From 686c269bae7de4d84d4dd241c9b9f9092ece4f01 Mon Sep 17 00:00:00 2001
From: Alex Pott <alex.a.pott@googlemail.com>
Date: Wed, 8 May 2013 00:29:47 +0100
Subject: [PATCH] Issue #1938670 by ParisLiakos, Xano, RobLoach, pp, alexpott:
Convert unicode.inc to \Drupal\Component\Utility\Unicode.
---
core/includes/bootstrap.inc | 68 +--
core/includes/theme.maintenance.inc | 4 +-
core/includes/unicode.inc | 393 ++----------
core/lib/Drupal/Component/Utility/String.php | 17 +
core/lib/Drupal/Component/Utility/Unicode.php | 578 ++++++++++++++++++
core/modules/search/search.module | 5 +-
.../system/Tests/System/UnicodeUnitTest.php | 312 ----------
.../Drupal/views/Plugin/views/HandlerBase.php | 5 +-
.../Tests/Component/Utility/StringTest.php | 44 +-
.../Tests/Component/Utility/UnicodeTest.php | 336 ++++++++++
core/tests/bootstrap.php | 5 +
11 files changed, 1034 insertions(+), 733 deletions(-)
create mode 100644 core/lib/Drupal/Component/Utility/Unicode.php
delete mode 100644 core/modules/system/lib/Drupal/system/Tests/System/UnicodeUnitTest.php
create mode 100644 core/tests/Drupal/Tests/Component/Utility/UnicodeTest.php
diff --git a/core/includes/bootstrap.inc b/core/includes/bootstrap.inc
index 25e9b9ab5087..9cdf41f8a773 100644
--- a/core/includes/bootstrap.inc
+++ b/core/includes/bootstrap.inc
@@ -5,6 +5,7 @@
use Drupal\Component\Utility\Settings;
use Drupal\Component\Utility\String;
use Drupal\Component\Utility\Timer;
+use Drupal\Component\Utility\Unicode;
use Drupal\Core\DrupalKernel;
use Drupal\Core\Database\Database;
use Drupal\Core\DependencyInjection\ContainerBuilder;
@@ -270,22 +271,6 @@
*/
const LANGUAGE_RTL = 1;
-/**
- * Indicates an error during check for PHP unicode support.
- */
-const UNICODE_ERROR = -1;
-
-/**
- * Indicates that standard PHP (emulated) unicode support is being used.
- */
-const UNICODE_SINGLEBYTE = 0;
-
-/**
- * Indicates that full unicode support with the PHP mbstring extension is being
- * used.
- */
-const UNICODE_MULTIBYTE = 1;
-
/**
* Time of the current request in seconds elapsed since the Unix Epoch.
*
@@ -667,9 +652,6 @@ function drupal_environment_initialize() {
// Set sane locale settings, to ensure consistent string, dates, times and
// numbers handling.
setlocale(LC_ALL, 'C');
-
- // Detect string handling method.
- unicode_check();
}
/**
@@ -682,51 +664,6 @@ function drupal_valid_http_host($host) {
return preg_match('/^\[?(?:[a-zA-Z0-9-:\]_]+\.?)+$/', $host);
}
-/**
- * Checks for Unicode support in PHP and sets the proper settings if possible.
- *
- * Because Drupal needs to be able to handle text in various encodings, we do
- * not support mbstring function overloading. HTTP input/output conversion must
- * be disabled for similar reasons.
- *
- * @return string
- * A string identifier of a failed multibyte extension check, if any.
- * Otherwise, an empty string.
- */
-function unicode_check() {
- global $multibyte;
-
- // Check for mbstring extension.
- if (!function_exists('mb_strlen')) {
- $multibyte = UNICODE_SINGLEBYTE;
- return 'mb_strlen';
- }
-
- // Check mbstring configuration.
- if (ini_get('mbstring.func_overload') != 0) {
- $multibyte = UNICODE_ERROR;
- return 'mbstring.func_overload';
- }
- if (ini_get('mbstring.encoding_translation') != 0) {
- $multibyte = UNICODE_ERROR;
- return 'mbstring.encoding_translation';
- }
- if (ini_get('mbstring.http_input') != 'pass') {
- $multibyte = UNICODE_ERROR;
- return 'mbstring.http_input';
- }
- if (ini_get('mbstring.http_output') != 'pass') {
- $multibyte = UNICODE_ERROR;
- return 'mbstring.http_output';
- }
-
- // Set appropriate configuration.
- mb_internal_encoding('utf-8');
- mb_language('uni');
- $multibyte = UNICODE_MULTIBYTE;
- return '';
-}
-
/**
* Sets the base URL, cookie domain, and session name from configuration.
*/
@@ -2165,6 +2102,9 @@ function _drupal_bootstrap_configuration() {
// Start a page timer:
Timer::start('page');
+ // Detect string handling method.
+ Unicode::check();
+
// Load the procedural configuration system helper functions.
require_once DRUPAL_ROOT . '/core/includes/config.inc';
diff --git a/core/includes/theme.maintenance.inc b/core/includes/theme.maintenance.inc
index 578d3544c0fd..33d44ee870c0 100644
--- a/core/includes/theme.maintenance.inc
+++ b/core/includes/theme.maintenance.inc
@@ -5,6 +5,8 @@
* Theming for maintenance pages.
*/
+use Drupal\Component\Utility\Unicode;
+
/**
* Sets up the theming system for maintenance page.
*
@@ -28,7 +30,7 @@ function _drupal_maintenance_theme() {
require_once DRUPAL_ROOT . '/core/includes/unicode.inc';
require_once DRUPAL_ROOT . '/core/includes/file.inc';
require_once DRUPAL_ROOT . '/core/includes/module.inc';
- unicode_check();
+ Unicode::check();
// Install and update pages are treated differently to prevent theming overrides.
if (defined('MAINTENANCE_MODE') && (MAINTENANCE_MODE == 'install' || MAINTENANCE_MODE == 'update')) {
diff --git a/core/includes/unicode.inc b/core/includes/unicode.inc
index 70a8fde186c4..1b9bcf15006c 100644
--- a/core/includes/unicode.inc
+++ b/core/includes/unicode.inc
@@ -5,66 +5,8 @@
* Provides Unicode-related conversions and operations.
*/
-/**
- * Matches Unicode characters that are word boundaries.
- *
- * Characters with the following General_category (gc) property values are used
- * as word boundaries. While this does not fully conform to the Word Boundaries
- * algorithm described in http://unicode.org/reports/tr29, as PCRE does not
- * contain the Word_Break property table, this simpler algorithm has to do.
- * - Cc, Cf, Cn, Co, Cs: Other.
- * - Pc, Pd, Pe, Pf, Pi, Po, Ps: Punctuation.
- * - Sc, Sk, Sm, So: Symbols.
- * - Zl, Zp, Zs: Separators.
- *
- * Non-boundary characters include the following General_category (gc) property
- * values:
- * - Ll, Lm, Lo, Lt, Lu: Letters.
- * - Mc, Me, Mn: Combining Marks.
- * - Nd, Nl, No: Numbers.
- *
- * Note that the PCRE property matcher is not used because we wanted to be
- * compatible with Unicode 5.2.0 regardless of the PCRE version used (and any
- * bugs in PCRE property tables).
- *
- * @see http://unicode.org/glossary
- */
-define('PREG_CLASS_UNICODE_WORD_BOUNDARY',
- '\x{0}-\x{2F}\x{3A}-\x{40}\x{5B}-\x{60}\x{7B}-\x{A9}\x{AB}-\x{B1}\x{B4}' .
- '\x{B6}-\x{B8}\x{BB}\x{BF}\x{D7}\x{F7}\x{2C2}-\x{2C5}\x{2D2}-\x{2DF}' .
- '\x{2E5}-\x{2EB}\x{2ED}\x{2EF}-\x{2FF}\x{375}\x{37E}-\x{385}\x{387}\x{3F6}' .
- '\x{482}\x{55A}-\x{55F}\x{589}-\x{58A}\x{5BE}\x{5C0}\x{5C3}\x{5C6}' .
- '\x{5F3}-\x{60F}\x{61B}-\x{61F}\x{66A}-\x{66D}\x{6D4}\x{6DD}\x{6E9}' .
- '\x{6FD}-\x{6FE}\x{700}-\x{70F}\x{7F6}-\x{7F9}\x{830}-\x{83E}' .
- '\x{964}-\x{965}\x{970}\x{9F2}-\x{9F3}\x{9FA}-\x{9FB}\x{AF1}\x{B70}' .
- '\x{BF3}-\x{BFA}\x{C7F}\x{CF1}-\x{CF2}\x{D79}\x{DF4}\x{E3F}\x{E4F}' .
- '\x{E5A}-\x{E5B}\x{F01}-\x{F17}\x{F1A}-\x{F1F}\x{F34}\x{F36}\x{F38}' .
- '\x{F3A}-\x{F3D}\x{F85}\x{FBE}-\x{FC5}\x{FC7}-\x{FD8}\x{104A}-\x{104F}' .
- '\x{109E}-\x{109F}\x{10FB}\x{1360}-\x{1368}\x{1390}-\x{1399}\x{1400}' .
- '\x{166D}-\x{166E}\x{1680}\x{169B}-\x{169C}\x{16EB}-\x{16ED}' .
- '\x{1735}-\x{1736}\x{17B4}-\x{17B5}\x{17D4}-\x{17D6}\x{17D8}-\x{17DB}' .
- '\x{1800}-\x{180A}\x{180E}\x{1940}-\x{1945}\x{19DE}-\x{19FF}' .
- '\x{1A1E}-\x{1A1F}\x{1AA0}-\x{1AA6}\x{1AA8}-\x{1AAD}\x{1B5A}-\x{1B6A}' .
- '\x{1B74}-\x{1B7C}\x{1C3B}-\x{1C3F}\x{1C7E}-\x{1C7F}\x{1CD3}\x{1FBD}' .
- '\x{1FBF}-\x{1FC1}\x{1FCD}-\x{1FCF}\x{1FDD}-\x{1FDF}\x{1FED}-\x{1FEF}' .
- '\x{1FFD}-\x{206F}\x{207A}-\x{207E}\x{208A}-\x{208E}\x{20A0}-\x{20B8}' .
- '\x{2100}-\x{2101}\x{2103}-\x{2106}\x{2108}-\x{2109}\x{2114}' .
- '\x{2116}-\x{2118}\x{211E}-\x{2123}\x{2125}\x{2127}\x{2129}\x{212E}' .
- '\x{213A}-\x{213B}\x{2140}-\x{2144}\x{214A}-\x{214D}\x{214F}' .
- '\x{2190}-\x{244A}\x{249C}-\x{24E9}\x{2500}-\x{2775}\x{2794}-\x{2B59}' .
- '\x{2CE5}-\x{2CEA}\x{2CF9}-\x{2CFC}\x{2CFE}-\x{2CFF}\x{2E00}-\x{2E2E}' .
- '\x{2E30}-\x{3004}\x{3008}-\x{3020}\x{3030}\x{3036}-\x{3037}' .
