annotate vendor/psy/psysh/src/Psy/Util/Str.php @ 7:848c88cfe644

More layout
author Chris Cannam
date Fri, 05 Jan 2018 13:59:44 +0000
parents 4c8ae668cc8c
children
rev   line source
Chris@0 1 <?php
Chris@0 2
Chris@0 3 /*
Chris@0 4 * This file is part of Psy Shell.
Chris@0 5 *
Chris@0 6 * (c) 2012-2017 Justin Hileman
Chris@0 7 *
Chris@0 8 * For the full copyright and license information, please view the LICENSE
Chris@0 9 * file that was distributed with this source code.
Chris@0 10 */
Chris@0 11
Chris@0 12 namespace Psy\Util;
Chris@0 13
Chris@0 14 /**
Chris@0 15 * String utility methods.
Chris@0 16 *
Chris@0 17 * @author ju1ius
Chris@0 18 */
Chris@0 19 class Str
Chris@0 20 {
Chris@0 21 const UNVIS_RX = <<<'EOS'
Chris@0 22 /
Chris@0 23 \\(?:
Chris@0 24 ((?:040)|s)
Chris@0 25 | (240)
Chris@0 26 | (?: M-(.) )
Chris@0 27 | (?: M\^(.) )
Chris@0 28 | (?: \^(.) )
Chris@0 29 )
Chris@0 30 /xS
Chris@0 31 EOS;
Chris@0 32
Chris@0 33 /**
Chris@0 34 * Decodes a string encoded by libsd's strvis.
Chris@0 35 *
Chris@0 36 * From `man 3 vis`:
Chris@0 37 *
Chris@0 38 * Use an ‘M’ to represent meta characters (characters with the 8th bit set),
Chris@0 39 * and use a caret ‘^’ to represent control characters (see iscntrl(3)).
Chris@0 40 * The following formats are used:
Chris@0 41 *
Chris@0 42 * \040 Represents ASCII space.
Chris@0 43 *
Chris@0 44 * \240 Represents Meta-space (&nbsp in HTML).
Chris@0 45 *
Chris@0 46 * \M-C Represents character ‘C’ with the 8th bit set.
Chris@0 47 * Spans characters ‘\241’ through ‘\376’.
Chris@0 48 *
Chris@0 49 * \M^C Represents control character ‘C’ with the 8th bit set.
Chris@0 50 * Spans characters ‘\200’ through ‘\237’, and ‘\377’ (as ‘\M^?’).
Chris@0 51 *
Chris@0 52 * \^C Represents the control character ‘C’.
Chris@0 53 * Spans characters ‘\000’ through ‘\037’, and ‘\177’ (as ‘\^?’).
Chris@0 54 *
Chris@0 55 * The other formats are supported by PHP's stripcslashes,
Chris@0 56 * except for the \s sequence (ASCII space).
Chris@0 57 *
Chris@0 58 * @param string $input The string to decode
Chris@0 59 *
Chris@0 60 * @return string
Chris@0 61 */
Chris@0 62 public static function unvis($input)
Chris@0 63 {
Chris@0 64 $output = preg_replace_callback(self::UNVIS_RX, 'self::unvisReplace', $input);
Chris@0 65 // other escapes & octal are handled by stripcslashes
Chris@0 66 return stripcslashes($output);
Chris@0 67 }
Chris@0 68
Chris@0 69 /**
Chris@0 70 * Callback for Str::unvis.
Chris@0 71 *
Chris@0 72 * @param array $match The matches passed by preg_replace_callback
Chris@0 73 *
Chris@0 74 * @return string
Chris@0 75 */
Chris@0 76 protected static function unvisReplace($match)
Chris@0 77 {
Chris@0 78 // \040, \s
Chris@0 79 if (!empty($match[1])) {
Chris@0 80 return "\x20";
Chris@0 81 }
Chris@0 82 // \240
Chris@0 83 if (!empty($match[2])) {
Chris@0 84 return "\xa0";
Chris@0 85 }
Chris@0 86 // \M-(.)
Chris@0 87 if (isset($match[3]) && $match[3] !== '') {
Chris@0 88 $chr = $match[3];
Chris@0 89 // unvis S_META1
Chris@0 90 $cp = 0200;
Chris@0 91 $cp |= ord($chr);
Chris@0 92
Chris@0 93 return chr($cp);
Chris@0 94 }
Chris@0 95 // \M^(.)
Chris@0 96 if (isset($match[4]) && $match[4] !== '') {
Chris@0 97 $chr = $match[4];
Chris@0 98 // unvis S_META | S_CTRL
Chris@0 99 $cp = 0200;
Chris@0 100 $cp |= ($chr === '?') ? 0177 : ord($chr) & 037;
Chris@0 101
Chris@0 102 return chr($cp);
Chris@0 103 }
Chris@0 104 // \^(.)
Chris@0 105 if (isset($match[5]) && $match[5] !== '') {
Chris@0 106 $chr = $match[5];
Chris@0 107 // unvis S_CTRL
Chris@0 108 $cp = 0;
Chris@0 109 $cp |= ($chr === '?') ? 0177 : ord($chr) & 037;
Chris@0 110
Chris@0 111 return chr($cp);
Chris@0 112 }
Chris@0 113 }
Chris@0 114 }