X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=src%2FUtil%2FStrings.php;h=1d440c19b7eede0aef7e7cd9b8ec13aea6df6c3c;hb=18cd4f7412b5b48108cc1a0d2f5d9d745f8bdbe9;hp=88dd1d39f81edd151151dac1ba6b7449528dd871;hpb=a9e534ea79c70385516ba74c589830ce7a6e4d39;p=friendica.git
diff --git a/src/Util/Strings.php b/src/Util/Strings.php
index 88dd1d39f8..1d440c19b7 100644
--- a/src/Util/Strings.php
+++ b/src/Util/Strings.php
@@ -1,6 +1,22 @@
.
+ *
*/
namespace Friendica\Util;
@@ -9,27 +25,27 @@ use Friendica\Content\ContactSelector;
use Friendica\Core\Logger;
/**
- * @brief This class handles string functions
+ * This class handles string functions
*/
class Strings
{
/**
- * @brief Generates a pseudo-random string of hexadecimal characters
+ * Generates a pseudo-random string of hexadecimal characters
*
* @param int $size
* @return string
* @throws \Exception
*/
- public static function getRandomHex($size = 64)
- {
- $byte_size = ceil($size / 2);
+ public static function getRandomHex($size = 64)
+ {
+ $byte_size = ceil($size / 2);
- $bytes = random_bytes($byte_size);
+ $bytes = random_bytes($byte_size);
- $return = substr(bin2hex($bytes), 0, $size);
+ $return = substr(bin2hex($bytes), 0, $size);
- return $return;
- }
+ return $return;
+ }
/**
* Checks, if the given string is a valid hexadecimal code
@@ -38,296 +54,298 @@ class Strings
*
* @return bool
*/
- public static function isHex($hexCode)
- {
- return !empty($hexCode) ? @preg_match("/^[a-f0-9]{2,}$/i", $hexCode) && !(strlen($hexCode) & 1) : false;
- }
-
- /**
- * @brief This is our primary input filter.
- *
- * Use this on any text input where angle chars are not valid or permitted
- * They will be replaced with safer brackets. This may be filtered further
- * if these are not allowed either.
- *
- * @param string $string Input string
- * @return string Filtered string
- */
- public static function escapeTags($string)
- {
- return str_replace(["<", ">"], ['[', ']'], $string);
- }
-
- /**
- * @brief Use this on "body" or "content" input where angle chars shouldn't be removed,
- * and allow them to be safely displayed.
- * @param string $string
- *
- * @return string
- */
- public static function escapeHtml($string)
- {
- return htmlspecialchars($string, ENT_COMPAT, 'UTF-8', false);
- }
-
- /**
- * @brief Generate a string that's random, but usually pronounceable. Used to generate initial passwords
- *
- * @param int $len length
- *
- * @return string
- */
- public static function getRandomName($len)
- {
- if ($len <= 0) {
- return '';
- }
-
- $vowels = ['a', 'a', 'ai', 'au', 'e', 'e', 'e', 'ee', 'ea', 'i', 'ie', 'o', 'ou', 'u'];
-
- if (mt_rand(0, 5) == 4) {
- $vowels[] = 'y';
- }
-
- $cons = [
- 'b', 'bl', 'br',
- 'c', 'ch', 'cl', 'cr',
- 'd', 'dr',
- 'f', 'fl', 'fr',
- 'g', 'gh', 'gl', 'gr',
- 'h',
- 'j',
- 'k', 'kh', 'kl', 'kr',
- 'l',
- 'm',
- 'n',
- 'p', 'ph', 'pl', 'pr',
- 'qu',
- 'r', 'rh',
- 's' ,'sc', 'sh', 'sm', 'sp', 'st',
- 't', 'th', 'tr',
- 'v',
- 'w', 'wh',
- 'x',
- 'z', 'zh'
- ];
-
- $midcons = ['ck', 'ct', 'gn', 'ld', 'lf', 'lm', 'lt', 'mb', 'mm', 'mn', 'mp',