- '\x{303D}-\x{303F}\x{309B}-\x{309C}\x{30A0}\x{30FB}\x{3190}-\x{3191}' .
- '\x{3196}-\x{319F}\x{31C0}-\x{31E3}\x{3200}-\x{321E}\x{322A}-\x{3250}' .
- '\x{3260}-\x{327F}\x{328A}-\x{32B0}\x{32C0}-\x{33FF}\x{4DC0}-\x{4DFF}' .
- '\x{A490}-\x{A4C6}\x{A4FE}-\x{A4FF}\x{A60D}-\x{A60F}\x{A673}\x{A67E}' .
- '\x{A6F2}-\x{A716}\x{A720}-\x{A721}\x{A789}-\x{A78A}\x{A828}-\x{A82B}' .
- '\x{A836}-\x{A839}\x{A874}-\x{A877}\x{A8CE}-\x{A8CF}\x{A8F8}-\x{A8FA}' .
- '\x{A92E}-\x{A92F}\x{A95F}\x{A9C1}-\x{A9CD}\x{A9DE}-\x{A9DF}' .
- '\x{AA5C}-\x{AA5F}\x{AA77}-\x{AA79}\x{AADE}-\x{AADF}\x{ABEB}' .
- '\x{E000}-\x{F8FF}\x{FB29}\x{FD3E}-\x{FD3F}\x{FDFC}-\x{FDFD}' .
- '\x{FE10}-\x{FE19}\x{FE30}-\x{FE6B}\x{FEFF}-\x{FF0F}\x{FF1A}-\x{FF20}' .
- '\x{FF3B}-\x{FF40}\x{FF5B}-\x{FF65}\x{FFE0}-\x{FFFD}');
+use Drupal\Component\Utility\Unicode;
+use Drupal\Component\Utility\String;
/**
* Returns Unicode library status and errors.
@@ -74,17 +16,17 @@ function unicode_requirements() {
$t = get_t();
$libraries = array(
- UNICODE_SINGLEBYTE => $t('Standard PHP'),
- UNICODE_MULTIBYTE => $t('PHP Mbstring Extension'),
- UNICODE_ERROR => $t('Error'),
+ Unicode::STATUS_SINGLEBYTE => $t('Standard PHP'),
+ Unicode::STATUS_MULTIBYTE => $t('PHP Mbstring Extension'),
+ Unicode::STATUS_ERROR => $t('Error'),
);
$severities = array(
- UNICODE_SINGLEBYTE => REQUIREMENT_WARNING,
- UNICODE_MULTIBYTE => NULL,
- UNICODE_ERROR => REQUIREMENT_ERROR,
+ Unicode::STATUS_SINGLEBYTE => REQUIREMENT_WARNING,
+ Unicode::STATUS_MULTIBYTE => NULL,
+ Unicode::STATUS_ERROR => REQUIREMENT_ERROR,
);
- $failed_check = unicode_check();
- $library = $GLOBALS['multibyte'];
+ $failed_check = Unicode::check();
+ $library = Unicode::getStatus();
$requirements['unicode'] = array(
'title' => $t('Unicode library'),
@@ -176,29 +118,20 @@ function drupal_xml_parser_create(&$data) {
/**
* Converts data to UTF-8.
*
- * Requires the iconv, GNU recode or mbstring PHP extension.
- *
- * @param $data
+ * @param string $data
* The data to be converted.
- * @param $encoding
+ * @param string $encoding
* The encoding that the data is in.
*
- * @return
+ * @return string|bool
* Converted data or FALSE.
+ *
+ * @see \Drupal\Component\Utility\Unicode::convertToUtf8().
*/
function drupal_convert_to_utf8($data, $encoding) {
- if (function_exists('iconv')) {
- $out = @iconv($encoding, 'utf-8', $data);
- }
- elseif (function_exists('mb_convert_encoding')) {
- $out = @mb_convert_encoding($data, 'utf-8', $encoding);
- }
- elseif (function_exists('recode_string')) {
- $out = @recode_string($encoding . '..utf-8', $data);
- }
- else {
+ $out = Unicode::convertToUtf8($data, $encoding);
+ if ($out === FALSE) {
watchdog('php', 'Unsupported encoding %s. Please install iconv, GNU recode or mbstring for PHP.', array('%s' => $encoding), WATCHDOG_ERROR);
- return FALSE;
}
return $out;
@@ -207,33 +140,18 @@ function drupal_convert_to_utf8($data, $encoding) {
/**
* Truncates a UTF-8-encoded string safely to a number of bytes.
*
- * If the end position is in the middle of a UTF-8 sequence, it scans backwards
- * until the beginning of the byte sequence.
- *
- * Use this function whenever you want to chop off a string at an unsure
- * location. On the other hand, if you're sure that you're splitting on a
- * character boundary (e.g. after using strpos() or similar), you can safely
- * use substr() instead.
- *
- * @param $string
+ * @param string $string
* The string to truncate.
- * @param $len
+ * @param int $len
* An upper limit on the returned string length.
*
- * @return
+ * @return string
* The truncated string.
+ *
+ * @see \Drupal\Component\Utility\Unicode::truncateBytes().
*/
function drupal_truncate_bytes($string, $len) {
- if (strlen($string) <= $len) {
- return $string;
- }
- if ((ord($string[$len]) < 0x80) || (ord($string[$len]) >= 0xC0)) {
- return substr($string, 0, $len);
- }
- // Scan backwards to beginning of the byte sequence.
- while (--$len >= 0 && ord($string[$len]) >= 0x80 && ord($string[$len]) < 0xC0);
-
- return substr($string, 0, $len);
+ return Unicode::truncateBytes($string, $len);
}
/**
@@ -247,7 +165,7 @@ function drupal_truncate_bytes($string, $len) {
* @param $wordsafe
* If TRUE, attempt to truncate on a word boundary. Word boundaries are
* spaces, punctuation, and Unicode characters used as word boundaries in
- * non-Latin languages; see PREG_CLASS_UNICODE_WORD_BOUNDARY for more
+ * non-Latin languages; see Unicode::PREG_CLASS_WORD_BOUNDARY for more
* information. If a word boundary cannot be found that would make the length
* of the returned string fall within length guidelines (see parameters
* $max_length and $min_wordsafe_length), word boundaries are ignored.
@@ -269,70 +187,16 @@ function drupal_truncate_bytes($string, $len) {
*
* @return string
* The truncated string.
+ *
+ * @see \Drupal\Component\Utility\Unicode::truncate().
*/
function truncate_utf8($string, $max_length, $wordsafe = FALSE, $add_ellipsis = FALSE, $min_wordsafe_length = 1) {
- $ellipsis = '';
- $max_length = max($max_length, 0);
- $min_wordsafe_length = max($min_wordsafe_length, 0);
-
- if (drupal_strlen($string) <= $max_length) {
- // No truncation needed, so don't add ellipsis, just return.
- return $string;
- }
-
- if ($add_ellipsis) {
- // Truncate ellipsis in case $max_length is small.
- $ellipsis = drupal_substr(t('…'), 0, $max_length);
- $max_length -= drupal_strlen($ellipsis);
- $max_length = max($max_length, 0);
- }
-
- if ($max_length <= $min_wordsafe_length) {
- // Do not attempt word-safe if lengths are bad.
- $wordsafe = FALSE;
- }
-
- if ($wordsafe) {
- $matches = array();
- // Find the last word boundary, if there is one within $min_wordsafe_length
- // to $max_length characters. preg_match() is always greedy, so it will
- // find the longest string possible.
- $found = preg_match('/^(.{' . $min_wordsafe_length . ',' . $max_length . '})[' . PREG_CLASS_UNICODE_WORD_BOUNDARY . ']/u', $string, $matches);
- if ($found) {
- $string = $matches[1];
- }
- else {
- $string = drupal_substr($string, 0, $max_length);
- }
- }
- else {
- $string = drupal_substr($string, 0, $max_length);
- }
-
- if ($add_ellipsis) {
- // If we're adding an ellipsis, remove any trailing periods.
- $string = rtrim($string, '.');
-
- $string .= $ellipsis;
- }
-
- return $string;
+ return Unicode::truncate($string, $max_length, $wordsafe, $add_ellipsis, $min_wordsafe_length);
}
/**
* Encodes MIME/HTTP header values that contain incorrectly encoded characters.
*
- * For example, mime_header_encode('tést.txt') returns "=?UTF-8?B?dMOpc3QudHh0?=".
- *
- * See http://www.rfc-editor.org/rfc/rfc2047.txt for more information.
- *
- * Notes:
- * - Only encode strings that contain non-ASCII characters.
- * - We progressively cut-off a chunk with truncate_utf8(). This is to ensure
- * each chunk starts and ends on a character boundary.
- * - Using \n as the chunk separator may cause problems on some systems and may
- * have to be changed to \r\n or \r.
- *
* @param $string
* The header to encode.
*
@@ -340,22 +204,10 @@ function truncate_utf8($string, $max_length, $wordsafe = FALSE, $add_ellipsis =
* The mime-encoded header.
*
* @see mime_header_decode()
+ * @see \Drupal\Component\Utility\Unicode::mimeHeaderEncode().
*/
function mime_header_encode($string) {
- if (preg_match('/[^\x20-\x7E]/', $string)) {
- $chunk_size = 47; // floor((75 - strlen("=?UTF-8?B??=")) * 0.75);
- $len = strlen($string);
- $output = '';
- while ($len > 0) {
- $chunk = drupal_truncate_bytes($string, $chunk_size);
- $output .= ' =?UTF-8?B?' . base64_encode($chunk) . "?=\n";
- $c = strlen($chunk);
- $string = substr($string, $c);
- $len -= $c;
- }
- return trim($output);
- }
- return $string;
+ return Unicode::mimeHeaderEncode($string);
}
/**
@@ -368,78 +220,41 @@ function mime_header_encode($string) {
* The mime-decoded header.
*
* @see mime_header_encode()
+ * @see \Drupal\Component\Utility\Unicode::mimeHeaderDecode().
*/
function mime_header_decode($header) {
- // First step: encoded chunks followed by other encoded chunks (need to collapse whitespace)
- $header = preg_replace_callback('/=\?([^?]+)\?(Q|B)\?([^?]+|\?(?!=))\?=\s+(?==\?)/', '_mime_header_decode', $header);
- // Second step: remaining chunks (do not collapse whitespace)
- return preg_replace_callback('/=\?([^?]+)\?(Q|B)\?([^?]+|\?(?!=))\?=/', '_mime_header_decode', $header);
-}
-
-/**
- * Decodes encoded header data passed from mime_header_decode().
- *
- * Callback for preg_replace_callback() within mime_header_decode().
- *
- * @param $matches
- * The array of matches from preg_replace_callback().
- *
- * @return string
- * The mime-decoded string.
- *
- * @see mime_header_decode()
- */
-function _mime_header_decode($matches) {
- // Regexp groups:
- // 1: Character set name
- // 2: Escaping method (Q or B)
- // 3: Encoded data
- $data = ($matches[2] == 'B') ? base64_decode($matches[3]) : str_replace('_', ' ', quoted_printable_decode($matches[3]));
- if (strtolower($matches[1]) != 'utf-8') {
- $data = drupal_convert_to_utf8($data, $matches[1]);
- }
- return $data;
+ return Unicode::mimeHeaderDecode($header);
}
/**
* Decodes all HTML entities (including numerical ones) to regular UTF-8 bytes.
