php中文支持函数php中文截取字符串函数PHP中文字符串翻转

2. /**
3. * 将一个字串中含有全角的数字字符、字母、空格或'%+-()'字符转换为相应半角字符
4. *
5. * @access public
6. * @param string $str 待转换字串
7. *
8. * @return string $str 处理后字串
9. */
10. function make_semiangle($str)
11. {
12. $arr = array('０' => '0', '１' => '1', '２' => '2', '３' => '3', '４' => '4',
13. '５' => '5', '６' => '6', '７' => '7', '８' => '8', '９' => '9',
14. 'Ａ' => 'A', 'Ｂ' => 'B', 'Ｃ' => 'C', 'Ｄ' => 'D', 'Ｅ' => 'E',
15. 'Ｆ' => 'F', 'Ｇ' => 'G', 'Ｈ' => 'H', 'Ｉ' => 'I', 'Ｊ' => 'J',
16. 'Ｋ' => 'K', 'Ｌ' => 'L', 'Ｍ' => 'M', 'Ｎ' => 'N', 'Ｏ' => 'O',
17. 'Ｐ' => 'P', 'Ｑ' => 'Q', 'Ｒ' => 'R', 'Ｓ' => 'S', 'Ｔ' => 'T',
18. 'Ｕ' => 'U', 'Ｖ' => 'V', 'Ｗ' => 'W', 'Ｘ' => 'X', 'Ｙ' => 'Y',
19. 'Ｚ' => 'Z', 'ａ' => 'a', 'ｂ' => 'b', 'ｃ' => 'c', 'ｄ' => 'd',
20. 'ｅ' => 'e', 'ｆ' => 'f', 'ｇ' => 'g', 'ｈ' => 'h', 'ｉ' => 'i',
21. 'ｊ' => 'j', 'ｋ' => 'k', 'ｌ' => 'l', 'ｍ' => 'm', 'ｎ' => 'n',
22. 'ｏ' => 'o', 'ｐ' => 'p', 'ｑ' => 'q', 'ｒ' => 'r', 'ｓ' => 's',
23. 'ｔ' => 't', 'ｕ' => 'u', 'ｖ' => 'v', 'ｗ' => 'w', 'ｘ' => 'x',
24. 'ｙ' => 'y', 'ｚ' => 'z',
25. '（' => '(', '）' => ')', '〔' => '[', '〕' => ']', '【' => '[',
26. '】' => ']', '〖' => '[', '〗' => ']', '“' => '[', '”' => ']',
27. '‘' => '[', '’' => ']', '｛' => '{', '｝' => '}', '《' => '<',
28. '》' => '>',
29. '％' => '%', '＋' => '+', '—' => '-', '－' => '-', '～' => '-',
30. '：' => ':', '。' => '.', '、' => ',', '，' => '.', '、' => '.',
31. '；' => ',', '？' => '?', '！' => '!', '…' => '-', '‖' => '|',
32. '”' => '"', '’' => '`', '‘' => '`', '｜' => '|', '〃' => '"',
33. '　' => ' ','＄'=>'$','＠'=>'@','＃'=>'#','＾'=>'^','＆'=>'&','＊'=>'*');
35. return strtr($str, $arr);
36. }

例2，php中文截取字符串

2. /*
3. Utf-8、gb2312都支持的汉字截取函数
4. cut_str(字符串, 截取长度, 开始长度, 编码);
5. 编码默认为 utf-8
6. 开始长度默认为 0
7. * edit: bbs.it-home.org
8. */
9. function cut_str($string, $sublen, $start = 0, $code = 'UTF-8') {
10. if ($code == 'UTF-8') {
11. $pa = "/[\x01-\x7f]|[\xc2-\xdf][\x80-\xbf]|\xe0[\xa0-\xbf][\x80-\xbf]|[\xe1-\xef][\x80-\xbf][\x80-\xbf]|\xf0[\x90-\xbf][\x80-\xbf][\x80-\xbf]|[\xf1-\xf7][\x80-\xbf][\x80-\xbf][\x80-\xbf]/";
12. preg_match_all ( $pa, $string, $t_string );
13. if (count ( $t_string [0] ) - $start > $sublen)
14. return join ( '', array_slice ( $t_string [0], $start, $sublen ) ) . "...";
15. return join ( '', array_slice ( $t_string [0], $start, $sublen ) );
16. } else {
17. $start = $start * 2;
18. $sublen = $sublen * 2;
19. $strlen = strlen ( $string );
20. $tmpstr = '';
21. for($i = 0; $i < $strlen; $i ++) {
22. if ($i >= $start && $i < ($start + $sublen)) {
23. if (ord ( substr ( $string, $i, 1 ) ) > 129) {
24. $tmpstr .= substr ( $string, $i, 2 );
25. } else {
26. $tmpstr .= substr ( $string, $i, 1 );
27. }
28. }
29. if (ord ( substr ( $string, $i, 1 ) ) > 129)
30. $i ++;
31. }
32. if (strlen ( $tmpstr ) < $strlen)
33. $tmpstr .= "...";
34. return $tmpstr;
35. }
36. }
37. $str = "abcd需要截取的字符串";
38. echo cut_str ( $str, 1, 0, 'gb2312' );
39. ?>

