/system/helpers/text_helper.php
PHP | 534 lines | 321 code | 60 blank | 153 comment | 42 complexity | e47aea772e4169212793b4ff5f49f668 MD5 | raw file
- <?php if ( ! defined('BASEPATH')) exit('No direct script access allowed');
- /**
- * CodeIgniter
- *
- * An open source application development framework for PHP 5.2.4 or newer
- *
- * NOTICE OF LICENSE
- *
- * Licensed under the Open Software License version 3.0
- *
- * This source file is subject to the Open Software License (OSL 3.0) that is
- * bundled with this package in the files license.txt / license.rst. It is
- * also available through the world wide web at this URL:
- * http://opensource.org/licenses/OSL-3.0
- * If you did not receive a copy of the license and are unable to obtain it
- * through the world wide web, please send an email to
- * licensing@ellislab.com so we can send you a copy immediately.
- *
- * @package CodeIgniter
- * @author EllisLab Dev Team
- * @copyright Copyright (c) 2008 - 2012, EllisLab, Inc. (http://ellislab.com/)
- * @license http://opensource.org/licenses/OSL-3.0 Open Software License (OSL 3.0)
- * @link http://codeigniter.com
- * @since Version 1.0
- * @filesource
- */
- /**
- * CodeIgniter Text Helpers
- *
- * @package CodeIgniter
- * @subpackage Helpers
- * @category Helpers
- * @author EllisLab Dev Team
- * @link http://codeigniter.com/user_guide/helpers/text_helper.html
- */
- // ------------------------------------------------------------------------
- if ( ! function_exists('word_limiter'))
- {
- /**
- * Word Limiter
- *
- * Limits a string to X number of words.
- *
- * @param string
- * @param int
- * @param string the end character. Usually an ellipsis
- * @return string
- */
- function word_limiter($str, $limit = 100, $end_char = '…')
- {
- if (trim($str) === '')
- {
- return $str;
- }
- preg_match('/^\s*+(?:\S++\s*+){1,'.(int) $limit.'}/', $str, $matches);
- if (strlen($str) === strlen($matches[0]))
- {
- $end_char = '';
- }
- return rtrim($matches[0]).$end_char;
- }
- }
- // ------------------------------------------------------------------------
- if ( ! function_exists('character_limiter'))
- {
- /**
- * Character Limiter
- *
- * Limits the string based on the character count. Preserves complete words
- * so the character count may not be exactly as specified.
- *
- * @param string
- * @param int
- * @param string the end character. Usually an ellipsis
- * @return string
- */
- function character_limiter($str, $n = 500, $end_char = '…')
- {
- if (strlen($str) < $n)
- {
- return $str;
- }
- $str = preg_replace('/\s+/', ' ', str_replace(array("\r\n", "\r", "\n"), ' ', $str));
- if (strlen($str) <= $n)
- {
- return $str;
- }
- $out = '';
- foreach (explode(' ', trim($str)) as $val)
- {
- $out .= $val.' ';
- if (strlen($out) >= $n)
- {
- $out = trim($out);
- return (strlen($out) === strlen($str)) ? $out : $out.$end_char;
- }
- }
- }
- }
- // ------------------------------------------------------------------------
- if ( ! function_exists('ascii_to_entities'))
- {
- /**
- * High ASCII to Entities
- *
- * Converts High ascii text and MS Word special characters to character entities
- *
- * @param string
- * @return string
- */
- function ascii_to_entities($str)
- {
- $count = 1;
- $out = '';
- $temp = array();
- for ($i = 0, $s = strlen($str); $i < $s; $i++)
- {
- $ordinal = ord($str[$i]);
- if ($ordinal < 128)
- {
- /*
- If the $temp array has a value but we have moved on, then it seems only
- fair that we output that entity and restart $temp before continuing. -Paul
- */
- if (count($temp) === 1)
- {
- $out .= '&#'.array_shift($temp).';';
- $count = 1;
- }
- $out .= $str[$i];
- }
- else
- {
- if (count($temp) === 0)
- {
- $count = ($ordinal < 224) ? 2 : 3;
- }
- $temp[] = $ordinal;
- if (count($temp) === $count)
- {
- $number = ($count === 3)
- ? (($temp[0] % 16) * 4096) + (($temp[1] % 64) * 64) + ($temp[2] % 64)
- : (($temp[0] % 32) * 64) + ($temp[1] % 64);
- $out .= '&#'.$number.';';
- $count = 1;
- $temp = array();
- }
- }
- }
- return $out;
- }
- }
- // ------------------------------------------------------------------------
- if ( ! function_exists('entities_to_ascii'))
- {
- /**
- * Entities to ASCII
- *
- * Converts character entities back to ASCII
- *
- * @param string
- * @param bool
- * @return string
- */
- function entities_to_ascii($str, $all = TRUE)
- {
- if (preg_match_all('/\&#(\d+)\;/', $str, $matches))
- {
- for ($i = 0, $s = count($matches[0]); $i < $s; $i++)
- {
- $digits = $matches[1][$i];
- $out = '';
- if ($digits < 128)
- {
- $out .= chr($digits);
- }
- elseif ($digits < 2048)
- {
- $out .= chr(192 + (($digits - ($digits % 64)) / 64)).chr(128 + ($digits % 64));
- }
- else
- {
- $out .= chr(224 + (($digits - ($digits % 4096)) / 4096))
- .chr(128 + ((($digits % 4096) - ($digits % 64)) / 64))
- .chr(128 + ($digits % 64));
- }
- $str = str_replace($matches[0][$i], $out, $str);
- }
- }
- if ($all)
- {
- return str_replace(array('&', '<', '>', '"', ''', '-'),
- array('&', '<', '>', '"', "'", '-'),
- $str);
- }
- return $str;
- }
- }
- // ------------------------------------------------------------------------
- if ( ! function_exists('word_censor'))
- {
- /**
- * Word Censoring Function
- *
- * Supply a string and an array of disallowed words and any
- * matched words will be converted to #### or to the replacement
- * word you've submitted.
