|
||||
static::createFromString('Symfony')->append("\xE9");
|
||||
}
|
||||
|
||||
public static function providePrepend(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::providePrepend(),
|
||||
[
|
||||
[
|
||||
'Σσς Déjà',
|
||||
['Déjà', 'Σσς '],
|
||||
],
|
||||
[
|
||||
'İIıi Σσς Déjà',
|
||||
['Déjà', 'Σσς ', 'İIıi '],
|
||||
],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public function testPrependInvalidUtf8String()
|
||||
{
|
||||
$this->expectException(InvalidArgumentException::class);
|
||||
|
||||
static::createFromString('Symfony')->prepend("\xE9");
|
||||
}
|
||||
|
||||
public static function provideBeforeAfter(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideBeforeAfter(),
|
||||
[
|
||||
['jàdéjà', 'jà', 'déjàdéjà', 0, false],
|
||||
['dé', 'jà', 'déjàdéjà', 0, true],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideBeforeAfterIgnoreCase(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideBeforeAfterIgnoreCase(),
|
||||
[
|
||||
['jàdéjà', 'JÀ', 'déjàdéjà', 0, false],
|
||||
['dé', 'jÀ', 'déjàdéjà', 0, true],
|
||||
['éjàdéjà', 'é', 'déjàdéjà', 0, false],
|
||||
['d', 'é', 'déjàdéjà', 0, true],
|
||||
['', 'Ç', 'déjàdéjà', 0, false],
|
||||
['', 'Ç', 'déjàdéjà', 0, true],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideBeforeAfterLast(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideBeforeAfterLast(),
|
||||
[
|
||||
['', 'Ç', 'déjàdéjà', 0, false],
|
||||
['', 'Ç', 'déjàdéjà', 0, true],
|
||||
['éjà', 'é', 'déjàdéjà', 0, false],
|
||||
['déjàd', 'é', 'déjàdéjà', 0, true],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideBeforeAfterLastIgnoreCase(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideBeforeAfterLastIgnoreCase(),
|
||||
[
|
||||
['', 'Ç', 'déjàdéjà', 0, false],
|
||||
['éjà', 'é', 'déjàdéjà', 0, false],
|
||||
['éjà', 'É', 'déjàdéjà', 0, false],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideToFoldedCase(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideToFoldedCase(),
|
||||
[
|
||||
['déjà', 'DéjÀ'],
|
||||
['σσσ', 'Σσς'],
|
||||
['iıi̇i', 'Iıİi'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideReplace(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideReplace(),
|
||||
[
|
||||
['ΣσΣ', 1, 'Σσς', 'ς', 'Σ'],
|
||||
['漢字はユニコード', 0, '漢字はユニコード', 'foo', 'bar'],
|
||||
['漢字ーユニコード', 1, '漢字はユニコード', 'は', 'ー'],
|
||||
['This is a jamais-vu situation!', 1, 'This is a déjà-vu situation!', 'déjà', 'jamais'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideReplaceIgnoreCase(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideReplaceIgnoreCase(),
|
||||
[
|
||||
// σ and ς are lowercase variants for Σ
|
||||
['ΣΣΣ', 3, 'σσσ', 'σ', 'Σ'],
|
||||
['ΣΣΣ', 3, 'σσσ', 'ς', 'Σ'],
|
||||
['Σσ', 1, 'σσσ', 'σσ', 'Σ'],
|
||||
['漢字はユニコード', 0, '漢字はユニコード', 'foo', 'bar'],
|
||||
['漢字ーユニコード', 1, '漢字はユニコード', 'は', 'ー'],
|
||||
['This is a jamais-vu situation!', 1, 'This is a déjà-vu situation!', 'DÉjÀ', 'jamais'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public function testReplaceWithInvalidUtf8Pattern()
|
||||
{
|
||||
$this->assertEquals('Symfony', static::createFromString('Symfony')->replace("\xE9", 'p'));
|
||||
}
|
||||
|
||||
public function testReplaceWithInvalidUtf8PatternReplacement()
|
||||
{
|
||||
$this->expectException(InvalidArgumentException::class);
|
||||
|
||||
static::createFromString('Symfony')->replace('f', "\xE9");
|
||||
}
|
||||
|
||||
public static function provideCamel()
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideCamel(),
|
||||
[
|
||||
['symfonyIstÄußerstCool', 'symfony_ist_äußerst_cool'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideSnake()
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideSnake(),