例3，字符串的载取

2. /**
3. * 字符截取 支持UTF8/GBK
4. * @param $string
5. * @param $length
6. * @param $dot
7. */
8. function str_cut($string, $length, $charset = 'utf-8', $dot = '...') {
9. $strlen = strlen($string);
10. if($strlen <= $length) return $string;
11. $string = str_replace(array(' ',' ', '&', '"', ''', '“', '”', '—', '<', '>', '·', '…'), array('∵',' ', '&', '"', "'", '“', '”', '—', '<', '>', '·', '…'), $string);
12. $strcut = '';
13. if(strtolower($charset) == 'utf-8') {
14. $length = intval($length-strlen($dot)-$length/3);
15. $n = $tn = $noc = 0;
16. while($n < strlen($string)) {
17. $t = ord($string[$n]);
18. if($t == 9 || $t == 10 || (32 <= $t && $t <= 126)) {
19. $tn = 1; $n++; $noc++;
20. } elseif(194 <= $t && $t <= 223) {
21. $tn = 2; $n += 2; $noc += 2;
22. } elseif(224 <= $t && $t <= 239) {
23. $tn = 3; $n += 3; $noc += 2;
24. } elseif(240 <= $t && $t <= 247) {
25. $tn = 4; $n += 4; $noc += 2;
26. } elseif(248 <= $t && $t <= 251) {
27. $tn = 5; $n += 5; $noc += 2;
28. } elseif($t == 252 || $t == 253) {
29. $tn = 6; $n += 6; $noc += 2;
30. } else {
31. $n++;
32. }
33. if($noc >= $length) {
34. break;
35. }
36. }
37. if($noc > $length) {
38. $n -= $tn;
39. }
40. $strcut = substr($string, 0, $n);
41. $strcut = str_replace(array('∵', '&', '"', "'", '“', '”', '—', '<', '>', '·', '…'), array(' ', '&', '"', ''', '“', '”', '—', '<', '>', '·', '…'), $strcut);
42. } else {
43. $dotlen = strlen($dot);
44. $maxi = $length - $dotlen - 1;
45. $current_str = '';
46. $search_arr = array('&',' ', '"', "'", '“', '”', '—', '<', '>', '·', '…','∵');
47. $replace_arr = array('&',' ', '"', ''', '“', '”', '—', '<', '>', '·', '…',' ');
48. $search_flip = array_flip($search_arr);
49. for ($i = 0; $i < $maxi; $i++) {
50. $current_str = ord($string[$i]) > 127 ? $string[$i].$string[++$i] : $string[$i];
51. if (in_array($current_str, $search_arr)) {
52. $key = $search_flip[$current_str];
53. $current_str = str_replace($search_arr[$key], $replace_arr[$key], $current_str);
54. }
55. $strcut .= $current_str;
56. }
57. }
58. return $strcut.$dot;
59. }

例4，PHP中文字符串翻转 翻转一个字符串可以使用strrev()函数即可。 但有时需要处理是字符串是含中文的，这样用strrev就会出现乱码。 这里自定义一个函数来处理含中文的字符。

3. /**

4. * 中文字符串翻转
5. * by bbs.it-home.org
6. */
7. function cstrrev($str)
8. {
9. $len = strlen($str);
10. for($i = 0; $i < $len; $i++)
11. {
12. $char = $str{0};
13. if(ord($char) > 127)
14. {
15. $i++;
16. if($i < $len)
17. {
18. $arr[] = substr($str, 0, 2);
19. $str = substr($str, 2);
20. }
21. }
22. else
23. {
24. $arr[] = $char;
25. $str = substr($str, 1);
26. }
27. }
28. return join(array_reverse($arr));
29. }

30. #使用方法：

31. $str = '中文.look!';
32. echo cstrrev($str);
33. #结果输出：!kool.文中

附5，

2. function str_replace_cn($needle, $str, $haystack, $charset = "utf-8"){
3. $re['utf-8'] = "/[\x01-\x7f]|[\xc2-\xdf][\x80-\xbf]|[\xe0-\xef][\x80-\xbf]{2}|[\xf0-\xff][\x80-\xbf]{3}/";
4. $re['gb2312'] = "/[\x01-\x7f]|[\xb0-\xf7][\xa0-\xfe]/";
5. $re['gbk'] = "/[\x01-\x7f]|[\x81-\xfe][\x40-\xfe]/";
6. $re['big5'] = "/[\x01-\x7f]|[\x81-\xfe]([\x40-\x7e]|\xa1-\xfe])/";
8. preg_match_all($re[$charset], $haystack, $match_haystack);
9. preg_match_all($re[$charset], $needle, $match_needle);
11. for($i = 0; $i < count($match_needle); $i ++){
12. if(!in_array($match_needle[0][$i], $match_haystack[0]))return $haystack;//无匹配
13. }
15. $match_haystack = $match_haystack[0];
16. $match_needle = $match_needle[0];
18. for($i = 0; $i < count($match_haystack); $i ++){
19. if($match_haystack[$i] == "")continue;
20. if($match_haystack[$i] == $match_needle[0]){
21. if(count($match_needle) == 1){//如果只一个字符
22. $match_haystack[$i] = $str;
23. }else{
24. $flag = true;
25. for($j = 1; $j < count($match_needle); $j ++){
26. if($match_haystack[$i + $j] != $match_needle[$j]){
27. $flag = false;
28. break;
29. }
30. }
31. if($flag){//匹配
32. $match_haystack[$i] = $str;
33. for($j = 1; $j < count($match_needle); $j ++){
34. $match_haystack[$i + $j] = "";
35. }
36. }
37. }
38. }
39. }
40. return implode("", $match_haystack);
41. }