- *
- * @param string the text string
- * @param string the array of censoered words
- * @param string the optional replacement value
- * @return string
- */
- function word_censor($str, $censored, $replacement = '')
- {
- if ( ! is_array($censored))
- {
- return $str;
- }
- $str = ' '.$str.' ';
- // \w, \b and a few others do not match on a unicode character
- // set for performance reasons. As a result words like 端ber
- // will not match on a word boundary. Instead, we'll assume that
- // a bad word will be bookeneded by any of these characters.
- $delim = '[-_\'\"`(){}<>\[\]|!?@#%&,.:;^~*+=\/ 0-9\n\r\t]';
- foreach ($censored as $badword)
- {
- if ($replacement !== '')
- {
- $str = preg_replace("/({$delim})(".str_replace('\*', '\w*?', preg_quote($badword, '/')).")({$delim})/i", "\\1{$replacement}\\3", $str);
- }
- else
- {
- $str = preg_replace("/({$delim})(".str_replace('\*', '\w*?', preg_quote($badword, '/')).")({$delim})/ie", "'\\1'.str_repeat('#', strlen('\\2')).'\\3'", $str);
- }
- }
- return trim($str);
- }
- }
- // ------------------------------------------------------------------------
- if ( ! function_exists('highlight_code'))
- {
- /**
- * Code Highlighter
- *
- * Colorizes code strings
- *
- * @param string the text string
- * @return string
- */
- function highlight_code($str)
- {
- /* The highlight string function encodes and highlights
- * brackets so we need them to start raw.
- *
- * Also replace any existing PHP tags to temporary markers
- * so they don't accidentally break the string out of PHP,
- * and thus, thwart the highlighting.
- */
- $str = str_replace(array('<', '>', '<?', '?>', '<%', '%>', '\\', '</script>'),
- array('<', '>', 'phptagopen', 'phptagclose', 'asptagopen', 'asptagclose', 'backslashtmp', 'scriptclose'),
- $str);
- // The highlight_string function requires that the text be surrounded
- // by PHP tags, which we will remove later
- $str = highlight_string('<?php '.$str.' ?>', TRUE);
- // Remove our artificially added PHP, and the syntax highlighting that came with it
- $str = preg_replace(array(
- '/<span style="color: #([A-Z0-9]+)"><\?php( | )/i',
- '/(<span style="color: #[A-Z0-9]+">.*?)\?><\/span>\n<\/span>\n<\/code>/is',
- '/<span style="color: #[A-Z0-9]+"\><\/span>/i'
- ),
- array(
- '<span style="color: #$1">',
- "$1</span>\n</span>\n</code>",
- ''
- ),
- $str);
- // Replace our markers back to PHP tags.