|
||||
[
|
||||
['symfony_ist_äußerst_cool', 'symfonyIstÄußerstCool'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideEqualsTo()
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideEqualsTo(),
|
||||
[
|
||||
[true, 'äußerst', 'äußerst'],
|
||||
[false, 'BÄR', 'bär'],
|
||||
[false, 'Bär', 'Bar'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideEqualsToIgnoreCase()
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideEqualsToIgnoreCase(),
|
||||
[
|
||||
[true, 'Äußerst', 'äußerst'],
|
||||
[false, 'Bär', 'Bar'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function providePadBoth(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::providePadBoth(),
|
||||
[
|
||||
['äußerst', 'äußerst', 7, '+'],
|
||||
['+äußerst+', 'äußerst', 9, '+'],
|
||||
['äö.äöä', '.', 6, 'äö'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function providePadEnd(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::providePadEnd(),
|
||||
[
|
||||
['äußerst', 'äußerst', 7, '+'],
|
||||
['äußerst+', 'äußerst', 8, '+'],
|
||||
['.äöä', '.', 4, 'äö'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function providePadStart(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::providePadStart(),
|
||||
[
|
||||
['äußerst', 'äußerst', 7, '+'],
|
||||
['+äußerst', 'äußerst', 8, '+'],
|
||||
['äöä.', '.', 4, 'äö'],
|
||||
]
|
||||
);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,33 @@
|
|||
<?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\Tests;
|
||||
|
||||
use Symfony\Component\String\AbstractString;
|
||||
use Symfony\Component\String\BinaryString;
|
||||
|
||||
class BinaryStringTest extends AbstractAsciiTestCase
|
||||
{
|
||||
protected static function createFromString(string $string): AbstractString
|
||||
{
|
||||
return new BinaryString($string);
|
||||
}
|
||||
|
||||
public static function provideLength(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideLength(),
|
||||
[
|
||||
[2, 'ä'],
|
||||
]
|
||||
);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,203 @@
|
|||
<?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\Tests;
|
||||
|
||||
use Symfony\Component\String\AbstractString;
|
||||
use Symfony\Component\String\GraphemeString;
|
||||
|
||||
class GraphemeStringTest extends AbstractUtf8TestCase
|
||||
{
|
||||
protected static function createFromString(string $string): AbstractString
|
||||
{
|
||||
return new GraphemeString($string);
|
||||
}
|
||||
|
||||
public static function provideLength(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideLength(),
|
||||
[
|
||||
// 5 letters + 3 combining marks
|
||||
[5, 'अनुच्छेद'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideSplit(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideSplit(),
|
||||
[
|
||||
[
|
||||
'अ.नु.च्.छे.द',
|
||||
'.',
|
||||
[
|
||||
static::createFromString('अ'),
|
||||
static::createFromString('नु'),
|
||||
static::createFromString('च्'),
|
||||
static::createFromString('छे'),
|
||||
static::createFromString('द'),
|
||||
],
|
||||
null,
|
||||
],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideChunk(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideChunk(),
|
||||
[
|
||||
[
|
||||
'अनुच्छेद',
|
||||
[
|
||||
static::createFromString('अ'),
|
||||
static::createFromString('नु'),
|
||||
static::createFromString('च्'),
|
||||
static::createFromString('छे'),
|
||||
static::createFromString('द'),
|
||||
],
|
||||
1,
|
||||
],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideLower(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideLower(),
|
||||
[
|
||||
// Hindi
|
||||
['अनुच्छेद', 'अनुच्छेद'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideUpper(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideUpper(),