*
- * Double-escaped entities will only be decoded once ("&lt;" becomes "<"
- * , not "<"). Be careful when using this function, as decode_entities can
- * revert previous sanitization efforts (<script> will become <script>).
- *
* @param $text
* The text to decode entities in.
*
* @return
* The input $text, with all HTML entities decoded once.
+ *
+ * @see \Drupal\Component\Utility\String::decodeEntities().
*/
function decode_entities($text) {
- return html_entity_decode($text, ENT_QUOTES, 'UTF-8');
+ return String::decodeEntities($text);
}
/**
* Counts the number of characters in a UTF-8 string.
*
- * This is less than or equal to the byte count.
- *
* @param $text
* The string to run the operation on.
*
* @return integer
* The length of the string.
*
+ * @see \Drupal\Component\Utility\Unicode::strlen().
* @ingroup php_wrappers
*/
function drupal_strlen($text) {
- global $multibyte;
- if ($multibyte == UNICODE_MULTIBYTE) {
- return mb_strlen($text);
- }
- else {
- // Do not count UTF-8 continuation bytes.
- return strlen(preg_replace("/[\x80-\xBF]/", '', $text));
- }
+ return Unicode::strlen($text);
}
/**
@@ -451,20 +266,11 @@ function drupal_strlen($text) {
* @return string
* The string in uppercase.
*
+ * @see \Drupal\Component\Utility\Unicode::strtoupper().
* @ingroup php_wrappers
*/
function drupal_strtoupper($text) {
- global $multibyte;
- if ($multibyte == UNICODE_MULTIBYTE) {
- return mb_strtoupper($text);
- }
- else {
- // Use C-locale for ASCII-only uppercase
- $text = strtoupper($text);
- // Case flip Latin-1 accented letters
- $text = preg_replace_callback('/\xC3[\xA0-\xB6\xB8-\xBE]/', '_unicode_caseflip', $text);
- return $text;
- }
+ return Unicode::strtoupper($text);
}
/**
@@ -476,35 +282,11 @@ function drupal_strtoupper($text) {
* @return string
* The string in lowercase.
*
+ * @see \Drupal\Component\Utility\Unicode::strtolower().
* @ingroup php_wrappers
*/
function drupal_strtolower($text) {
- global $multibyte;
- if ($multibyte == UNICODE_MULTIBYTE) {
- return mb_strtolower($text);
- }
- else {
- // Use C-locale for ASCII-only lowercase
- $text = strtolower($text);
- // Case flip Latin-1 accented letters
- $text = preg_replace_callback('/\xC3[\x80-\x96\x98-\x9E]/', '_unicode_caseflip', $text);
- return $text;
- }
-}
-
-/**
- * Flips U+C0-U+DE to U+E0-U+FD and back.
- *
- * @param $matches
- * An array of matches.
- *
- * @return array
- * The Latin-1 version of the array of matches.
- *
- * @see drupal_strtolower()
- */
-function _unicode_caseflip($matches) {
- return $matches[0][0] . chr(ord($matches[0][1]) ^ 32);
+ return Unicode::strtolower($text);
}
/**
@@ -516,20 +298,16 @@ function _unicode_caseflip($matches) {
* @return
* The string with the first letter as uppercase.
*
+ * @see \Drupal\Component\Utility\Unicode::ucfirst().
* @ingroup php_wrappers
*/
function drupal_ucfirst($text) {
- // Note: no mbstring equivalent!
- return drupal_strtoupper(drupal_substr($text, 0, 1)) . drupal_substr($text, 1);
+ return Unicode::ucfirst($text);
}
/**
* Cuts off a piece of a string based on character indices and counts.
*
- * Follows the same behavior as PHP's own substr() function. Note that for
- * cutting off a string at a known character/substring location, the usage of
- * PHP's normal strpos/substr is safe and much faster.
- *
* @param $text
* The input string.
* @param $start
@@ -540,92 +318,9 @@ function drupal_ucfirst($text) {
* @return
* The shortened string.
*
+ * @see \Drupal\Component\Utility\Unicode::substr().
* @ingroup php_wrappers
*/
function drupal_substr($text, $start, $length = NULL) {
- global $multibyte;
- if ($multibyte == UNICODE_MULTIBYTE) {
- return $length === NULL ? mb_substr($text, $start) : mb_substr($text, $start, $length);
- }
- else {
- $strlen = strlen($text);
- // Find the starting byte offset.
- $bytes = 0;
- if ($start > 0) {
- // Count all the continuation bytes from the start until we have found
- // $start characters or the end of the string.
- $bytes = -1; $chars = -1;
- while ($bytes < $strlen - 1 && $chars < $start) {
- $bytes++;
- $c = ord($text[$bytes]);
- if ($c < 0x80 || $c >= 0xC0) {
- $chars++;
- }
- }
- }
- elseif ($start < 0) {
- // Count all the continuation bytes from the end until we have found
- // abs($start) characters.
- $start = abs($start);
- $bytes = $strlen; $chars = 0;
- while ($bytes > 0 && $chars < $start) {
- $bytes--;
- $c = ord($text[$bytes]);
- if ($c < 0x80 || $c >= 0xC0) {
- $chars++;
- }
- }
- }
- $istart = $bytes;
-
- // Find the ending byte offset.
- if ($length === NULL) {
- $iend = $strlen;
- }
- elseif ($length > 0) {
- // Count all the continuation bytes from the starting index until we have
- // found $length characters or reached the end of the string, then
- // backtrace one byte.
- $iend = $istart - 1;
- $chars = -1;
- $last_real = FALSE;
- while ($iend < $strlen - 1 && $chars < $length) {
- $iend++;
- $c = ord($text[$iend]);
- $last_real = FALSE;
- if ($c < 0x80 || $c >= 0xC0) {
- $chars++;
- $last_real = TRUE;
- }
- }
- // Backtrace one byte if the last character we found was a real character
- // and we don't need it.
- if ($last_real && $chars >= $length) {
- $iend--;
- }
- }
- elseif ($length < 0) {
- // Count all the continuation bytes from the end until we have found
- // abs($start) characters, then backtrace one byte.
- $length = abs($length);
- $iend = $strlen; $chars = 0;
- while ($iend > 0 && $chars < $length) {
- $iend--;
- $c = ord($text[$iend]);
- if ($c < 0x80 || $c >= 0xC0) {
- $chars++;
- }
- }
- // Backtrace one byte if we are not at the beginning of the string.
- if ($iend > 0) {
- $iend--;
- }
- }
- else {
- // $length == 0, return an empty string.
- return '';
- }
-
- return substr($text, $istart, max(0, $iend - $istart + 1));
- }
+ return Unicode::substr($text, $start, $length);
}
diff --git a/core/lib/Drupal/Component/Utility/String.php b/core/lib/Drupal/Component/Utility/String.php
index c79b5af2b1d1..a6df8fe6780f 100644
--- a/core/lib/Drupal/Component/Utility/String.php
+++ b/core/lib/Drupal/Component/Utility/String.php
@@ -31,6 +31,23 @@ public static function checkPlain($text) {
return htmlspecialchars($text, ENT_QUOTES, 'UTF-8');
}
+ /**
+ * Decodes all HTML entities including numerical ones to regular UTF-8 bytes.
+ *
+ * Double-escaped entities will only be decoded once ("&lt;" becomes
+ * "<", not "<"). Be careful when using this function, as it will revert
+ * previous sanitization efforts (<script> will become <script>).
+ *
+ * @param string $text
+ * The text to decode entities in.
+ *
+ * @return string
+ * The input $text, with all HTML entities decoded once.
+ */
+ public static function decodeEntities($text) {
+ return html_entity_decode($text, ENT_QUOTES, 'UTF-8');
+ }
+
/**
* Formats a string for HTML display by replacing variable placeholders.
*
diff --git a/core/lib/Drupal/Component/Utility/Unicode.php b/core/lib/Drupal/Component/Utility/Unicode.php
new file mode 100644
index 000000000000..6ee23d11d6f8
--- /dev/null
+++ b/core/lib/Drupal/Component/Utility/Unicode.php
@@ -0,0 +1,578 @@
+<?php
+
+/**
+ * @file
+ * Contains \Drupal\Component\Utility\Unicode.
+ */
+
+namespace Drupal\Component\Utility;
+
+/**
+ * Provides Unicode-related conversions and operations.
+ */
+class Unicode {
+
+ /**
+ * Matches Unicode characters that are word boundaries.
+ *
+ * Characters with the following General_category (gc) property values are used
+ * as word boundaries. While this does not fully conform to the Word Boundaries
+ * algorithm described in http://unicode.org/reports/tr29, as PCRE does not
+ * contain the Word_Break property table, this simpler algorithm has to do.
+ * - Cc, Cf, Cn, Co, Cs: Other.
+ * - Pc, Pd, Pe, Pf, Pi, Po, Ps: Punctuation.
+ * - Sc, Sk, Sm, So: Symbols.
+ * - Zl, Zp, Zs: Separators.
+ *
+ * Non-boundary characters include the following General_category (gc) property
+ * values:
+ * - Ll, Lm, Lo, Lt, Lu: Letters.
+ * - Mc, Me, Mn: Combining Marks.
+ * - Nd, Nl, No: Numbers.
+ *
+ * Note that the PCRE property matcher is not used because we wanted to be
+ * compatible with Unicode 5.2.0 regardless of the PCRE version used (and any
+ * bugs in PCRE property tables).
