tims-todo/system/helpers/text_helper.php

568 lines
14 KiB
PHP
Raw Permalink Normal View History

<?php
2014-08-08 15:41:59 -04:00
/**
* CodeIgniter
*
* An open source application development framework for PHP
2014-08-08 15:41:59 -04:00
*
* This content is released under the MIT License (MIT)
*
* Copyright (c) 2014 - 2019, British Columbia Institute of Technology
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*
* @package CodeIgniter
* @author EllisLab Dev Team
* @copyright Copyright (c) 2008 - 2014, EllisLab, Inc. (https://ellislab.com/)
* @copyright Copyright (c) 2014 - 2019, British Columbia Institute of Technology (https://bcit.ca/)
* @license https://opensource.org/licenses/MIT MIT License
* @link https://codeigniter.com
* @since Version 1.0.0
2014-08-08 15:41:59 -04:00
* @filesource
*/
defined('BASEPATH') OR exit('No direct script access allowed');
2014-08-08 15:41:59 -04:00
/**
* CodeIgniter Text Helpers
*
* @package CodeIgniter
* @subpackage Helpers
* @category Helpers
* @author EllisLab Dev Team
* @link https://codeigniter.com/user_guide/helpers/text_helper.html
2014-08-08 15:41:59 -04:00
*/
// ------------------------------------------------------------------------
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
*/
2014-08-08 15:41:59 -04:00
function word_limiter($str, $limit = 100, $end_char = '&#8230;')
{
if (trim($str) === '')
2014-08-08 15:41:59 -04:00
{
return $str;
}
preg_match('/^\s*+(?:\S++\s*+){1,'.(int) $limit.'}/', $str, $matches);
if (strlen($str) === strlen($matches[0]))
2014-08-08 15:41:59 -04:00
{
$end_char = '';
}
return rtrim($matches[0]).$end_char;
}
}
// ------------------------------------------------------------------------
if ( ! function_exists('character_limiter'))
{
/**
* Character Limiter
*
* Limits the string based on the character count. Preserves complete words
* so the character count may not be exactly as specified.
*
* @param string
* @param int
* @param string the end character. Usually an ellipsis
* @return string
*/
2014-08-08 15:41:59 -04:00
function character_limiter($str, $n = 500, $end_char = '&#8230;')
{
if (mb_strlen($str) < $n)
2014-08-08 15:41:59 -04:00
{
return $str;
}
// a bit complicated, but faster than preg_replace with \s+
$str = preg_replace('/ {2,}/', ' ', str_replace(array("\r", "\n", "\t", "\v", "\f"), ' ', $str));
2014-08-08 15:41:59 -04:00
if (mb_strlen($str) <= $n)
2014-08-08 15:41:59 -04:00
{
return $str;
}
$out = '';
2014-08-08 15:41:59 -04:00
foreach (explode(' ', trim($str)) as $val)
{
$out .= $val.' ';
if (mb_strlen($out) >= $n)
2014-08-08 15:41:59 -04:00
{
$out = trim($out);
return (mb_strlen($out) === mb_strlen($str)) ? $out : $out.$end_char;
2014-08-08 15:41:59 -04:00
}
}
}
}
// ------------------------------------------------------------------------
if ( ! function_exists('ascii_to_entities'))
{
/**
* High ASCII to Entities
*
* Converts high ASCII text and MS Word special characters to character entities
*
* @param string $str
* @return string
*/
2014-08-08 15:41:59 -04:00
function ascii_to_entities($str)
{
$out = '';
$length = defined('MB_OVERLOAD_STRING')
? mb_strlen($str, '8bit') - 1
: strlen($str) - 1;
for ($i = 0, $count = 1, $temp = array(); $i <= $length; $i++)
2014-08-08 15:41:59 -04:00
{
$ordinal = ord($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)
2014-08-08 15:41:59 -04:00
{
$out .= '&#'.array_shift($temp).';';
2014-08-08 15:41:59 -04:00
$count = 1;
}
$out .= $str[$i];
}
else
{
if (count($temp) === 0)
2014-08-08 15:41:59 -04:00
{
$count = ($ordinal < 224) ? 2 : 3;
}
$temp[] = $ordinal;
if (count($temp) === $count)
2014-08-08 15:41:59 -04:00
{
$number = ($count === 3)
? (($temp[0] % 16) * 4096) + (($temp[1] % 64) * 64) + ($temp[2] % 64)