- 'nd', 'ng', 'nk', 'nt', 'rn', 'rp', 'rt'];
-
- $noend = ['bl', 'br', 'cl', 'cr', 'dr', 'fl', 'fr', 'gl', 'gr',
- 'kh', 'kl', 'kr', 'mn', 'pl', 'pr', 'rh', 'tr', 'qu', 'wh', 'q'];
-
- $start = mt_rand(0, 2);
- if ($start == 0) {
- $table = $vowels;
- } else {
- $table = $cons;
- }
-
- $word = '';
-
- for ($x = 0; $x < $len; $x ++) {
- $r = mt_rand(0, count($table) - 1);
- $word .= $table[$r];
-
- if ($table == $vowels) {
- $table = array_merge($cons, $midcons);
- } else {
- $table = $vowels;
- }
-
- }
-
- $word = substr($word, 0, $len);
-
- foreach ($noend as $noe) {
- $noelen = strlen($noe);
- if ((strlen($word) > $noelen) && (substr($word, -$noelen) == $noe)) {
- $word = self::getRandomName($len);
- break;
- }
- }
-
- return $word;
- }
+ public static function isHex($hexCode)
+ {
+ return !empty($hexCode) ? @preg_match("/^[a-f0-9]{2,}$/i", $hexCode) && !(strlen($hexCode) & 1) : false;
+ }
+
+ /**
+ * This is our primary input filter.
+ *
+ * Use this on any text input where angle chars are not valid or permitted
+ * They will be replaced with safer brackets. This may be filtered further
+ * if these are not allowed either.
+ *
+ * @param string $string Input string
+ * @return string Filtered string
+ */
+ public static function escapeTags($string)
+ {
+ return str_replace(["<", ">"], ['[', ']'], $string);
+ }
+
+ /**
+ * Use this on "body" or "content" input where angle chars shouldn't be removed,
+ * and allow them to be safely displayed.
+ * @param string $string
+ *
+ * @return string
+ */
+ public static function escapeHtml($string)
+ {
+ return htmlspecialchars($string, ENT_COMPAT, 'UTF-8', false);
+ }
+
+ /**
+ * Generate a string that's random, but usually pronounceable. Used to generate initial passwords
+ *
+ * @param int $len length
+ *
+ * @return string
+ */
+ public static function getRandomName($len)
+ {
+ if ($len <= 0) {
+ return '';
+ }
+
+ $vowels = ['a', 'a', 'ai', 'au', 'e', 'e', 'e', 'ee', 'ea', 'i', 'ie', 'o', 'ou', 'u'];
+
+ if (mt_rand(0, 5) == 4) {
+ $vowels[] = 'y';
+ }
+
+ $cons = [
+ 'b', 'bl', 'br',
+ 'c', 'ch', 'cl', 'cr',
+ 'd', 'dr',
+ 'f', 'fl', 'fr',
+ 'g', 'gh', 'gl', 'gr',
+ 'h',
+ 'j',
+ 'k', 'kh', 'kl', 'kr',
+ 'l',
+ 'm',
+ 'n',
+ 'p', 'ph', 'pl', 'pr',
+ 'qu',
+ 'r', 'rh',
+ 's', 'sc', 'sh', 'sm', 'sp', 'st',
+ 't', 'th', 'tr',
+ 'v',
+ 'w', 'wh',
+ 'x',
+ 'z', 'zh'
+ ];
+
+ $midcons = [
+ 'ck', 'ct', 'gn', 'ld', 'lf', 'lm', 'lt', 'mb', 'mm', 'mn', 'mp',
+ 'nd', 'ng', 'nk', 'nt', 'rn', 'rp', 'rt'
+ ];
+
+ $noend = [
+ 'bl', 'br', 'cl', 'cr', 'dr', 'fl', 'fr', 'gl', 'gr',
+ 'kh', 'kl', 'kr', 'mn', 'pl', 'pr', 'rh', 'tr', 'qu', 'wh', 'q'
+ ];
+
+ $start = mt_rand(0, 2);
+ if ($start == 0) {
+ $table = $vowels;
+ } else {
+ $table = $cons;
+ }
+
+ $word = '';
+
+ for ($x = 0; $x < $len; $x++) {
+ $r = mt_rand(0, count($table) - 1);
+ $word .= $table[$r];
+
+ if ($table == $vowels) {
+ $table = array_merge($cons, $midcons);
+ } else {
+ $table = $vowels;
+ }
+ }
+
+ $word = substr($word, 0, $len);
+
+ foreach ($noend as $noe) {
+ $noelen = strlen($noe);
+ if ((strlen($word) > $noelen) && (substr($word, -$noelen) == $noe)) {
