/*
When we process Chinese data, we often have to deal with some situations. Here are some functions I made for these situations
, which have been used in practice
*/
# Determine whether a certain position is the left or right half of a Chinese character, or not Chinese
# Return value -1 Left 0 Not a Chinese character 1 Right
# Usage
/*
$a = this is Chinese;
print is_chinese($a, 1); // 0
print is_chinese($a,8); // -1
print is_chinese($a,9 ); // 1
*/
function is_chinese(&$str, $location) {
$ch = true;
$i = $location;
while(ord($str [$i])>0xa0 && $i >= 0) {
$ch = !$ch;
$i --;
}
if($i ! = $location) {
$f_str = $ch ? 1: -1;
}
else {
$f_str = false;
}
return $f_str;
}
#Chinese string inversion function
# If one inverts a string with Chinese characters using strrev, garbled characters will be generated
/*
print cstrrev(this is Chinese); // In the text si siht
*/
function cstrrev(&$str) {
$long = strlen($str);
for($f_str=, $ chinese=false, $i=$long-1; $i>=0; $i--) {
if(ord($str[$i]) > 0xa0) {
$chinese = ! $chinese;
if($chinese == false) {
$f_str .= $str[$i].$str[$i+1];
}
}
else {
$f_str .= $str[$i];
}
}
return $f_str;
}
/* Chinese string interception function
Some Chinese characters String interception functions often have some problems, for example, in some automatic line wrapping programs
$a = "1 in 2";
After intercepting twice,
csubstr($str,$a,0,2 );
csubstr($str, $a, 2,2)
Since the loading position points to the right byte of "middle", the result may be like this
1, 2
Use this The function will produce the correct result
1, 2
*/
# start starting position, starting from 0
# long = 0, then take from start to the end of the string
# ltor = true, the characters are taken from left to right, and false, the characters are taken from right to left
# $cn_len Chinese characters are taken in bytes or word count. If they are taken in word count, one Chinese character is counted as one byte
Function csubstr(&$str, $start=0, $long=0, $ltor=true, $cn_len=2) {
if($long == 0) $long = strlen($str) ;
if($ltor == false) $str = cstrrev($str);
if($cn_len == 1) {
for($i=0, $ fs=0; $i<$start; $fs++)
$i += (ord($str[$fs]) <= 0xa0) ? 1 : 0.5;
for($i=0, $fe=$fs; $i<$long; $fe++)
$i += (ord($str[$fe]) <= 0xa0) ? 1 : 0.5;
$long = $fe - $fs;
}
else {
$fs = (is_chinese($str, $start) == 1) ? $start - 1 : $start;
$fe = $long + $start - 1;
$end = ( is_chinese($str, $fe) == -1 ) ? $fe -1 : $fe;
$long = $end - $ fs + 1;
}
$f_str = substr($str, $fs, $long);
if($ltor == false) $f_str = cstrrev($f_str);
return $f_str;
}
# Get the left string
Function cleft(&$str, $long, $cn_len=2) {
$f_str = csubstr($str, 0, $long, true, $cn_len);
return $f_str;
}
# Get the right string
function cright(&$str, $long, $cn_len=2) {
$f_str = cstrrev($str);
$f_str = csubstr($f_str, 0, $long, true, $cn_len);
$f_str = cstrrev($f_str);
return $f_str;
}
# Branch articles containing Chinese characters Formatting
# No more problems caused by line breaks! ! !
# Note: Each line of the article must be separated by n (chr(13))
# $width How many characters per line
# $br What character should be used as the end character for each line
Function ctext_wrap(&$text, $width=60, $br="
") {