- return str_replace(array('phptagopen', 'phptagclose', 'asptagopen', 'asptagclose', 'backslashtmp', 'scriptclose'),
- array('<?', '?>', '<%', '%>', '\\', '</script>'),
- $str);
- }
- }
- // ------------------------------------------------------------------------
- if ( ! function_exists('highlight_phrase'))
- {
- /**
- * Phrase Highlighter
- *
- * Highlights a phrase within a text string
- *
- * @param string the text string
- * @param string the phrase you'd like to highlight
- * @param string the openging tag to precede the phrase with
- * @param string the closing tag to end the phrase with
- * @return string
- */
- function highlight_phrase($str, $phrase, $tag_open = '<strong>', $tag_close = '</strong>')
- {
- if ($str === '')
- {
- return '';
- }
- if ($phrase !== '')
- {
- return preg_replace('/('.preg_quote($phrase, '/').')/i', $tag_open.'\\1'.$tag_close, $str);
- }
- return $str;
- }
- }
- // ------------------------------------------------------------------------
- if ( ! function_exists('convert_accented_characters'))
- {
- /**
- * Convert Accented Foreign Characters to ASCII
- *
- * @param string the text string
- * @return string
- */
- function convert_accented_characters($str)
- {
- global $foreign_characters;
- if ( ! isset($foreign_characters) OR ! is_array($foreign_characters))
- {
- if (defined('ENVIRONMENT') && is_file(APPPATH.'config/'.ENVIRONMENT.'/foreign_chars.php'))
- {
- include(APPPATH.'config/'.ENVIRONMENT.'/foreign_chars.php');
- }
- elseif (is_file(APPPATH.'config/foreign_chars.php'))
- {
- include(APPPATH.'config/foreign_chars.php');
- }
- if ( ! isset($foreign_characters) OR ! is_array($foreign_characters))
- {
- return $str;
- }
- }
- return preg_replace(array_keys($foreign_characters), array_values($foreign_characters), $str);
- }
- }
- // ------------------------------------------------------------------------
- /**
- * Word Wrap
- *
- * Wraps text at the specified character. Maintains the integrity of words.
- * Anything placed between {unwrap}{/unwrap} will not be word wrapped, nor
- * will URLs.
- *
- * @param string the text string
- * @param int the number of characters to wrap at
- * @return string
- */
- if ( ! function_exists('word_wrap'))
- {
- function word_wrap($str, $charlim = 76)
- {
- // Set the character limit
- if ( ! is_numeric($charlim))
- {
- $charlim = 76;
- }
- // Reduce multiple spaces
- $str = preg_replace('| +|', ' ', $str);
- // Standardize newlines
- if (strpos($str, "\r") !== FALSE)
- {
- $str = str_replace(array("\r\n", "\r"), "\n", $str);
- }
- // If the current word is surrounded by {unwrap} tags we'll
- // strip the entire chunk and replace it with a marker.
- $unwrap = array();
- if (preg_match_all('|(\{unwrap\}.+?\{/unwrap\})|s', $str, $matches))
- {
- for ($i = 0, $c = count($matches[0]); $i < $c; $i++)
- {
- $unwrap[] = $matches[1][$i];
- $str = str_replace($matches[1][$i], '{{unwrapped'.$i.'}}', $str);
- }
- }
- // Use PHP's native function to do the initial wordwrap.
- // We set the cut flag to FALSE so that any individual words that are
- // too long get left alone. In the next step we'll deal with them.
- $str = wordwrap($str, $charlim, "\n", FALSE);
- // Split the string into individual lines of text and cycle through them
- $output = '';
- foreach (explode("\n", $str) as $line)
- {
- // Is the line within the allowed character count?
- // If so we'll join it to the output and continue
- if (strlen($line) <= $charlim)
- {
- $output .= $line."\n";
- continue;
- }
- $temp = '';
- while ((strlen($line)) > $charlim)
- {
- // If the over-length word is a URL we won't wrap it
- if (preg_match('!\[url.+\]|://|wwww.!', $line))
- {
- break;
- }
- // Trim the word down
- $temp .= substr($line, 0, $charlim - 1);
- $line = substr($line, $charlim - 1);
- }
- // If $temp contains data it means we had to split up an over-length
- // word into smaller chunks so we'll add it back to our current line
- if ($temp !== '')
- {
- $output .= $temp."\n".$line."\n";
- }
- else
- {
- $output .= $line."\n";
- }
- }
- // Put our markers back
- if (count($unwrap) > 0)
- {
- foreach ($unwrap as $key => $val)
- {
- $output = str_replace('{{unwrapped'.$key.'}}', $val, $output);
- }
- }
- // Remove the unwrap tags and return
- return str_replace(array('{unwrap}', '{/unwrap}'), '', $output);
- }
- }
- // ------------------------------------------------------------------------
- if ( ! function_exists('ellipsize'))
- {
- /**
- * Ellipsize String
- *
- * This function will strip tags from a string, split it at its max_length and ellipsize
- *
- * @param string string to ellipsize
- * @param int max length of string
- * @param mixed int (1|0) or float, .5, .2, etc for position to split
- * @param string ellipsis ; Default '...'
- * @return string ellipsized string
- */
- function ellipsize($str, $max_length, $position = 1, $ellipsis = '…')
- {
- // Strip tags
- $str = trim(strip_tags($str));
- // Is the string long enough to ellipsize?
- if (strlen($str) <= $max_length)
- {
- return $str;
- }
- $beg = substr($str, 0, floor($max_length * $position));
- $position = ($position > 1) ? 1 : $position;
- if ($position === 1)
- {
- $end = substr($str, 0, -($max_length - strlen($beg)));
- }
- else
- {
- $end = substr($str, -($max_length - strlen($beg)));
- }
- return $beg.$ellipsis.$end;
- }
- }
- /* End of file text_helper.php */
- /* Location: ./system/helpers/text_helper.php */