|
||||
[
|
||||
// Hindi
|
||||
['अनुच्छेद', 'अनुच्छेद'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideAppend(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideAppend(),
|
||||
[
|
||||
[
|
||||
'तद्भव देशज',
|
||||
['तद्भव', ' ', 'देशज'],
|
||||
],
|
||||
[
|
||||
'तद्भव देशज विदेशी',
|
||||
['तद्भव', ' देशज', ' विदेशी'],
|
||||
],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function providePrepend(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::providePrepend(),
|
||||
[
|
||||
[
|
||||
'देशज तद्भव',
|
||||
['तद्भव', 'देशज '],
|
||||
],
|
||||
[
|
||||
'विदेशी देशज तद्भव',
|
||||
['तद्भव', 'देशज ', 'विदेशी '],
|
||||
],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideBeforeAfter(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideBeforeAfter(),
|
||||
[
|
||||
['द foo अनुच्छेद', 'द', 'अनुच्छेद foo अनुच्छेद', 0, false],
|
||||
['अनुच्छे', 'द', 'अनुच्छेद foo अनुच्छेद', 0, true],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideBeforeAfterIgnoreCase(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideBeforeAfterIgnoreCase(),
|
||||
[
|
||||
['', 'छेछे', 'दछेच्नुअ', 0, false],
|
||||
['', 'छेछे', 'दछेच्नुअ', 0, true],
|
||||
['छेच्नुअ', 'छे', 'दछेच्नुअ', 0, false],
|
||||
['द', 'छे', 'दछेच्नुअ', 0, true],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideBeforeAfterLast(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideBeforeAfterLast(),
|
||||
[
|
||||
['', 'छेछे', 'दछेच्नुअ-दछेच्नु-अदछेच्नु', 0, false],
|
||||
['', 'छेछे', 'दछेच्नुअ-दछेच्नु-अदछेच्नु', 0, true],
|
||||
['-दछेच्नु', '-द', 'दछेच्नुअ-दछेच्नु-अद-दछेच्नु', 0, false],
|
||||
['दछेच्नुअ-दछेच्नु-अद', '-द', 'दछेच्नुअ-दछेच्नु-अद-दछेच्नु', 0, true],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideBeforeAfterLastIgnoreCase(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideBeforeAfterLastIgnoreCase(),
|
||||
[
|
||||
['', 'छेछे', 'दछेच्नुअ-दछेच्नु-अदछेच्नु', 0, false],
|
||||
['', 'छेछे', 'दछेच्नुअ-दछेच्नु-अदछेच्नु', 0, true],
|
||||
['-दछेच्नु', '-द', 'दछेच्नुअ-दछेच्नु-अद-दछेच्नु', 0, false],
|
||||
['दछेच्नुअ-दछेच्नु-अद', '-द', 'दछेच्नुअ-दछेच्नु-अद-दछेच्नु', 0, true],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideReplace(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideReplace(),
|
||||
[
|
||||
['Das Innenministerium', 1, 'Das Außenministerium', 'Auß', 'Inn'],
|
||||
['दछेच्नुद-दछेच्नु-ददछेच्नु', 2, 'दछेच्नुअ-दछेच्नु-अदछेच्नु', 'अ', 'द'],
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
public static function provideReplaceIgnoreCase(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideReplaceIgnoreCase(),
|
||||
[
|
||||
['Das Aussenministerium', 1, 'Das Außenministerium', 'auß', 'Auss'],
|
||||
['दछेच्नुद-दछेच्नु-ददछेच्नु', 2, 'दछेच्नुअ-दछेच्नु-अदछेच्नु', 'अ', 'द'],
|
||||
]
|
||||
);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
<?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\Tests;
|
||||
|
||||
use Symfony\Component\String\AbstractString;
|
||||
use Symfony\Component\String\Utf8String;
|
||||
|
||||
class Utf8StringTest extends AbstractUtf8TestCase
|
||||
{
|
||||
protected static function createFromString(string $string): AbstractString
|
||||
{
|
||||
return new Utf8String($string);
|
||||
}
|
||||
|
||||
public static function provideLength(): array
|
||||
{
|
||||
return array_merge(
|
||||
parent::provideLength(),
|
||||
[
|
||||
// 8 instead of 5 if it were processed as a grapheme cluster
|
||||
[8, 'अनुच्छेद'],
|
||||
]
|
||||
);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,261 @@
|
|||
<?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 code points encoded as UTF-8.