+ *
+ * @see http://unicode.org/glossary
+ */
+ const PREG_CLASS_WORD_BOUNDARY = <<< 'EOD'
+\x{0}-\x{2F}\x{3A}-\x{40}\x{5B}-\x{60}\x{7B}-\x{A9}\x{AB}-\x{B1}\x{B4}
+\x{B6}-\x{B8}\x{BB}\x{BF}\x{D7}\x{F7}\x{2C2}-\x{2C5}\x{2D2}-\x{2DF}
+\x{2E5}-\x{2EB}\x{2ED}\x{2EF}-\x{2FF}\x{375}\x{37E}-\x{385}\x{387}\x{3F6}
+\x{482}\x{55A}-\x{55F}\x{589}-\x{58A}\x{5BE}\x{5C0}\x{5C3}\x{5C6}
+\x{5F3}-\x{60F}\x{61B}-\x{61F}\x{66A}-\x{66D}\x{6D4}\x{6DD}\x{6E9}
+\x{6FD}-\x{6FE}\x{700}-\x{70F}\x{7F6}-\x{7F9}\x{830}-\x{83E}
+\x{964}-\x{965}\x{970}\x{9F2}-\x{9F3}\x{9FA}-\x{9FB}\x{AF1}\x{B70}
+\x{BF3}-\x{BFA}\x{C7F}\x{CF1}-\x{CF2}\x{D79}\x{DF4}\x{E3F}\x{E4F}
+\x{E5A}-\x{E5B}\x{F01}-\x{F17}\x{F1A}-\x{F1F}\x{F34}\x{F36}\x{F38}
+\x{F3A}-\x{F3D}\x{F85}\x{FBE}-\x{FC5}\x{FC7}-\x{FD8}\x{104A}-\x{104F}
+\x{109E}-\x{109F}\x{10FB}\x{1360}-\x{1368}\x{1390}-\x{1399}\x{1400}
+\x{166D}-\x{166E}\x{1680}\x{169B}-\x{169C}\x{16EB}-\x{16ED}
+\x{1735}-\x{1736}\x{17B4}-\x{17B5}\x{17D4}-\x{17D6}\x{17D8}-\x{17DB}
+\x{1800}-\x{180A}\x{180E}\x{1940}-\x{1945}\x{19DE}-\x{19FF}
+\x{1A1E}-\x{1A1F}\x{1AA0}-\x{1AA6}\x{1AA8}-\x{1AAD}\x{1B5A}-\x{1B6A}
+\x{1B74}-\x{1B7C}\x{1C3B}-\x{1C3F}\x{1C7E}-\x{1C7F}\x{1CD3}\x{1FBD}
+\x{1FBF}-\x{1FC1}\x{1FCD}-\x{1FCF}\x{1FDD}-\x{1FDF}\x{1FED}-\x{1FEF}
+\x{1FFD}-\x{206F}\x{207A}-\x{207E}\x{208A}-\x{208E}\x{20A0}-\x{20B8}
+\x{2100}-\x{2101}\x{2103}-\x{2106}\x{2108}-\x{2109}\x{2114}
+\x{2116}-\x{2118}\x{211E}-\x{2123}\x{2125}\x{2127}\x{2129}\x{212E}
+\x{213A}-\x{213B}\x{2140}-\x{2144}\x{214A}-\x{214D}\x{214F}
+\x{2190}-\x{244A}\x{249C}-\x{24E9}\x{2500}-\x{2775}\x{2794}-\x{2B59}
+\x{2CE5}-\x{2CEA}\x{2CF9}-\x{2CFC}\x{2CFE}-\x{2CFF}\x{2E00}-\x{2E2E}
+\x{2E30}-\x{3004}\x{3008}-\x{3020}\x{3030}\x{3036}-\x{3037}
+\x{303D}-\x{303F}\x{309B}-\x{309C}\x{30A0}\x{30FB}\x{3190}-\x{3191}
+\x{3196}-\x{319F}\x{31C0}-\x{31E3}\x{3200}-\x{321E}\x{322A}-\x{3250}
+\x{3260}-\x{327F}\x{328A}-\x{32B0}\x{32C0}-\x{33FF}\x{4DC0}-\x{4DFF}
+\x{A490}-\x{A4C6}\x{A4FE}-\x{A4FF}\x{A60D}-\x{A60F}\x{A673}\x{A67E}
+\x{A6F2}-\x{A716}\x{A720}-\x{A721}\x{A789}-\x{A78A}\x{A828}-\x{A82B}
+\x{A836}-\x{A839}\x{A874}-\x{A877}\x{A8CE}-\x{A8CF}\x{A8F8}-\x{A8FA}
+\x{A92E}-\x{A92F}\x{A95F}\x{A9C1}-\x{A9CD}\x{A9DE}-\x{A9DF}
+\x{AA5C}-\x{AA5F}\x{AA77}-\x{AA79}\x{AADE}-\x{AADF}\x{ABEB}
+\x{E000}-\x{F8FF}\x{FB29}\x{FD3E}-\x{FD3F}\x{FDFC}-\x{FDFD}
+\x{FE10}-\x{FE19}\x{FE30}-\x{FE6B}\x{FEFF}-\x{FF0F}\x{FF1A}-\x{FF20}
+\x{FF3B}-\x{FF40}\x{FF5B}-\x{FF65}\x{FFE0}-\x{FFFD}
+EOD;
+
+ /**
+ * Indicates that standard PHP (emulated) unicode support is being used.
+ */
+ const STATUS_SINGLEBYTE = 0;
+
+ /**
+ * Indicates that full unicode support with the PHP mbstring extension is
+ * being used.
+ */
+ const STATUS_MULTIBYTE = 1;
+
+ /**
+ * Indicates an error during check for PHP unicode support.
+ */
+ const STATUS_ERROR = -1;
+
+ /**
+ * Holds the multibyte capabilities of the current enviroment.
+ *
+ * @var int
+ */
+ protected static $status = 0;
+
+ /**
+ * Get the current status of unicode/multibyte support on this enviroment.
+ *
+ * @return int
+ * The status of multibyte support. It can be one of:
+ * - \Drupal\Component\Utility\Unicode::STATUS_MULTIBYTE
+ * Full unicode support using an extension.
+ * - \Drupal\Component\Utility\Unicode::STATUS_SINGLEBYTE
+ * Standard PHP (emulated) unicode support.
+ * - \Drupal\Component\Utility\Unicode::STATUS_ERROR
+ * An error occured. No unicode support.
+ */
+ public static function getStatus() {
+ return static::$status;
+ }
+
+ /**
+ * Sets the value for multibyte support status for the current enviroment.
+ *
+ * The following status keys are supported:
+ * - \Drupal\Component\Utility\Unicode::STATUS_MULTIBYTE
+ * Full unicode support using an extension.
+ * - \Drupal\Component\Utility\Unicode::STATUS_SINGLEBYTE
+ * Standard PHP (emulated) unicode support.
+ * - \Drupal\Component\Utility\Unicode::STATUS_ERROR
+ * An error occured. No unicode support.
+ *
+ * @param int $status
+ * The new status of multibyte support.
+ */
+ public static function setStatus($status) {
+ if (!in_array($status, array(static::STATUS_SINGLEBYTE, static::STATUS_MULTIBYTE, static::STATUS_ERROR))) {
+ throw new \InvalidArgumentException('Invalid status value for unicode support.');
+ }
+ static::$status = $status;
+ }
+
+ /**
+ * Checks for Unicode support in PHP and sets the proper settings if possible.
+ *
+ * Because of the need to be able to handle text in various encodings, we do
+ * not support mbstring function overloading. HTTP input/output conversion
+ * must be disabled for similar reasons.
+ *
+ * @return string
+ * A string identifier of a failed multibyte extension check, if any.
+ * Otherwise, an empty string.
+ */
+ public static function check() {
+ // Check for mbstring extension.
+ if (!function_exists('mb_strlen')) {
+ static::$status = static::STATUS_SINGLEBYTE;
+ return 'mb_strlen';
+ }
+
+ // Check mbstring configuration.
+ if (ini_get('mbstring.func_overload') != 0) {
+ static::$status = static::STATUS_ERROR;
+ return 'mbstring.func_overload';
+ }
+ if (ini_get('mbstring.encoding_translation') != 0) {
+ static::$status = static::STATUS_ERROR;
+ return 'mbstring.encoding_translation';
+ }
+ if (ini_get('mbstring.http_input') != 'pass') {
+ static::$status = static::STATUS_ERROR;
+ return 'mbstring.http_input';
+ }
+ if (ini_get('mbstring.http_output') != 'pass') {
+ static::$status = static::STATUS_ERROR;
+ return 'mbstring.http_output';
+ }
+
+ // Set appropriate configuration.
+ mb_internal_encoding('utf-8');
+ mb_language('uni');
+ static::$status = static::STATUS_MULTIBYTE;
+ return '';
+ }
+
+ /**
+ * Converts data to UTF-8.
+ *
+ * Requires the iconv, GNU recode or mbstring PHP extension.
+ *
+ * @param string $data
+ * The data to be converted.
+ * @param string $encoding
+ * The encoding that the data is in.
+ *
+ * @return string|bool
+ * Converted data or FALSE.
+ */
+ public static function convertToUtf8($data, $encoding) {
+ if (function_exists('iconv')) {
+ return @iconv($encoding, 'utf-8', $data);
+ }
+ elseif (function_exists('mb_convert_encoding')) {
+ return @mb_convert_encoding($data, 'utf-8', $encoding);
+ }
+ elseif (function_exists('recode_string')) {
+ return @recode_string($encoding . '..utf-8', $data);
+ }
+ // Cannot convert.
+ return FALSE;
+ }
+
+ /**
+ * Truncates a UTF-8-encoded string safely to a number of bytes.
+ *
+ * If the end position is in the middle of a UTF-8 sequence, it scans backwards
+ * until the beginning of the byte sequence.
+ *
+ * Use this function whenever you want to chop off a string at an unsure
+ * location. On the other hand, if you're sure that you're splitting on a
+ * character boundary (e.g. after using strpos() or similar), you can safely
+ * use substr() instead.
+ *
+ * @param string $string
+ * The string to truncate.
+ * @param int $len
+ * An upper limit on the returned string length.
+ *
+ * @return string
+ * The truncated string.
+ */
+ public static function truncateBytes($string, $len) {
+ if (strlen($string) <= $len) {
+ return $string;
+ }
+ if ((ord($string[$len]) < 0x80) || (ord($string[$len]) >= 0xC0)) {
+ return substr($string, 0, $len);
+ }
+ // Scan backwards to beginning of the byte sequence.
+ while (--$len >= 0 && ord($string[$len]) >= 0x80 && ord($string[$len]) < 0xC0);
+
+ return substr($string, 0, $len);
+ }
+
+ /**
+ * Counts the number of characters in a UTF-8 string.
+ *
+ * This is less than or equal to the byte count.
+ *
+ * @param string $text
+ * The string to run the operation on.
+ *
+ * @return int
+ * The length of the string.
+ */
+ public static function strlen($text) {
+ if (static::getStatus() == static::STATUS_MULTIBYTE) {
+ return mb_strlen($text);
+ }
+ else {
+ // Do not count UTF-8 continuation bytes.
+ return strlen(preg_replace("/[\x80-\xBF]/", '', $text));
+ }
+ }
+
+ /**
+ * Uppercase a UTF-8 string.
+ *
+ * @param string $text
+ * The string to run the operation on.
+ *
+ * @return string
+ * The string in uppercase.
+ */
+ public static function strtoupper($text) {
+ if (static::getStatus() == static::STATUS_MULTIBYTE) {
+ return mb_strtoupper($text);
+ }
+ else {
+ // Use C-locale for ASCII-only uppercase.
+ $text = strtoupper($text);
+ // Case flip Latin-1 accented letters.
+ $text = preg_replace_callback('/\xC3[\xA0-\xB6\xB8-\xBE]/', '\Drupal\Component\Utility\Unicode::caseFlip', $text);
+ return $text;
+ }
+ }
+
+ /**
+ * Lowercase a UTF-8 string.
+ *
+ * @param string $text
+ * The string to run the operation on.
+ *
+ * @return string
+ * The string in lowercase.
+ */
+ public static function strtolower($text) {
+ if (static::getStatus() == static::STATUS_MULTIBYTE) {
+ return mb_strtolower($text);
+ }
+ else {
+ // Use C-locale for ASCII-only lowercase.
+ $text = strtolower($text);
+ // Case flip Latin-1 accented letters.