+ $word = self::getRandomName($len);
+ break;
+ }
+ }
+
+ return $word;
+ }
/**
* Translate and format the network name of a contact
*
* @param string $network Network name of the contact (e.g. dfrn, rss and so on)
- * @param string $url The contact url
+ * @param string $url The contact url
*
* @return string Formatted network name
* @throws \Friendica\Network\HTTPException\InternalServerErrorException
*/
- public static function formatNetworkName($network, $url = '')
- {
- if ($network != '') {
- if ($url != '') {
- $network_name = '' . ContactSelector::networkToName($network, $url) . '';
- } else {
- $network_name = ContactSelector::networkToName($network);
- }
-
- return $network_name;
- }
- }
-
- /**
- * @brief Remove indentation from a text
- *
- * @param string $text String to be transformed.
- * @param string $chr Optional. Indentation tag. Default tab (\t).
- * @param int $count Optional. Default null.
- *
- * @return string Transformed string.
- */
- public static function deindent($text, $chr = "[\t ]", $count = NULL)
- {
- $lines = explode("\n", $text);
-
- if (is_null($count)) {
- $m = [];
- $k = 0;
- while ($k < count($lines) && strlen($lines[$k]) == 0) {
- $k++;
- }
- preg_match("|^" . $chr . "*|", $lines[$k], $m);
- $count = strlen($m[0]);
- }
-
- for ($k = 0; $k < count($lines); $k++) {
- $lines[$k] = preg_replace("|^" . $chr . "{" . $count . "}|", "", $lines[$k]);
- }
-
- return implode("\n", $lines);
- }
-
- /**
- * @brief Get byte size returned in a Data Measurement (KB, MB, GB)
- *
- * @param int $bytes The number of bytes to be measured
- * @param int $precision Optional. Default 2.
- *
- * @return string Size with measured units.
- */
- public static function formatBytes($bytes, $precision = 2)
- {
- $units = ['B', 'KB', 'MB', 'GB', 'TB'];
- $bytes = max($bytes, 0);
- $pow = floor(($bytes ? log($bytes) : 0) / log(1024));
- $pow = min($pow, count($units) - 1);
- $bytes /= pow(1024, $pow);
-
- return round($bytes, $precision) . ' ' . $units[$pow];
- }
-
- /**
- * @brief Protect percent characters in sprintf calls
- *
- * @param string $s String to transform.
- *
- * @return string Transformed string.
- */
- public static function protectSprintf($s)
- {
- return str_replace('%', '%%', $s);
- }
-
- /**
- * @brief Base64 Encode URL and translate +/ to -_ Optionally strip padding.
- *
- * @param string $s URL to encode
- * @param boolean $strip_padding Optional. Default false
- *
- * @return string Encoded URL
- */
- public static function base64UrlEncode($s, $strip_padding = false)
- {
- $s = strtr(base64_encode($s), '+/', '-_');
-
- if ($strip_padding) {
- $s = str_replace('=', '', $s);
- }
-
- return $s;
- }
+ public static function formatNetworkName($network, $url = '')
+ {
+ if ($network != '') {
+ if ($url != '') {
+ $network_name = '' . ContactSelector::networkToName($network, $url) . '';
+ } else {
+ $network_name = ContactSelector::networkToName($network);
+ }
+
+ return $network_name;
+ }
+ }
+
+ /**
+ * Remove indentation from a text
+ *
+ * @param string $text String to be transformed.