|
||||
*
|
||||
* @author Nicolas Grekas <p@tchwork.com>
|
||||
* @author Hugo Hamon <hugohamon@neuf.fr>
|
||||
*
|
||||
* @throws ExceptionInterface
|
||||
*
|
||||
* @experimental in 5.0
|
||||
*/
|
||||
class Utf8String extends AbstractUnicodeString
|
||||
{
|
||||
public function __construct(string $string = '')
|
||||
{
|
||||
if ('' !== $string && !preg_match('//u', $string)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
$this->string = $string;
|
||||
}
|
||||
|
||||
public function append(string ...$suffix): AbstractString
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string .= 1 >= \count($suffix) ? ($suffix[0] ?? '') : implode('', $suffix);
|
||||
|
||||
if (!preg_match('//u', $str->string)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 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 .= '.{65535}';
|
||||
$length -= 65535;
|
||||
}
|
||||
$rx .= '.{'.$length.'})/us';
|
||||
|
||||
$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 $chunks;
|
||||
}
|
||||
|
||||
public function endsWith($suffix): bool
|
||||
{
|
||||
if ($suffix instanceof AbstractString) {
|
||||
$suffix = $suffix->string;
|
||||
} elseif (\is_array($suffix) || $suffix instanceof \Traversable) {
|
||||
return parent::endsWith($suffix);
|
||||
} else {
|
||||
$suffix = (string) $suffix;
|
||||
}
|
||||
|
||||
if ('' === $suffix || !preg_match('//u', $suffix)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
if ($this->ignoreCase) {
|
||||
return preg_match('{'.preg_quote($suffix).'$}iuD', $this->string);
|
||||
}
|
||||
|
||||
return \strlen($this->string) - \strlen($suffix) === strrpos($this->string, $suffix);
|
||||
}
|
||||
|
||||
public function equalsTo($string): bool
|
||||
{
|
||||
if ($string instanceof AbstractString) {
|
||||
$string = $string->string;
|
||||
} elseif (\is_array($string) || $string instanceof \Traversable) {
|
||||
return parent::equalsTo($string);
|
||||
} else {
|
||||
$string = (string) $string;
|
||||
}
|
||||
|
||||
if ('' !== $string && $this->ignoreCase) {
|
||||
return mb_strlen($string, 'UTF-8') === mb_strlen($this->string, 'UTF-8') && 0 === mb_stripos($this->string, $string, 0, 'UTF-8');
|
||||
}
|
||||
|
||||
return $string === $this->string;
|
||||
}
|
||||
|
||||
public function indexOf($needle, int $offset = 0): ?int
|
||||
{
|
||||
if ($needle instanceof AbstractString) {
|
||||
$needle = $needle->string;
|
||||
} elseif (\is_array($needle) || $needle instanceof \Traversable) {
|
||||
return parent::indexOf($needle, $offset);
|
||||
} else {
|
||||
$needle = (string) $needle;
|
||||
}
|
||||
|
||||
if ('' === $needle) {
|
||||
return null;
|
||||
}
|
||||
|
||||
$i = $this->ignoreCase ? mb_stripos($this->string, $needle, $offset, 'UTF-8') : mb_strpos($this->string, $needle, $offset, 'UTF-8');
|
||||
|
||||
return false === $i ? null : $i;
|
||||
}
|
||||
|
||||
public function indexOfLast($needle, int $offset = 0): ?int
|
||||
{
|
||||
if ($needle instanceof AbstractString) {
|
||||
$needle = $needle->string;
|
||||
} elseif (\is_array($needle) || $needle instanceof \Traversable) {
|
||||
return parent::indexOfLast($needle, $offset);
|
||||
} else {
|
||||
$needle = (string) $needle;
|
||||
}
|
||||
|
||||
if ('' === $needle) {
|
||||
return null;
|
||||
}
|
||||
|
||||
$i = $this->ignoreCase ? mb_strripos($this->string, $needle, $offset, 'UTF-8') : mb_strrpos($this->string, $needle, $offset, 'UTF-8');
|
||||
|
||||
return false === $i ? null : $i;
|
||||
}
|
||||
|
||||
public function length(): int
|
||||
{
|
||||
return mb_strlen($this->string, 'UTF-8');
|
||||
}
|
||||
|
||||
public function prepend(string ...$prefix): AbstractString
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = (1 >= \count($prefix) ? ($prefix[0] ?? '') : implode('', $prefix)).$this->string;
|
||||
|
||||
if (!preg_match('//u', $str->string)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function replace(string $from, string $to): AbstractString
|
||||
{
|