+ $text = preg_replace_callback('/\xC3[\x80-\x96\x98-\x9E]/', '\Drupal\Component\Utility\Unicode::caseFlip', $text);
+ return $text;
+ }
+ }
+
+ /**
+ * Capitalizes the first letter of a UTF-8 string.
+ *
+ * @param string $text
+ * The string to convert.
+ *
+ * @return string
+ * The string with the first letter as uppercase.
+ */
+ public static function ucfirst($text) {
+ return static::strtoupper(static::substr($text, 0, 1)) . static::substr($text, 1);
+ }
+
+ /**
+ * Cuts off a piece of a string based on character indices and counts.
+ *
+ * Follows the same behavior as PHP's own substr() function. Note that for
+ * cutting off a string at a known character/substring location, the usage of
+ * PHP's normal strpos/substr is safe and much faster.
+ *
+ * @param string $text
+ * The input string.
+ * @param int $start
+ * The position at which to start reading.
+ * @param int $length
+ * The number of characters to read.
+ *
+ * @return string
+ * The shortened string.
+ */
+ public static function substr($text, $start, $length = NULL) {
+ if (static::getStatus() == static::STATUS_MULTIBYTE) {
+ return $length === NULL ? mb_substr($text, $start) : mb_substr($text, $start, $length);
+ }
+ else {
+ $strlen = strlen($text);
+ // Find the starting byte offset.
+ $bytes = 0;
+ if ($start > 0) {
+ // Count all the continuation bytes from the start until we have found
+ // $start characters or the end of the string.
+ $bytes = -1; $chars = -1;
+ while ($bytes < $strlen - 1 && $chars < $start) {
+ $bytes++;
+ $c = ord($text[$bytes]);
+ if ($c < 0x80 || $c >= 0xC0) {
+ $chars++;
+ }
+ }
+ }
+ elseif ($start < 0) {
+ // Count all the continuation bytes from the end until we have found
+ // abs($start) characters.
+ $start = abs($start);
+ $bytes = $strlen; $chars = 0;
+ while ($bytes > 0 && $chars < $start) {
+ $bytes--;
+ $c = ord($text[$bytes]);
+ if ($c < 0x80 || $c >= 0xC0) {
+ $chars++;
+ }
+ }
+ }
+ $istart = $bytes;
+
+ // Find the ending byte offset.
+ if ($length === NULL) {
+ $iend = $strlen;
+ }
+ elseif ($length > 0) {
+ // Count all the continuation bytes from the starting index until we have
+ // found $length characters or reached the end of the string, then
+ // backtrace one byte.
+ $iend = $istart - 1;
+ $chars = -1;
+ $last_real = FALSE;
+ while ($iend < $strlen - 1 && $chars < $length) {
+ $iend++;
+ $c = ord($text[$iend]);
+ $last_real = FALSE;
+ if ($c < 0x80 || $c >= 0xC0) {
+ $chars++;
+ $last_real = TRUE;
+ }
+ }
+ // Backtrace one byte if the last character we found was a real character
+ // and we don't need it.
+ if ($last_real && $chars >= $length) {
+ $iend--;
+ }
+ }
+ elseif ($length < 0) {
+ // Count all the continuation bytes from the end until we have found
+ // abs($start) characters, then backtrace one byte.
+ $length = abs($length);
+ $iend = $strlen; $chars = 0;
+ while ($iend > 0 && $chars < $length) {
+ $iend--;
+ $c = ord($text[$iend]);
+ if ($c < 0x80 || $c >= 0xC0) {
+ $chars++;
+ }
+ }
+ // Backtrace one byte if we are not at the beginning of the string.
+ if ($iend > 0) {
+ $iend--;
+ }
+ }
+ else {
+ // $length == 0, return an empty string.
+ return '';
+ }
+
+ return substr($text, $istart, max(0, $iend - $istart + 1));
+ }
+ }
+
+ /**
+ * Truncates a UTF-8-encoded string safely to a number of characters.
+ *
+ * @param string $string
+ * The string to truncate.
+ * @param int $max_length
+ * An upper limit on the returned string length, including trailing ellipsis
+ * if $add_ellipsis is TRUE.
+ * @param bool $wordsafe
+ * If TRUE, attempt to truncate on a word boundary. Word boundaries are
+ * spaces, punctuation, and Unicode characters used as word boundaries in
+ * non-Latin languages; see Unicode::PREG_CLASS_WORD_BOUNDARY for more
+ * information. If a word boundary cannot be found that would make the length
+ * of the returned string fall within length guidelines (see parameters
+ * $max_length and $min_wordsafe_length), word boundaries are ignored.
+ * @param bool $add_ellipsis
+ * If TRUE, add '...' to the end of the truncated string (defaults to
+ * FALSE). The string length will still fall within $max_length.
+ * @param bool $min_wordsafe_length
+ * If $wordsafe is TRUE, the minimum acceptable length for truncation (before
+ * adding an ellipsis, if $add_ellipsis is TRUE). Has no effect if $wordsafe
+ * is FALSE. This can be used to prevent having a very short resulting string
+ * that will not be understandable. For instance, if you are truncating the
+ * string "See myverylongurlexample.com for more information" to a word-safe
+ * return length of 20, the only available word boundary within 20 characters
+ * is after the word "See", which wouldn't leave a very informative string. If
+ * you had set $min_wordsafe_length to 10, though, the function would realise
+ * that "See" alone is too short, and would then just truncate ignoring word
+ * boundaries, giving you "See myverylongurl..." (assuming you had set
+ * $add_ellipses to TRUE).
+ *
+ * @return string
+ * The truncated string.
+ */
+ public static function truncate($string, $max_length, $wordsafe = FALSE, $add_ellipsis = FALSE, $min_wordsafe_length = 1) {
+ $ellipsis = '';
+ $max_length = max($max_length, 0);
+ $min_wordsafe_length = max($min_wordsafe_length, 0);
+
+ if (static::strlen($string) <= $max_length) {
+ // No truncation needed, so don't add ellipsis, just return.
+ return $string;
+ }
+
+ if ($add_ellipsis) {
+ // Truncate ellipsis in case $max_length is small.
+ $ellipsis = static::substr('…', 0, $max_length);
+ $max_length -= static::strlen($ellipsis);
+ $max_length = max($max_length, 0);
+ }
+
+ if ($max_length <= $min_wordsafe_length) {
+ // Do not attempt word-safe if lengths are bad.
+ $wordsafe = FALSE;
+ }
+
+ if ($wordsafe) {
+ $matches = array();
+ // Find the last word boundary, if there is one within $min_wordsafe_length
+ // to $max_length characters. preg_match() is always greedy, so it will
+ // find the longest string possible.
+ $found = preg_match('/^(.{' . $min_wordsafe_length . ',' . $max_length . '})[' . Unicode::PREG_CLASS_WORD_BOUNDARY . ']/u', $string, $matches);
+ if ($found) {
+ $string = $matches[1];
+ }
+ else {
+ $string = static::substr($string, 0, $max_length);
+ }
+ }
+ else {
+ $string = static::substr($string, 0, $max_length);
+ }
+
+ if ($add_ellipsis) {
+ // If we're adding an ellipsis, remove any trailing periods.
+ $string = rtrim($string, '.');
+
+ $string .= $ellipsis;
+ }
+
+ return $string;
+ }
+
+ /**
+ * Encodes MIME/HTTP headers that contain incorrectly encoded characters.
+ *
+ * For example, Unicode::mimeHeaderEncode('tést.txt') returns
+ * "=?UTF-8?B?dMOpc3QudHh0?=".
+ *
+ * See http://www.rfc-editor.org/rfc/rfc2047.txt for more information.
+ *
+ * Notes:
+ * - Only encode strings that contain non-ASCII characters.
+ * - We progressively cut-off a chunk with self::truncateBytes(). This ensures
+ * each chunk starts and ends on a character boundary.
+ * - Using \n as the chunk separator may cause problems on some systems and
+ * may have to be changed to \r\n or \r.
+ *
+ * @param string $string
+ * The header to encode.
+ *
+ * @return string
+ * The mime-encoded header.
+ */
+ public static function mimeHeaderEncode($string) {
+ if (preg_match('/[^\x20-\x7E]/', $string)) {
+ $chunk_size = 47; // floor((75 - strlen("=?UTF-8?B??=")) * 0.75);
+ $len = strlen($string);
+ $output = '';
+ while ($len > 0) {
+ $chunk = static::truncateBytes($string, $chunk_size);
+ $output .= ' =?UTF-8?B?' . base64_encode($chunk) . "?=\n";
+ $c = strlen($chunk);
+ $string = substr($string, $c);
+ $len -= $c;
+ }
+ return trim($output);
+ }
+ return $string;
+ }
+
+ /**
+ * Decodes MIME/HTTP encoded header values.
+ *
+ * @param string $header
+ * The header to decode.
+ *
+ * @return string
+ * The mime-decoded header.
+ */
+ public static function mimeHeaderDecode($header) {
+ $callback = function ($matches) {
+ $data = ($matches[2] == 'B') ? base64_decode($matches[3]) : str_replace('_', ' ', quoted_printable_decode($matches[3]));
+ if (strtolower($matches[1]) != 'utf-8') {
+ $data = static::convertToUtf8($data, $matches[1]);
+ }
+ return $data;
+ };
+ // First step: encoded chunks followed by other encoded chunks (need to collapse whitespace)
+ $header = preg_replace_callback('/=\?([^?]+)\?(Q|B)\?([^?]+|\?(?!=))\?=\s+(?==\?)/', $callback, $header);
+ // Second step: remaining chunks (do not collapse whitespace)
+ return preg_replace_callback('/=\?([^?]+)\?(Q|B)\?([^?]+|\?(?!=))\?=/', $callback, $header);
+ }
+
+ /**
+ * Flip U+C0-U+DE to U+E0-U+FD and back. Can be used as preg_replace callback.
+ *
+ * @param array $matches
+ * An array of matches by preg_replace_callback().
+ *
+ * @return string
+ * The flipped text.
+ */
+ public static function caseFlip($matches) {
+ return $matches[0][0] . chr(ord($matches[0][1]) ^ 32);
+ }
+
+}
diff --git a/core/modules/search/search.module b/core/modules/search/search.module
index 6dd68d952049..6501a854f99a 100644
--- a/core/modules/search/search.module
+++ b/core/modules/search/search.module
@@ -6,6 +6,7 @@
*/
use Drupal\Core\Entity\EntityInterface;
+use Drupal\Component\Utility\Unicode;
/**
* Matches all 'N' Unicode character classes (numbers)
@@ -447,7 +448,7 @@ function search_simplify($text, $langcode = NULL) {
// With the exception of the rules above, we consider all punctuation,
// marks, spacers, etc, to be a word boundary.
- $text = preg_replace('/[' . PREG_CLASS_UNICODE_WORD_BOUNDARY . ']+/u', ' ', $text);
+ $text = preg_replace('/[' . Unicode::PREG_CLASS_WORD_BOUNDARY . ']+/u', ' ', $text);
// Truncate everything to 50 characters.