+ * @param string $chr Optional. Indentation tag. Default tab (\t).
+ * @param int $count Optional. Default null.
+ *
+ * @return string Transformed string.
+ */
+ public static function deindent($text, $chr = "[\t ]", $count = NULL)
+ {
+ $lines = explode("\n", $text);
+
+ if (is_null($count)) {
+ $m = [];
+ $k = 0;
+ while ($k < count($lines) && strlen($lines[$k]) == 0) {
+ $k++;
+ }
+ preg_match("|^" . $chr . "*|", $lines[$k], $m);
+ $count = strlen($m[0]);
+ }
+
+ for ($k = 0; $k < count($lines); $k++) {
+ $lines[$k] = preg_replace("|^" . $chr . "{" . $count . "}|", "", $lines[$k]);
+ }
+
+ return implode("\n", $lines);
+ }
+
+ /**
+ * Get byte size returned in a Data Measurement (KB, MB, GB)
+ *
+ * @param int $bytes The number of bytes to be measured
+ * @param int $precision Optional. Default 2.
+ *
+ * @return string Size with measured units.
+ */
+ public static function formatBytes($bytes, $precision = 2)
+ {
+ $units = ['B', 'KB', 'MB', 'GB', 'TB'];
+ $bytes = max($bytes, 0);
+ $pow = floor(($bytes ? log($bytes) : 0) / log(1024));
+ $pow = min($pow, count($units) - 1);
+ $bytes /= pow(1024, $pow);
+
+ return round($bytes, $precision) . ' ' . $units[$pow];
+ }
+
+ /**
+ * Protect percent characters in sprintf calls
+ *
+ * @param string $s String to transform.
+ *
+ * @return string Transformed string.
+ */
+ public static function protectSprintf($s)
+ {
+ return str_replace('%', '%%', $s);
+ }
+
+ /**
+ * Base64 Encode URL and translate +/ to -_ Optionally strip padding.
+ *
+ * @param string $s URL to encode
+ * @param boolean $strip_padding Optional. Default false
+ *
+ * @return string Encoded URL
+ */
+ public static function base64UrlEncode($s, $strip_padding = false)
+ {
+ $s = strtr(base64_encode($s), '+/', '-_');
+
+ if ($strip_padding) {
+ $s = str_replace('=', '', $s);
+ }
+
+ return $s;
+ }
/**
- * @brief Decode Base64 Encoded URL and translate -_ to +/
+ * Decode Base64 Encoded URL and translate -_ to +/
* @param string $s URL to decode
*
- * @return string Decoded URL
+ * @return string Decoded URL
* @throws \Exception
*/
- public static function base64UrlDecode($s)
- {
- if (is_array($s)) {
- Logger::log('base64url_decode: illegal input: ' . print_r(debug_backtrace(), true));
- return $s;
- }
-
- /*
- * // Placeholder for new rev of salmon which strips base64 padding.
- * // PHP base64_decode handles the un-padded input without requiring this step
- * // Uncomment if you find you need it.
- *
- * $l = strlen($s);
- * if (!strpos($s,'=')) {
- * $m = $l % 4;
- * if ($m == 2)
- * $s .= '==';
- * if ($m == 3)
- * $s .= '=';
- * }
- *
- */
-
- return base64_decode(strtr($s, '-_', '+/'));
- }
-
- /**
- * @brief Normalize url
- *
- * @param string $url URL to be normalized.
- *
- * @return string Normalized URL.
- */
- public static function normaliseLink($url)
- {
- $ret = str_replace(['https:', '//www.'], ['http:', '//'], $url);
- return rtrim($ret, '/');
- }
-
- /**
- * @brief Normalize OpenID identity
- *
- * @param string $s OpenID Identity
- *
- * @return string normalized OpenId Identity
- */
- public static function normaliseOpenID($s)
- {
- return trim(str_replace(['http://', 'https://'], ['', ''], $s), '/');
- }
-
- /**
- * @brief Compare two URLs to see if they are the same, but ignore
- * slight but hopefully insignificant differences such as if one
- * is https and the other isn't, or if one is www.something and
- * the other isn't - and also ignore case differences.
