Compare discuz and ecshop interception string function php version_PHP tutorial

/**
* [discuz] Intercept string based on PHP without mb_substr and other extensions installed. If Chinese characters are intercepted, it will be calculated as 2 characters
* @param $string The string to be intercepted
* @param $length to be Number of characters intercepted
* @param $dot Replace the ending string of the truncated part
* @return Return the intercepted string
* /
function cutstr($string, $length, $dot = '...') {
// If the string is less than the length to be intercepted, return directly
// Use strlen here to get the characters String length has great disadvantages. For example, if you want to intercept 4 Chinese characters from the string "Happy New Year",
// then you must know the number of bytes of these 4 Chinese characters, otherwise the returned string may be " Happy New Year..."
if (strlen($string) <= $length) {
return $string;
}
// Convert htmlspecialchars in the original string
$pre = chr(1);
$end = chr(1);
$string = str_replace ( array ('&', '"', '<', '>' ), array ($pre . '&' . $end, $pre . '"' . $end, $pre . '<' . $end, $pre . '>' . $end ), $string );
$strcut = ''; // Initialization return value
// If it is utf-8 encoding (this judgment is a bit incomplete, it may be utf8)
if (strtolower ( CHARSET ) == 'utf-8') {
//Initial continuous loop pointer $n, the last number of characters $tn, the number of intercepted characters $noc
$n = $tn = $noc = 0;
while ( $n < strlen ( $string ) ) {
$t = ord ( $string [$n] );
if ($t == 9 || $t == 10 || (32 <= $t && $t <= 126)) {
// If it is an English half-width symbol, etc., the $n pointer moves back by 1 digit, and the last word of $tn is 1 digit
$tn = 1;
$n++;
$noc++;
} elseif (194 <= $t && $t <= 223) {
// If it is a two-byte character, the $n pointer is moved back by 2 bits, and the last word of $tn is 2 bit
$tn = 2;
$n += 2;
$noc += 2;
} elseif (224 <= $t && $t <= 239) {
// If it is three bytes (can be understood as a Chinese word), $n is shifted back by 3 digits, and the last word of $tn is 3 digits
$tn = 3;
$n += 3;
$noc += 2;
} elseif (240 <= $t && $t <= 247) {
$tn = 4;
$n += 4;
$noc += 2;
} elseif (248 <= $t && $t <= 251) {
$tn = 5;
$n += 5;
$noc += 2 ;
} elseif ($t == 252 || $t == 253) {
$tn = 6;
$n += 6;
$noc += 2;
} else {
$n++;
}
// Break out of the continuous loop if the number is exceeded
if ($noc >= $length) {
break;
}
}
// This place is to remove the last word in preparation for adding $dot
if ($noc > $length) {
$n -= $tn;
}
$strcut = substr ( $string, 0, $n );
} else {
// Full-width encoding that is not utf-8 is shifted back by 2 bits
for ($i = 0 ; $i < $length; $i ++) {
$strcut .= ord ( $string [$i] ) > 127 ? $string [$i] . $string [++ $i] : $string [$i];
}
}
// Restore the original htmlspecialchars
$strcut = str_replace( array ($pre . '&' . $end, $pre . '" ' . $end, $pre . '<' . $end, $pre . '>' . $end ), array ('&', '"', '<', '>' ), $ strcut );
$pos = strrpos ( $strcut, chr ( 1 ) );
if ($pos !== false) {
$strcut = substr ( $strcut, 0, $pos );
}
return $strcut . $dot; // Finally add the interception to $dot and output
}

$str1 = "desire to be poor";
echo my_cutstr($str1, 10, "...")."n"; // Output: desire to be poor Qianmile... [This is a bug, think about what causes it? ]
echo my_cutstr($str1, 15, "...")."n"; // Output: Seeing a Thousand Miles Away

/**
* [ecshop] Based on PHP's mb_substr and iconv_substr extensions, these two extensions are used to intercept strings. Chinese characters are calculated as 1 character in length;
* This function is only applicable to utf-8 encoded Chinese strings. .
*
* @param $str Original string
* @param $length Number of characters intercepted
* @param $append Replace the ending string with the truncated part
* @return Return The intercepted string
* /
function sub_str($str, $length = 0, $append = '...') {
$str = trim($str);
$strlength = strlen($str);
if ($length == 0 || $length >= $strlength) {
return $str;
} elseif ($length < 0) {
$length = $strlength + $ length;
if ($length < 0) {
$length = $strlength;
}
}
if ( function_exists('mb_substr') ) {
$newstr = mb_substr($str, 0, $length, 'utf-8');
} elseif ( function_exists('iconv_substr') ) {
$newstr = iconv_substr($str, 0, $length, 'utf- 8');
} else {
//$newstr = trim_right(substr($str, 0, $length));
$newstr = substr($str, 0, $length);
}
if ($append && $str != $newstr) {
$newstr .= $append;
}
return $newstr;
}

$str1 = "The sun is over the mountains, the Yellow River is over. Into the sea";
echo $str1."n";
echo my_sub_str($str1, 4, "...")."n"; // Output: The sun is shining on the mountain...
$str2 = "白1日2伊3山4";
echo $str2."n";
echo my_sub_str($str2, 4, "...")."n"; // Output: White 1st 2...

/**
* String interception, Chinese characters are calculated as 2 characters, and both GBK and UTF-8 encoding are supported
* @param $string The string to be intercepted
* @param $length The number of characters to be intercepted
* @param $append The tail added to the substring
* @return Returns the intercepted string
*/
function substring($string, $length, $append = false) {
if ( $length <= 0 ) {
return '';
}
// Check whether the original string is UTF-8 encoded
$is_utf8 = false;
$str1 = @iconv("UTF-8", "GBK", $string);
$str2 = @iconv("GBK", "UTF-8", $str1);
if ( $string == $str2 ) {
$is_utf8 = true;
// If it is UTF-8 encoding, use GBK encoded
$string = $str1;
}
$newstr = '';
for ($i = 0 ; $i < $length; $i ++) {
$newstr .= ord ($string[$i]) > 127 ? $string[$i] . $string[++$i] : $string[$i];
}
if ( $is_utf8 ) {
$newstr = @iconv("GBK", "UTF-8", $newstr);
}
if ($append && $newstr != $string) {
$newstr .= $append;
}
return $newstr;
}

$str1 = "白日At the end of the mountains, the Yellow River flows into the sea";
echo substring($str1, 4, "...")."n"; // Output: During the day...
echo substring($str1, 5 , "...")."n"; // Output: Bai Riyi...
$str2 = "12 Bai 34 Ri 56 Yi 78 Mountains";
echo substring($str2, 4, "...")."n"; // Output: 12 white...
echo substring($str2, 5, "...")."n"; // Output: 12 white 3. ..