$words = explode(' ', $text);
@@ -1102,7 +1103,7 @@ function search_data($keys, $module, $conditions = NULL) {
*/
function search_excerpt($keys, $text, $langcode = NULL) {
// We highlight around non-indexable or CJK characters.
- $boundary = '(?:(?<=[' . PREG_CLASS_UNICODE_WORD_BOUNDARY . PREG_CLASS_CJK . '])|(?=[' . PREG_CLASS_UNICODE_WORD_BOUNDARY . PREG_CLASS_CJK . ']))';
+ $boundary = '(?:(?<=[' . Unicode::PREG_CLASS_WORD_BOUNDARY . PREG_CLASS_CJK . '])|(?=[' . Unicode::PREG_CLASS_WORD_BOUNDARY . PREG_CLASS_CJK . ']))';
// Extract positive keywords and phrases
preg_match_all('/ ("([^"]+)"|(?!OR)([^" ]+))/', ' ' . $keys, $matches);
diff --git a/core/modules/system/lib/Drupal/system/Tests/System/UnicodeUnitTest.php b/core/modules/system/lib/Drupal/system/Tests/System/UnicodeUnitTest.php
deleted file mode 100644
index 58bef1032904..000000000000
--- a/core/modules/system/lib/Drupal/system/Tests/System/UnicodeUnitTest.php
+++ /dev/null
@@ -1,312 +0,0 @@
-<?php
-
-/**
- * @file
- * Definition of Drupal\system\Tests\System\UnicodeUnitTest.
- */
-
-namespace Drupal\system\Tests\System;
-
-use Drupal\simpletest\UnitTestBase;
-
-/**
- * Test unicode handling features implemented in unicode.inc.
- */
-class UnicodeUnitTest extends UnitTestBase {
-
- /**
- * Whether to run the extended version of the tests (including non latin1 characters).
- *
- * @var boolean
- */
- protected $extendedMode = FALSE;
-
- public static function getInfo() {
- return array(
- 'name' => 'Unicode handling',
- 'description' => 'Tests Drupal Unicode handling.',
- 'group' => 'System',
- );
- }
-
- /**
- * Test full unicode features implemented using the mbstring extension.
- */
- function testMbStringUnicode() {
- global $multibyte;
-
- // mbstring was not detected on this installation, there is no way to test
- // multibyte features. Treat that as an exception.
- if ($multibyte == UNICODE_SINGLEBYTE) {
- $this->error(t('Unable to test Multibyte features: mbstring extension was not detected.'));
- }
-
- $multibyte = UNICODE_MULTIBYTE;
-
- $this->extendedMode = TRUE;
- $this->pass(t('Testing in mbstring mode'));
-
- $this->helperTestStrToLower();
- $this->helperTestStrToUpper();
- $this->helperTestUcFirst();
- $this->helperTestStrLen();
- $this->helperTestSubStr();
- $this->helperTestTruncate();
- }
-
- /**
- * Test emulated unicode features.
- */
- function testEmulatedUnicode() {
- global $multibyte;
-
- $multibyte = UNICODE_SINGLEBYTE;
-
- $this->extendedMode = FALSE;
-
- $this->pass(t('Testing in emulated (best-effort) mode'));
-
- $this->helperTestStrToLower();
- $this->helperTestStrToUpper();
- $this->helperTestUcFirst();
- $this->helperTestStrLen();
- $this->helperTestSubStr();
- $this->helperTestTruncate();
- }
-
- function helperTestStrToLower() {
- $testcase = array(
- 'tHe QUIcK bRoWn' => 'the quick brown',
- 'FrançAIS is ÜBER-åwesome' => 'français is über-åwesome',
- );
- if ($this->extendedMode) {
- $testcase['ΑΒΓΔΕΖΗΘΙΚΛΜÎΞΟΣὨ'] = 'αβγδεζηθικλμνξοσὠ';
- }
-
- foreach ($testcase as $input => $output) {
- $this->assertEqual(drupal_strtolower($input), $output, format_string('%input is lowercased as %output', array('%input' => $input, '%output' => $output)));
- }
- }
-
- function helperTestStrToUpper() {
- $testcase = array(
- 'tHe QUIcK bRoWn' => 'THE QUICK BROWN',
- 'FrançAIS is ÜBER-åwesome' => 'FRANÇAIS IS ÜBER-ÅWESOME',
- );
- if ($this->extendedMode) {
- $testcase['αβγδεζηθικλμνξοσὠ'] = 'ΑΒΓΔΕΖΗΘΙΚΛΜÎΞΟΣὨ';
- }
-
- foreach ($testcase as $input => $output) {
- $this->assertEqual(drupal_strtoupper($input), $output, format_string('%input is uppercased as %output', array('%input' => $input, '%output' => $output)));
- }
- }
-
- function helperTestUcFirst() {
- $testcase = array(
- 'tHe QUIcK bRoWn' => 'THe QUIcK bRoWn',
- 'françAIS' => 'FrançAIS',
- 'über' => 'Über',
- 'Ã¥wesome' => 'Ã…wesome'
- );
- if ($this->extendedMode) {
- $testcase['σion'] = 'Σion';
- }
-
- foreach ($testcase as $input => $output) {
- $this->assertEqual(drupal_ucfirst($input), $output, format_string('%input is ucfirst-ed as %output', array('%input' => $input, '%output' => $output)));
- }
- }
-
- function helperTestStrLen() {
- $testcase = array(
- 'tHe QUIcK bRoWn' => 15,
- 'ÃœBER-Ã¥wesome' => 12,
- );
-
- foreach ($testcase as $input => $output) {
- $this->assertEqual(drupal_strlen($input), $output, format_string('%input length is %output', array('%input' => $input, '%output' => $output)));
- }
- }
-
- function helperTestSubStr() {
- $testcase = array(
- // 012345678901234567890123
- array('frà nçAIS is über-åwesome', 0, 0,
- ''),
- array('frà nçAIS is über-åwesome', 0, 1,
- 'f'),
- array('frà nçAIS is über-åwesome', 0, 8,
- 'frà nçAIS'),
- array('frà nçAIS is über-åwesome', 0, 23,
- 'frà nçAIS is über-åwesom'),
- array('frà nçAIS is über-åwesome', 0, 24,
- 'frà nçAIS is über-åwesome'),
- array('frà nçAIS is über-åwesome', 0, 25,
- 'frà nçAIS is über-åwesome'),
- array('frà nçAIS is über-åwesome', 0, 100,
- 'frà nçAIS is über-åwesome'),
- array('frà nçAIS is über-åwesome', 4, 4,
- 'çAIS'),
- array('frà nçAIS is über-åwesome', 1, 0,
- ''),
- array('frà nçAIS is über-åwesome', 100, 0,
- ''),
- array('frà nçAIS is über-åwesome', -4, 2,
- 'so'),
- array('frà nçAIS is über-åwesome', -4, 3,
- 'som'),
- array('frà nçAIS is über-åwesome', -4, 4,
- 'some'),
- array('frà nçAIS is über-åwesome', -4, 5,
- 'some'),
- array('frà nçAIS is über-åwesome', -7, 10,
- 'Ã¥wesome'),
- array('frà nçAIS is über-åwesome', 5, -10,
- 'AIS is üb'),
- array('frà nçAIS is über-åwesome', 0, -10,
- 'frà nçAIS is üb'),
- array('frà nçAIS is über-åwesome', 0, -1,
- 'frà nçAIS is über-åwesom'),
- array('frà nçAIS is über-åwesome', -7, -2,
- 'Ã¥weso'),
- array('frà nçAIS is über-åwesome', -7, -6,
- 'Ã¥'),
- array('frà nçAIS is über-åwesome', -7, -7,
- ''),
- array('frà nçAIS is über-åwesome', -7, -8,
- ''),
- array('...', 0, 2, '..'),
- array('以呂波耳・ã»ã¸ã¨ã¡ã€‚リヌルヲ。', 1, 3,
- '呂波耳'),
-
- );
-
- foreach ($testcase as $test) {
- list($input, $start, $length, $output) = $test;
- $result = drupal_substr($input, $start, $length);
- $this->assertEqual($result, $output, format_string('%input substring at offset %offset for %length characters is %output (got %result)', array('%input' => $input, '%offset' => $start, '%length' => $length, '%output' => $output, '%result' => $result)));
- }
- }
-
- /**
- * Test decode_entities().
- */
- function testDecodeEntities() {
- $testcase = array(
- 'Drupal' => 'Drupal',
- '<script>' => '<script>',
- '<script>' => '<script>',
- '<script>' => '<script>',
- '&lt;script&gt;' => '<script>',
- '"' => '"',
- '"' => '"',
- '&#34;' => '"',
- '"' => '"',
- '&quot;' => '"',
- "'" => "'",
- ''' => "'",
- '&#39;' => ''',
- '©' => '©',
- '©' => '©',
- '©' => '©',
- '→' => '→',
- '→' => '→',
- 'âž¼' => 'âž¼',
- '➼' => 'âž¼',
- '€' => '€',
- );
- foreach ($testcase as $input => $output) {
- $this->assertEqual(decode_entities($input), $output, format_string('Make sure the decoded entity of @input is @output', array('@input' => $input, '@output' => $output)));
- }
- }
-
- /**
- * Tests truncate_utf8().
- */
- function helperTestTruncate() {
- // Each case is an array with input string, length to truncate to, and
- // expected return value.
-
- // Test non-wordsafe, non-ellipsis cases.
- $non_wordsafe_non_ellipsis_cases = array(
- array('frà nçAIS is über-åwesome', 24, 'frà nçAIS is über-åwesome'),
- array('frà nçAIS is über-åwesome', 23, 'frà nçAIS is über-åwesom'),
- array('frà nçAIS is über-åwesome', 17, 'frà nçAIS is über-'),
- array('以呂波耳・ã»ã¸ã¨ã¡ã€‚リヌルヲ。', 6, '以呂波耳・ã»'),
- );
- $this->runTruncateTests($non_wordsafe_non_ellipsis_cases, FALSE, FALSE);
-
- // Test non-wordsafe, ellipsis cases.
- $non_wordsafe_ellipsis_cases = array(
- array('frà nçAIS is über-åwesome', 24, 'frà nçAIS is über-åwesome'),
- array('frà nçAIS is über-åwesome', 23, 'frà nçAIS is über-åweso…'),
- array('frà nçAIS is über-åwesome', 17, 'frà nçAIS is über…'),
- );
- $this->runTruncateTests($non_wordsafe_ellipsis_cases, FALSE, TRUE);
-
- // Test wordsafe, ellipsis cases.