- *
- * @param string $a first url
- * @param string $b second url
- * @return boolean True if the URLs match, otherwise False
- *
- */
- public static function compareLink($a, $b)
- {
- return (strcasecmp(self::normaliseLink($a), self::normaliseLink($b)) === 0);
- }
+ public static function base64UrlDecode($s)
+ {
+ if (is_array($s)) {
+ Logger::log('base64url_decode: illegal input: ' . print_r(debug_backtrace(), true));
+ return $s;
+ }
+
+ /*
+ * // Placeholder for new rev of salmon which strips base64 padding.
+ * // PHP base64_decode handles the un-padded input without requiring this step
+ * // Uncomment if you find you need it.
+ *
+ * $l = strlen($s);
+ * if (!strpos($s,'=')) {
+ * $m = $l % 4;
+ * if ($m == 2)
+ * $s .= '==';
+ * if ($m == 3)
+ * $s .= '=';
+ * }
+ *
+ */
+
+ return base64_decode(strtr($s, '-_', '+/'));
+ }
+
+ /**
+ * Normalize url
+ *
+ * @param string $url URL to be normalized.
+ *
+ * @return string Normalized URL.
+ */
+ public static function normaliseLink($url)
+ {
+ $ret = str_replace(['https:', '//www.'], ['http:', '//'], $url);
+ return rtrim($ret, '/');
+ }
+
+ /**
+ * Normalize OpenID identity
+ *
+ * @param string $s OpenID Identity
+ *
+ * @return string normalized OpenId Identity
+ */
+ public static function normaliseOpenID($s)
+ {
+ return trim(str_replace(['http://', 'https://'], ['', ''], $s), '/');
+ }
+ /**
+ * Compare two URLs to see if they are the same, but ignore
+ * slight but hopefully insignificant differences such as if one
+ * is https and the other isn't, or if one is www.something and
+ * the other isn't - and also ignore case differences.
+ *
+ * @param string $a first url
+ * @param string $b second url
+ * @return boolean True if the URLs match, otherwise False
+ *
+ */
+ public static function compareLink($a, $b)
+ {
+ return (strcasecmp(self::normaliseLink($a), self::normaliseLink($b)) === 0);
+ }
/**
* Ensures the provided URI has its query string punctuation in order.
@@ -344,21 +362,50 @@ class Strings
return $uri;
}
-
/**
* Check if the trimmed provided string is starting with one of the provided characters
*
* @param string $string
- * @param array $chars
+ * @param array $chars
* @return bool
*/
- public static function startsWith($string, array $chars)
+ public static function startsWithChars($string, array $chars)
{
$return = in_array(substr(trim($string), 0, 1), $chars);
return $return;
}
+ /**
+ * Check if the first string starts with the second
+ *
+ * @see http://maettig.com/code/php/php-performance-benchmarks.php#startswith
+ * @param string $string
+ * @param string $start
+ * @return bool
+ */
+ public static function startsWith(string $string, string $start)
+ {
+ $return = substr_compare($string, $start, 0, strlen($start)) === 0;
+
+ return $return;
+ }
+
+ /**
+ * Checks if the first string ends with the second
+ *
+ * @see http://maettig.com/code/php/php-performance-benchmarks.php#endswith
+ * @param string $string
+ * @param string $end
+ * @return bool
+ */
+ public static function endsWith(string $string, string $end)
+ {
+ $return = substr_compare($string, $end, -strlen($end)) === 0;
+
+ return $return;
+ }
+
/**
* Returns the regular expression string to match URLs in a given text
*
@@ -368,22 +415,22 @@ class Strings
public static function autoLinkRegEx()
{
return '@
-(??«»ââââ.] # Domain can\'t start with a .