: (($temp[0] % 32) * 64) + ($temp[1] % 64);
2014-08-08 15:41:59 -04:00
$out .= '&#'.$number.';';
$count = 1;
$temp = array();
}
// If this is the last iteration, just output whatever we have
elseif ($i === $length)
{
$out .= '&#'.implode(';', $temp).';';
}
2014-08-08 15:41:59 -04:00
}
}
return $out;
}
}
// ------------------------------------------------------------------------
if ( ! function_exists('entities_to_ascii'))
{
/**
* Entities to ASCII
*
* Converts character entities back to ASCII
*
* @param string
* @param bool
* @return string
*/
2014-08-08 15:41:59 -04:00
function entities_to_ascii($str, $all = TRUE)
{
if (preg_match_all('/\&#(\d+)\;/', $str, $matches))
{
for ($i = 0, $s = count($matches[0]); $i < $s; $i++)
2014-08-08 15:41:59 -04:00
{
$digits = $matches[1][$i];
2014-08-08 15:41:59 -04:00
$out = '';
if ($digits < 128)
{
$out .= chr($digits);
}
elseif ($digits < 2048)
{
$out .= chr(192 + (($digits - ($digits % 64)) / 64)).chr(128 + ($digits % 64));
2014-08-08 15:41:59 -04:00
}
else
{
$out .= chr(224 + (($digits - ($digits % 4096)) / 4096))
.chr(128 + ((($digits % 4096) - ($digits % 64)) / 64))
.chr(128 + ($digits % 64));
2014-08-08 15:41:59 -04:00
}
$str = str_replace($matches[0][$i], $out, $str);
2014-08-08 15:41:59 -04:00
}
}
if ($all)
{
return str_replace(
array('&amp;', '&lt;', '&gt;', '&quot;', '&apos;', '&#45;'),
array('&', '<', '>', '"', "'", '-'),
$str
);
2014-08-08 15:41:59 -04:00
}
return $str;
}
}
// ------------------------------------------------------------------------
if ( ! function_exists('word_censor'))
{
/**
* Word Censoring Function
*
* Supply a string and an array of disallowed words and any
* matched words will be converted to #### or to the replacement
* word you've submitted.
*
* @param string the text string
* @param string the array of censored words
* @param string the optional replacement value
* @return string
*/
2014-08-08 15:41:59 -04:00
function word_censor($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 über
// 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)
{
$badword = str_replace('\*', '\w*?', preg_quote($badword, '/'));
if ($replacement !== '')
2014-08-08 15:41:59 -04:00
{
$str = preg_replace(
"/({$delim})(".$badword.")({$delim})/i",
"\\1{$replacement}\\3",
$str
);
2014-08-08 15:41:59 -04:00
}
elseif (preg_match_all("/{$delim}(".$badword."){$delim}/i", $str, $matches, PREG_PATTERN_ORDER | PREG_OFFSET_CAPTURE))
2014-08-08 15:41:59 -04:00
{
$matches = $matches[1];
for ($i = count($matches) - 1; $i >= 0; $i--)
{
$length = strlen($matches[$i][0]);
$str = substr_replace(
$str,
str_repeat('#', $length),
$matches[$i][1],
$length
);
}
2014-08-08 15:41:59 -04:00
}
}
return trim($str);
}
}
// ------------------------------------------------------------------------
if ( ! function_exists('highlight_code'))
{
/**
* Code Highlighter
*
* Colorizes code strings
*
* @param string the text string
* @return string
*/
2014-08-08 15:41:59 -04:00
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('&lt;', '&gt;', '<?', '?>', '<%', '%>', '\\', '</script>'),
array('<', '>', 'phptagopen', 'phptagclose', 'asptagopen', 'asptagclose', 'backslashtmp', 'scriptclose'),
$str
);
2014-08-08 15:41:59 -04:00
// The highlight_string function requires that the text be surrounded
// by PHP tags, which we will remove later
$str = highlight_string('<?php '.$str.' ?>', TRUE);
2014-08-08 15:41:59 -04:00
// Remove our artificially added PHP, and the syntax highlighting that came with it
$str = preg_replace(
array(
'/<span style="color: #([A-Z0-9]+)">&lt;\?php(&nbsp;| )/i',
'/(<span style="color: #[A-Z0-9]+">.*?)\?&gt;<\/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
);
2014-08-08 15:41:59 -04:00
// Replace our markers back to PHP tags.