- $wordsafe_ellipsis_cases = array(
- array('123', 1, '…'),
- array('123', 2, '1…'),
- array('123', 3, '123'),
- array('1234', 3, '12…'),
- array('1234567890', 10, '1234567890'),
- array('12345678901', 10, '123456789…'),
- array('12345678901', 11, '12345678901'),
- array('123456789012', 11, '1234567890…'),
- array('12345 7890', 10, '12345 7890'),
- array('12345 7890', 9, '12345…'),
- array('123 567 90', 10, '123 567 90'),
- array('123 567 901', 10, '123 567…'),
- array('Stop. Hammertime.', 17, 'Stop. Hammertime.'),
- array('Stop. Hammertime.', 16, 'Stop…'),
- array('frà nçAIS is über-åwesome', 24, 'frà nçAIS is über-åwesome'),
- array('frà nçAIS is über-åwesome', 23, 'frà nçAIS is über…'),
- array('frà nçAIS is über-åwesome', 17, 'frà nçAIS is über…'),
- array('¿Dónde está el niño?', 20, '¿Dónde está el niño?'),
- array('¿Dónde está el niño?', 19, '¿Dónde está el…'),
- array('¿Dónde está el niño?', 13, '¿Dónde está…'),
- array('¿Dónde está el niño?', 10, '¿Dónde…'),
- array('Help! Help! Help!', 17, 'Help! Help! Help!'),
- array('Help! Help! Help!', 16, 'Help! Help!…'),
- array('Help! Help! Help!', 15, 'Help! Help!…'),
- array('Help! Help! Help!', 14, 'Help! Help!…'),
- array('Help! Help! Help!', 13, 'Help! Help!…'),
- array('Help! Help! Help!', 12, 'Help! Help!…'),
- array('Help! Help! Help!', 11, 'Help! Help…'),
- array('Help! Help! Help!', 10, 'Help!…'),
- array('Help! Help! Help!', 9, 'Help!…'),
- array('Help! Help! Help!', 8, 'Help!…'),
- array('Help! Help! Help!', 7, 'Help!…'),
- array('Help! Help! Help!', 6, 'Help!…'),
- array('Help! Help! Help!', 5, 'Help…'),
- array('Help! Help! Help!', 4, 'Hel…'),
- array('Help! Help! Help!', 3, 'He…'),
- array('Help! Help! Help!', 2, 'H…'),
- );
- $this->runTruncateTests($wordsafe_ellipsis_cases, TRUE, TRUE);
- }
-
- /**
- * Runs test cases for helperTestTruncate().
- *
- * Runs each test case through truncate_utf8() and compares the output
- * to the expected output.
- *
- * @param $cases
- * Cases array. Each case is an array with the input string, length to
- * truncate to, and expected output.
- * @param $wordsafe
- * TRUE to use word-safe truncation, FALSE to not use word-safe truncation.
- * @param $ellipsis
- * TRUE to append ... if the input is truncated, FALSE to not append ....
- */
- function runTruncateTests($cases, $wordsafe, $ellipsis) {
- foreach ($cases as $case) {
- list($input, $max_length, $expected) = $case;
- $output = truncate_utf8($input, $max_length, $wordsafe, $ellipsis);
- $this->assertEqual($output, $expected, format_string('%input truncate to %length characters with %wordsafe, %ellipsis is %expected (got %output)', array('%input' => $input, '%length' => $max_length, '%output' => $output, '%expected' => $expected, '%wordsafe' => ($wordsafe ? 'word-safe' : 'not word-safe'), '%ellipsis' => ($ellipsis ? 'ellipsis' : 'not ellipsis'))));
- }
- }
-}
diff --git a/core/modules/views/lib/Drupal/views/Plugin/views/HandlerBase.php b/core/modules/views/lib/Drupal/views/Plugin/views/HandlerBase.php
index 71fc789a8268..3f510aa8ce28 100644
--- a/core/modules/views/lib/Drupal/views/Plugin/views/HandlerBase.php
+++ b/core/modules/views/lib/Drupal/views/Plugin/views/HandlerBase.php
@@ -7,6 +7,7 @@
namespace Drupal\views\Plugin\views;
+use Drupal\Component\Utility\Unicode;
use Drupal\views\Plugin\views\display\DisplayPluginBase;
use Drupal\views\Plugin\views\PluginBase;
use Drupal\views\ViewExecutable;
@@ -242,8 +243,6 @@ public function sanitizeValue($value, $type = NULL) {
* The transformed string.
*/
protected function caseTransform($string, $option) {
- global $multibyte;
-
switch ($option) {
default:
return $string;
@@ -254,7 +253,7 @@ protected function caseTransform($string, $option) {
case 'ucfirst':
return drupal_strtoupper(drupal_substr($string, 0, 1)) . drupal_substr($string, 1);
case 'ucwords':
- if ($multibyte == UNICODE_MULTIBYTE) {
+ if (Unicode::getStatus() == Unicode::STATUS_MULTIBYTE) {
return mb_convert_case($string, MB_CASE_TITLE);
}
else {
diff --git a/core/tests/Drupal/Tests/Component/Utility/StringTest.php b/core/tests/Drupal/Tests/Component/Utility/StringTest.php
index c1a75292e4e9..10e3af7e200b 100644
--- a/core/tests/Drupal/Tests/Component/Utility/StringTest.php
+++ b/core/tests/Drupal/Tests/Component/Utility/StringTest.php
@@ -41,7 +41,7 @@ public static function getInfo() {
*/
function testCheckPlain($text, $expected, $message, $ignorewarnings = FALSE) {
$result = $ignorewarnings ? @String::checkPlain($text) : String::checkPlain($text);
- $this->assertEquals($result, $expected, $message);
+ $this->assertEquals($expected, $result, $message);
}
/**
@@ -80,7 +80,7 @@ function providerCheckPlain() {
*/
function testFormat($string, $args, $expected, $message) {
$result = String::format($string, $args);
- $this->assertEquals($result, $expected, $message);
+ $this->assertEquals($expected, $result, $message);
}
/**
@@ -106,4 +106,44 @@ function testPlaceholder() {
$this->assertEquals('<em class="placeholder">Some text</em>', String::placeholder('Some text'));
}
+ /**
+ * Tests String::decodeEntities().
+ *
+ * @dataProvider providerDecodeEntities
+ */
+ public function testDecodeEntities($text, $expected) {
+ $this->assertEquals($expected, String::decodeEntities($text));
+ }
+
+ /**
+ * Data provider for testDecodeEntities().
+ *
+ * @see testCheckPlain()
+ */
+ public function providerDecodeEntities() {
+ return array(
+ array('Drupal', 'Drupal'),
+ array('<script>', '<script>'),
+ array('<script>', '<script>'),
+ array('<script>', '<script>'),
+ array('&lt;script&gt;', '<script>'),
+ array('"', '"'),
+ array('"', '"'),
+ array('&#34;', '"'),
+ array('"', '"'),
+ array('&quot;', '"'),
+ array("'", "'"),
+ array(''', "'"),
+ array('&#39;', '''),
+ array('©', '©'),
+ array('©', '©'),
+ array('©', '©'),
+ array('→', '→'),
+ array('→', '→'),
+ array('âž¼', 'âž¼'),
+ array('➼', 'âž¼'),
+ array('€', '€'),
+ );
+ }
+
}
diff --git a/core/tests/Drupal/Tests/Component/Utility/UnicodeTest.php b/core/tests/Drupal/Tests/Component/Utility/UnicodeTest.php
new file mode 100644
index 000000000000..5f49a6d3c9b8
--- /dev/null
+++ b/core/tests/Drupal/Tests/Component/Utility/UnicodeTest.php
@@ -0,0 +1,336 @@
+<?php
+
+/**
+ * @file
+ * Contains \Drupal\Tests\Component\Utility\UnicodeTest.
+ */
+
+namespace Drupal\Tests\Component\Utility;
+
+use Drupal\Tests\UnitTestCase;
+use Drupal\Component\Utility\Unicode;
+
+/**
+ * Test unicode handling features implemented in Unicode component.
+ */
+class UnicodeTest extends UnitTestCase {
+
+ public static function getInfo() {
+ return array(
+ 'name' => 'Unicode handling',
+ 'description' => 'Tests Drupal Unicode handling.',
+ 'group' => 'System',
+ );
+ }
+
+ public function setUp() {
+ // Initialize unicode component.
+ Unicode::check();
+ }
+
+ /**
+ * Tests Unicode::getStatus() and Unicode::setStatus().
+ *
+ * @dataProvider providerTestStatus
+ */
+ public function testStatus($value, $expected, $invalid = FALSE) {
+ if ($invalid) {
+ $this->setExpectedException('InvalidArgumentException');
+ }
+ Unicode::setStatus($value);
+ $this->assertEquals($expected, Unicode::getStatus());
+ }
+
+ /**
+ * Data provider for testStatus().
+ *
+ * @see testStatus()
+ *
+ * @return array
+ * An array containing:
+ * - The status value to set.
+ * - The status value to expect after setting the new value.
+ * - (optional) Boolean indicating invalid status. Defaults to FALSE.
+ */
+ public function providerTestStatus() {
+ return array(
+ array(Unicode::STATUS_SINGLEBYTE, Unicode::STATUS_SINGLEBYTE),
+ array(rand(10, 100), Unicode::STATUS_SINGLEBYTE, TRUE),
+ array(rand(10, 100), Unicode::STATUS_SINGLEBYTE, TRUE),
+ array(Unicode::STATUS_MULTIBYTE, Unicode::STATUS_MULTIBYTE),
+ array(rand(10, 100), Unicode::STATUS_MULTIBYTE, TRUE),
+ array(Unicode::STATUS_ERROR, Unicode::STATUS_ERROR),
+ array(Unicode::STATUS_MULTIBYTE, Unicode::STATUS_MULTIBYTE),
+ );
+ }
+
+ /**
+ * Tests Unicode::mimeHeaderEncode() and Unicode::mimeHeaderDecode().
+ *
+ * @dataProvider providerTestMimeHeader
+ */
+ public function testMimeHeader($value, $encoded) {
+ $this->assertEquals($encoded, Unicode::mimeHeaderEncode($value));
+ $this->assertEquals($value, Unicode::mimeHeaderDecode($encoded));
+ }
+
+ /**
+ * Data provider for testMimeHeader().
+ *
+ * @see testMimeHeader()
+ *
+ * @return array
+ * An array containing a string and its encoded value.
+ */
+ public function providerTestMimeHeader() {
+ return array(
+ array('tést.txt', '=?UTF-8?B?dMOpc3QudHh0?='),
+ );
+ }
+
+
+ /**
+ * Tests Unicode::strtolower().
+ *
+ * @dataProvider providerStrtolower
+ */
+ public function testStrtolower($text, $expected, $multibyte = FALSE) {
+ $status = $multibyte ? Unicode::STATUS_MULTIBYTE : Unicode::STATUS_SINGLEBYTE;
+ Unicode::setStatus($status);
+ $this->assertEquals($expected, Unicode::strtolower($text));
+ }
+
+ /**
+ * Data provider for testStrtolower().
+ *
+ * @see testStrtolower()
+ *
+ * @return array
+ * An array containing a string, its lowercase version and whether it should
+ * be processed as multibyte.
+ */
+ public function providerStrtolower() {
+ $cases = array(
+ array('tHe QUIcK bRoWn', 'the quick brown'),
+ array('FrançAIS is ÜBER-åwesome', 'français is über-åwesome'),
+ );
+ foreach ($cases as $case) {
+ // Test the same string both in multibyte and singlebyte conditions.
+ array_push($case, TRUE);
+ $cases[] = $case;
+ }
+ // Add a multibyte string.