- [^/\s\xA0`!()\[\]{};:\'",<>?«»ââââ]+ # Domain can\'t end with a .
- \.
- [^/\s\xA0`!()\[\]{};:\'".,<>?«»ââââ]+/? # Followed by a slash
+ [^/\s\xA0`!()\[\]{};:\'",<>?«»ââââ.] # Domain can\'t start with a .
+ [^/\s\xA0`!()\[\]{};:\'",<>?«»ââââ]+ # Domain can\'t end with a .
+ \.
+ [^/\s\xA0`!()\[\]{};:\'".,<>?«»ââââ]+/? # Followed by a slash
)
- (?: # One or more:
- [^\s\xA0()<>]+ # Run of non-space, non-()<>
- | # or
- \(([^\s\xA0()<>]+|(\([^\s()<>]+\)))*\) # balanced parens, up to 2 levels
- | # or
- [^\s\xA0`!()\[\]{};:\'".,<>?«»ââââ] # not a space or one of these punct chars
+ (?: # One or more:
+ [^\s\xA0()<>]+ # Run of non-space, non-()<>
+ | # or
+ \(([^\s\xA0()<>]+|(\([^\s()<>]+\)))*\) # balanced parens, up to 2 levels
+ | # or
+ [^\s\xA0`!()\[\]{};:\'".,<>?«»ââââ] # not a space or one of these punct chars
)*
)@xiu';
}
@@ -403,4 +450,90 @@ class Strings
return $pathItem;
}
+
+ /**
+ * Multi-byte safe implementation of substr_replace where $start and $length are character offset and count rather
+ * than byte offset and counts.
+ *
+ * Depends on mbstring, use default encoding.
+ *
+ * @param string $string
+ * @param string $replacement
+ * @param int $start
+ * @param int|null $length
+ * @return string
+ * @see substr_replace()
+ */
+ public static function substringReplace(string $string, string $replacement, int $start, int $length = null)
+ {
+ $string_length = mb_strlen($string);
+
+ $length = $length ?? $string_length;
+
+ if ($start < 0) {
+ $start = max(0, $string_length + $start);
+ } else if ($start > $string_length) {
+ $start = $string_length;
+ }
+
+ if ($length < 0) {
+ $length = max(0, $string_length - $start + $length);
+ } else if ($length > $string_length) {
+ $length = $string_length;
+ }
+
+ if (($start + $length) > $string_length) {
+ $length = $string_length - $start;
+ }
+
+ return mb_substr($string, 0, $start) . $replacement . mb_substr($string, $start + $length, $string_length - $start - $length);
+ }
+
+ /**
+ * Perform a custom function on a text after having escaped blocks matched by the provided regular expressions.
+ * Only full matches are used, capturing group are ignored.
+ *
+ * To change the provided text, the callback function needs to return it and this function will return the modified
+ * version as well after having restored the escaped blocks.
+ *
+ * @param string $text
+ * @param string $regex
+ * @param callable $callback
+ * @return string
+ * @throws \Exception
+ */
+ public static function performWithEscapedBlocks(string $text, string $regex, callable $callback)
+ {
+ // Enables nested use
+ $executionId = random_int(PHP_INT_MAX / 10, PHP_INT_MAX);
+
+ $blocks = [];
+
+ $text = preg_replace_callback($regex,
+ function ($matches) use ($executionId, &$blocks) {
+ $return = '«block-' . $executionId . '-' . count($blocks) . '»';
+
+ $blocks[] = $matches[0];
+
+ return $return;
+ },
+ $text
+ );
+
+ $text = $callback($text) ?? '';
+
+ // Restore code blocks
+ $text = preg_replace_callback('/«block-' . $executionId . '-([0-9]+)»/iU',
+ function ($matches) use ($blocks) {
+ $return = $matches[0];
+ if (isset($blocks[intval($matches[1])])) {
+ $return = $blocks[$matches[1]];
+ }
+ return $return;
+ },
+ $text
+ );
+
+ return $text;
+ }
}