||||
$str = clone $this;
|
||||
|
||||
if ('' === $from || !preg_match('//u', $from)) {
|
||||
return $str;
|
||||
}
|
||||
|
||||
if ('' !== $to && !preg_match('//u', $to)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
if ($this->ignoreCase) {
|
||||
$str->string = implode($to, preg_split('{'.preg_quote($from).'}iuD', $this->string));
|
||||
} else {
|
||||
$str->string = str_replace($from, $to, $this->string);
|
||||
}
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function slice(int $start = 0, int $length = null): AbstractString
|
||||
{
|
||||
$str = clone $this;
|
||||
$str->string = mb_substr($this->string, $start, $length, 'UTF-8');
|
||||
|
||||
return $str;
|
||||
}
|
||||
|
||||
public function splice(string $replacement, int $start = 0, int $length = null): AbstractString
|
||||
{
|
||||
if (!preg_match('//u', $replacement)) {
|
||||
throw new InvalidArgumentException('Invalid UTF-8 string.');
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$start = $start ? \strlen(mb_substr($this->string, 0, $start, 'UTF-8')) : 0;
|
||||
$length = $length ? \strlen(mb_substr($this->string, $start, $length, 'UTF-8')) : $length;
|
||||
$str->string = substr_replace($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 = $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.'u', $limit, $flags);
|
||||
}
|
||||
|
||||
if (!preg_match('//u', $delimiter)) {
|
||||
throw new InvalidArgumentException('Split delimiter is not a valid UTF-8 string.');
|
||||
}
|
||||
|
||||
$str = clone $this;
|
||||
$chunks = $this->ignoreCase
|
||||
? preg_split('{'.preg_quote($delimiter).'}iuD', $this->string, $limit)
|
||||
: explode($delimiter, $this->string, $limit);
|
||||
|
||||
foreach ($chunks as &$chunk) {
|
||||
$str->string = $chunk;
|
||||
$chunk = clone $str;
|
||||
}
|
||||
|
||||
return $chunks;
|
||||
}
|
||||
|
||||
public function startsWith($prefix): bool
|
||||
{
|
||||
if ($prefix instanceof AbstractString) {
|
||||
$prefix = $prefix->string;
|
||||
} elseif (\is_array($prefix) || $prefix instanceof \Traversable) {
|
||||
return parent::startsWith($prefix);
|
||||
} else {
|
||||
$prefix = (string) $prefix;
|
||||
}
|
||||
|
||||
if ('' === $prefix || !preg_match('//u', $prefix)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return 0 === ($this->ignoreCase ? mb_stripos($this->string, $prefix, 0, 'UTF-8') : strpos($this->string, $prefix));
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,37 @@
|
|||
{
|
||||
"name": "symfony/string",
|
||||
"type": "library",
|
||||
"description": "Symfony String component",
|
||||
"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": "^7.2.9",
|
||||
"symfony/polyfill-intl-grapheme": "~1.0",
|
||||
"symfony/polyfill-intl-normalizer": "~1.0",
|
||||
"symfony/polyfill-mbstring": "~1.0"
|
||||
},
|
||||
"autoload": {
|
||||
"psr-4": { "Symfony\\Component\\String\\": "" },
|
||||
"files": [ "Resources/functions.php" ],
|
||||
"exclude-from-classmap": [
|
||||
"/Tests/"
|
||||
]
|
||||
},
|
||||
"minimum-stability": "dev",
|
||||
"extra": {
|
||||
"branch-alias": {
|
||||
"dev-master": "5.0-dev"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
|
||||
<phpunit xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xsi:noNamespaceSchemaLocation="http://schema.phpunit.de/5.2/phpunit.xsd"
|
||||
backupGlobals="false"
|
||||
colors="true"
|
||||
bootstrap="vendor/autoload.php"
|
||||
failOnRisky="true"
|
||||
failOnWarning="true"
|
||||
>
|
||||
<php>
|
||||
<ini name="error_reporting" value="-1" />
|
||||
</php>
|
||||
|
||||
<testsuites>
|
||||
<testsuite name="Symfony String Component Test Suite">
|
||||
<directory>./Tests/</directory>
|
||||
</testsuite>
|
||||
</testsuites>
|
||||
|
||||
<filter>
|
||||
<whitelist>
|
||||
<directory>./</directory>
|
||||
<exclude>
|
||||
<directory>./Tests</directory>
|
||||
<directory>./vendor</directory>
|
||||
</exclude>
|
||||
</whitelist>
|
||||
</filter>
|
||||
</phpunit>
|
||||
Reference in New Issue