+ $cases[] = array('ΑΒΓΔΕΖΗΘΙΚΛΜÎΞΟΣὨ', 'αβγδεζηθικλμνξοσὠ', TRUE);
+ return $cases;
+ }
+
+ /**
+ * Tests Unicode::strtoupper().
+ *
+ * @dataProvider providerStrtoupper
+ */
+ public function testStrtoupper($text, $expected, $multibyte = FALSE) {
+ $status = $multibyte ? Unicode::STATUS_MULTIBYTE : Unicode::STATUS_SINGLEBYTE;
+ Unicode::setStatus($status);
+ $this->assertEquals($expected, Unicode::strtoupper($text));
+ }
+
+ /**
+ * Data provider for testStrtoupper().
+ *
+ * @see testStrtoupper()
+ *
+ * @return array
+ * An array containing a string, its uppercase version and whether it should
+ * be processed as multibyte.
+ */
+ public function providerStrtoupper() {
+ $cases = array(
+ array('tHe QUIcK bRoWn', 'THE QUICK BROWN'),
+ array('FrançAIS is ÜBER-åwesome', 'FRANÇAIS IS ÜBER-ÅWESOME'),
+ );
+ foreach ($cases as $case) {
+ // Test the same string both in multibyte and singlebyte conditions.
+ array_push($case, TRUE);
+ $cases[] = $case;
+ }
+ // Add a multibyte string.
+ $cases[] = array('αβγδεζηθικλμνξοσὠ', 'ΑΒΓΔΕΖΗΘΙΚΛΜÎΞΟΣὨ', TRUE);
+ return $cases;
+ }
+
+ /**
+ * Tests Unicode::ucfirst().
+ *
+ * @dataProvider providerUcfirst
+ */
+ public function testUcfirst($text, $expected) {
+ $this->assertEquals($expected, Unicode::ucfirst($text));
+ }
+
+ /**
+ * Data provider for testUcfirst().
+ *
+ * @see testUcfirst()
+ *
+ * @return array
+ * An array containing a string and its uppercase first version.
+ */
+ public function providerUcfirst() {
+ return array(
+ array('tHe QUIcK bRoWn', 'THe QUIcK bRoWn'),
+ array('françAIS', 'FrançAIS'),
+ array('über', 'Über'),
+ array('Ã¥wesome', 'Ã…wesome'),
+ // A multibyte string.
+ array('σion', 'Σion'),
+ );
+ }
+
+ /**
+ * Tests Unicode::strlen().
+ *
+ * @dataProvider providerStrlen
+ */
+ public function testStrlen($text, $expected) {
+ $this->assertEquals($expected, Unicode::strlen($text));
+ }
+
+ /**
+ * Data provider for testStrlen().
+ *
+ * @see testStrlen()
+ *
+ * @return array
+ * An array containing a string and its length.
+ */
+ public function providerStrlen() {
+ return array(
+ array('tHe QUIcK bRoWn', 15),
+ array('ÃœBER-Ã¥wesome', 12),
+ );
+ }
+
+ /**
+ * Tests Unicode::substr().
+ *
+ * @dataProvider providerSubstr
+ */
+ public function testSubstr($text, $start, $length, $expected) {
+ $this->assertEquals($expected, Unicode::substr($text, $start, $length));
+ }
+
+ /**
+ * Data provider for testSubstr().
+ *
+ * @see testSubstr()
+ *
+ * @return array
+ * An array containing:
+ * - The string to test.
+ * - The start number to be processed by substr.
+ * - The length number to be processed by substr.
+ * - The expected string result.
+ */
+ public function providerSubstr() {
+ return array(
+ array('frà nçAIS is über-åwesome', 0, 0, ''),
+ array('frà nçAIS is über-åwesome', 0, 1, 'f'),
+ array('frà nçAIS is über-åwesome', 0, 8, 'frà nçAIS'),
+ array('frà nçAIS is über-åwesome', 0, 23, 'frà nçAIS is über-åwesom'),
+ array('frà nçAIS is über-åwesome', 0, 24, 'frà nçAIS is über-åwesome'),
+ array('frà nçAIS is über-åwesome', 0, 25, 'frà nçAIS is über-åwesome'),
+ array('frà nçAIS is über-åwesome', 0, 100, 'frà nçAIS is über-åwesome'),
+ array('frà nçAIS is über-åwesome', 4, 4, 'çAIS'),
+ array('frà nçAIS is über-åwesome', 1, 0, ''),
+ array('frà nçAIS is über-åwesome', 100, 0, ''),
+ array('frà nçAIS is über-åwesome', -4, 2, 'so'),
+ array('frà nçAIS is über-åwesome', -4, 3, 'som'),
+ array('frà nçAIS is über-åwesome', -4, 4, 'some'),
+ array('frà nçAIS is über-åwesome', -4, 5, 'some'),
+ array('frà nçAIS is über-åwesome', -7, 10, 'åwesome'),
+ array('frà nçAIS is über-åwesome', 5, -10, 'AIS is üb'),
+ array('frà nçAIS is über-åwesome', 0, -10, 'frà nçAIS is üb'),
+ array('frà nçAIS is über-åwesome', 0, -1, 'frà nçAIS is über-åwesom'),
+ array('frà nçAIS is über-åwesome', -7, -2, 'åweso'),
+ array('frà nçAIS is über-åwesome', -7, -6, 'å'),
+ array('frà nçAIS is über-åwesome', -7, -7, ''),
+ array('frà nçAIS is über-åwesome', -7, -8, ''),
+ array('...', 0, 2, '..'),
+ array('以呂波耳・ã»ã¸ã¨ã¡ã€‚リヌルヲ。', 1, 3, '呂波耳'),
+ );
+ }
+
+ /**
+ * Tests Unicode::truncate().
+ *
+ * @dataProvider providerTruncate
+ */
+ public function testTruncate($text, $max_length, $expected, $wordsafe = FALSE, $add_ellipsis = FALSE) {
+ Unicode::check();
+ $this->assertEquals($expected, Unicode::truncate($text, $max_length, $wordsafe, $add_ellipsis));
+ }
+
+ /**
+ * Data provider for testTruncate().
+ *
+ * @see testTruncate()
+ *
+ * @return array
+ * An array containing:
+ * - The string to test.
+ * - The max length to truncate this string to.
+ * - The expected string result.
+ * - (optional) Boolean for the $wordsafe flag. Defaults to FALSE.
+ * - (optional) Boolean for the $add_ellipsis flag. Defaults to FALSE.
+ */
+ public function providerTruncate() {
+ return array(
+ array('frà nçAIS is über-åwesome', 24, 'frà nçAIS is über-åwesome'),
+ array('frà nçAIS is über-åwesome', 23, 'frà nçAIS is über-åwesom'),
+ array('frà nçAIS is über-åwesome', 17, 'frà nçAIS is über-'),
+ array('以呂波耳・ã»ã¸ã¨ã¡ã€‚リヌルヲ。', 6, '以呂波耳・ã»'),
+ array('frà nçAIS is über-åwesome', 24, 'frà nçAIS is über-åwesome', FALSE, TRUE),
+ array('frà nçAIS is über-åwesome', 23, 'frà nçAIS is über-åweso…', FALSE, TRUE),
+ array('frà nçAIS is über-åwesome', 17, 'frà nçAIS is über…', FALSE, TRUE),
+ array('123', 1, '…', TRUE, TRUE),
+ array('123', 2, '1…', TRUE, TRUE),
+ array('123', 3, '123', TRUE, TRUE),
+ array('1234', 3, '12…', TRUE, TRUE),
+ array('1234567890', 10, '1234567890', TRUE, TRUE),
+ array('12345678901', 10, '123456789…', TRUE, TRUE),
+ array('12345678901', 11, '12345678901', TRUE, TRUE),
+ array('123456789012', 11, '1234567890…', TRUE, TRUE),
+ array('12345 7890', 10, '12345 7890', TRUE, TRUE),
+ array('12345 7890', 9, '12345…', TRUE, TRUE),
+ array('123 567 90', 10, '123 567 90', TRUE, TRUE),
+ array('123 567 901', 10, '123 567…', TRUE, TRUE),
+ array('Stop. Hammertime.', 17, 'Stop. Hammertime.', TRUE, TRUE),
+ array('Stop. Hammertime.', 16, 'Stop…', TRUE, TRUE),
+ array('frà nçAIS is über-åwesome', 24, 'frà nçAIS is über-åwesome', TRUE, TRUE),
+ array('frà nçAIS is über-åwesome', 23, 'frà nçAIS is über…', TRUE, TRUE),
+ array('frà nçAIS is über-åwesome', 17, 'frà nçAIS is über…', TRUE, TRUE),
+ array('¿Dónde está el niño?', 20, '¿Dónde está el niño?', TRUE, TRUE),
+ array('¿Dónde está el niño?', 19, '¿Dónde está el…', TRUE, TRUE),
+ array('¿Dónde está el niño?', 13, '¿Dónde está…', TRUE, TRUE),
+ array('¿Dónde está el niño?', 10, '¿Dónde…', TRUE, TRUE),
+ array('Help! Help! Help!', 17, 'Help! Help! Help!', TRUE, TRUE),
+ array('Help! Help! Help!', 16, 'Help! Help!…', TRUE, TRUE),
+ array('Help! Help! Help!', 15, 'Help! Help!…', TRUE, TRUE),
+ array('Help! Help! Help!', 14, 'Help! Help!…', TRUE, TRUE),
+ array('Help! Help! Help!', 13, 'Help! Help!…', TRUE, TRUE),
+ array('Help! Help! Help!', 12, 'Help! Help!…', TRUE, TRUE),
+ array('Help! Help! Help!', 11, 'Help! Help…', TRUE, TRUE),
+ array('Help! Help! Help!', 10, 'Help!…', TRUE, TRUE),
+ array('Help! Help! Help!', 9, 'Help!…', TRUE, TRUE),
+ array('Help! Help! Help!', 8, 'Help!…', TRUE, TRUE),
+ array('Help! Help! Help!', 7, 'Help!…', TRUE, TRUE),
+ array('Help! Help! Help!', 6, 'Help!…', TRUE, TRUE),
+ array('Help! Help! Help!', 5, 'Help…', TRUE, TRUE),
+ array('Help! Help! Help!', 4, 'Hel…', TRUE, TRUE),
+ array('Help! Help! Help!', 3, 'He…', TRUE, TRUE),
+ array('Help! Help! Help!', 2, 'H…', TRUE, TRUE),
+ );
+ }
+
+}
diff --git a/core/tests/bootstrap.php b/core/tests/bootstrap.php
index 57e3da621c61..08d887166d93 100644
--- a/core/tests/bootstrap.php
+++ b/core/tests/bootstrap.php
@@ -20,3 +20,8 @@
require __DIR__ . "/../../core/lib/Drupal.php";
// Look into removing this later.
define('REQUEST_TIME', (int) $_SERVER['REQUEST_TIME']);
+
+// Set sane locale settings, to ensure consistent string, dates, times and
+// numbers handling.
+// @see drupal_environment_initialize()
+setlocale(LC_ALL, 'C');
--
GitLab