return str_replace(
array('phptagopen', 'phptagclose', 'asptagopen', 'asptagclose', 'backslashtmp', 'scriptclose'),
array('&lt;?', '?&gt;', '&lt;%', '%&gt;', '\\', '&lt;/script&gt;'),
$str
);
2014-08-08 15:41:59 -04:00
}
}
// ------------------------------------------------------------------------
if ( ! function_exists('highlight_phrase'))
{
/**
* Phrase Highlighter
*
* Highlights a phrase within a text string
*
* @param string $str the text string
* @param string $phrase the phrase you'd like to highlight
* @param string $tag_open the openging tag to precede the phrase with
* @param string $tag_close the closing tag to end the phrase with
* @return string
*/
function highlight_phrase($str, $phrase, $tag_open = '<mark>', $tag_close = '</mark>')
2014-08-08 15:41:59 -04:00
{
return ($str !== '' && $phrase !== '')
? preg_replace('/('.preg_quote($phrase, '/').')/i'.(UTF8_ENABLED ? 'u' : ''), $tag_open.'\\1'.$tag_close, $str)
: $str;
2014-08-08 15:41:59 -04:00
}
}
// ------------------------------------------------------------------------
if ( ! function_exists('convert_accented_characters'))
{
/**
* Convert Accented Foreign Characters to ASCII
*
* @param string $str Input string
* @return string
*/
2014-08-08 15:41:59 -04:00
function convert_accented_characters($str)
{
static $array_from, $array_to;
2014-08-08 15:41:59 -04:00
if ( ! is_array($array_from))
2014-08-08 15:41:59 -04:00
{
if (file_exists(APPPATH.'config/foreign_chars.php'))
{
include(APPPATH.'config/foreign_chars.php');
}
if (file_exists(APPPATH.'config/'.ENVIRONMENT.'/foreign_chars.php'))
{
include(APPPATH.'config/'.ENVIRONMENT.'/foreign_chars.php');
}
if (empty($foreign_characters) OR ! is_array($foreign_characters))
{
$array_from = array();
$array_to = array();
return $str;
}
$array_from = array_keys($foreign_characters);
$array_to = array_values($foreign_characters);
2014-08-08 15:41:59 -04:00
}
return preg_replace($array_from, $array_to, $str);
2014-08-08 15:41:59 -04:00
}
}
// ------------------------------------------------------------------------
if ( ! function_exists('word_wrap'))
{
/**
* 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 $str the text string
* @param int $charlim = 76 the number of characters to wrap at
* @return string
*/
function word_wrap($str, $charlim = 76)
2014-08-08 15:41:59 -04:00
{
// Set the character limit
is_numeric($charlim) OR $charlim = 76;
2014-08-08 15:41:59 -04:00
// Reduce multiple spaces
$str = preg_replace('| +|', ' ', $str);
2014-08-08 15:41:59 -04:00
// Standardize newlines
if (strpos($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, $matches))
2014-08-08 15:41:59 -04:00
{
for ($i = 0, $c = count($matches[0]); $i < $c; $i++)
2014-08-08 15:41:59 -04:00
{
$unwrap[] = $matches[1][$i];
$str = str_replace($matches[0][$i], '{{unwrapped'.$i.'}}', $str);
2014-08-08 15:41:59 -04:00
}
}
// 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.
2014-08-08 15:41:59 -04:00
$str = wordwrap($str, $charlim, "\n", FALSE);
// Split the string into individual lines of text and cycle through them
$output = '';
2014-08-08 15:41:59 -04:00
foreach (explode("\n", $str) as $line)
{
// Is the line within the allowed character count?
// If so we'll join it to the output and continue
if (mb_strlen($line) <= $charlim)
2014-08-08 15:41:59 -04:00
{
$output .= $line."\n";
continue;
}
$temp = '';
while (mb_strlen($line) > $charlim)
2014-08-08 15:41:59 -04:00
{
// If the over-length word is a URL we won't wrap it
if (preg_match('!\[url.+\]|://|www\.!', $line))
2014-08-08 15:41:59 -04:00
{
break;
}
// Trim the word down
$temp .= mb_substr($line, 0, $charlim - 1);
$line = mb_substr($line, $charlim - 1);
2014-08-08 15:41:59 -04:00
}
// 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 !== '')
2014-08-08 15:41:59 -04:00
{
$output .= $temp."\n".$line."\n";
2014-08-08 15:41:59 -04:00
}
else
{
$output .= $line."\n";
2014-08-08 15:41:59 -04:00
}
}
// Put our markers back
if (count($unwrap) > 0)
{
foreach ($unwrap as $key => $val)
{
$output = str_replace('{{unwrapped'.$key.'}}', $val, $output);
2014-08-08 15:41:59 -04:00
}
}
return $output;
}
}
// ------------------------------------------------------------------------
if ( ! function_exists('ellipsize'))
{
/**
* Ellipsize String
*
* This function will strip tags from a string, split it at its max_length and ellipsize
*
* @param string string to ellipsize
* @param int max length of string
* @param mixed int (1|0) or float, .5, .2, etc for position to split
* @param string ellipsis ; Default '...'
* @return string ellipsized string
*/
2014-08-08 15:41:59 -04:00
function ellipsize($str, $max_length, $position = 1, $ellipsis = '&hellip;')
{
// Strip tags
$str = trim(strip_tags($str));
// Is the string long enough to ellipsize?
if (mb_strlen($str) <= $max_length)
2014-08-08 15:41:59 -04:00
{
return $str;
}
$beg = mb_substr($str, 0, floor($max_length * $position));
2014-08-08 15:41:59 -04:00
$position = ($position > 1) ? 1 : $position;
if ($position === 1)
{
$end = mb_substr($str, 0, -($max_length - mb_strlen($beg)));
2014-08-08 15:41:59 -04:00
}
else
{
$end = mb_substr($str, -($max_length - mb_strlen($beg)));
2014-08-08 15:41:59 -04:00
}
return $beg.$ellipsis.$end;
}
}