php内置函数分析之trim()

官方手册中：

类似函数还有两个：ltrim() 和 rtrim()。分别处理字符串的左侧、右侧。

trim()的具体实现位于：ext/standard/string.c

/* {{{ proto string trim(string str [, string character_mask])
   Strips whitespace from the beginning and end of a string */
PHP_FUNCTION(trim)
{
    php_do_trim(INTERNAL_FUNCTION_PARAM_PASSTHRU, 3);
}
/* }}} */

/* {{{ php_do_trim
 * Base for trim(), rtrim() and ltrim() functions.
 */
static void php_do_trim(INTERNAL_FUNCTION_PARAMETERS, int mode)
{
    zend_string *str;
    zend_string *what = NULL;

    ZEND_PARSE_PARAMETERS_START(1, 2)
        Z_PARAM_STR(str)
        Z_PARAM_OPTIONAL
        Z_PARAM_STR(what)
    ZEND_PARSE_PARAMETERS_END();

    ZVAL_STR(return_value, php_trim(str, (what ? ZSTR_VAL(what) : NULL), (what ? ZSTR_LEN(what) : 0), mode));
}
/* }}} */

具体实现：

/* {{{ php_trim()
 * mode 1 : trim left
 * mode 2 : trim right
 * mode 3 : trim left and right
 * what indicates which chars are to be trimmed. NULL->default (' 	

v')
 */
PHPAPI zend_string *php_trim(zend_string *str, char *what, size_t what_len, int mode)
{
    const char *c = ZSTR_VAL(str);
    size_t len = ZSTR_LEN(str);
    register size_t i;
    size_t trimmed = 0;
    char mask[256];

    if (what) {
        if (what_len == 1) {
            char p = *what;
            if (mode & 1) {
                for (i = 0; i < len; i++) {
                    if (c[i] == p) {
                        trimmed++;
                    } else {
                        break;
                    }
                }
                len -= trimmed;
                c += trimmed;
            }
            if (mode & 2) {
                if (len > 0) {
                    i = len - 1;
                    do {
                        if (c[i] == p) {
                            len--;
                        } else {
                            break;
                        }
                    } while (i-- != 0);
                }
            }
        } else {
            php_charmask((unsigned char*)what, what_len, mask);

            if (mode & 1) {
                for (i = 0; i < len; i++) {
                    if (mask[(unsigned char)c[i]]) {
                        trimmed++;
                    } else {
                        break;
                    }
                }
                len -= trimmed;
                c += trimmed;
            }
            if (mode & 2) {
                if (len > 0) {
                    i = len - 1;
                    do {
                        if (mask[(unsigned char)c[i]]) {
                            len--;
                        } else {
                            break;
                        }
                    } while (i-- != 0);
                }
            }
        }
    } else {
        if (mode & 1) {
            for (i = 0; i < len; i++) {
                if ((unsigned char)c[i] <= ' ' &&
                    (c[i] == ' ' || c[i] == '
' || c[i] == '
' || c[i] == '	' || c[i] == 'v' || c[i] == '')) {
                    trimmed++;
                } else {
                    break;
                }
            }
            len -= trimmed;
            c += trimmed;
        }
        if (mode & 2) {
            if (len > 0) {
                i = len - 1;
                do {
                    if ((unsigned char)c[i] <= ' ' &&
                        (c[i] == ' ' || c[i] == '
' || c[i] == '
' || c[i] == '	' || c[i] == 'v' || c[i] == '')) {
                        len--;
                    } else {
                        break;
                    }
                } while (i-- != 0);
            }
        }
    }

    if (ZSTR_LEN(str) == len) {
        return zend_string_copy(str);
    } else {
        return zend_string_init(c, len, 0);
    }
}
/* }}} */

ltrim()、rtrim() 或 trim()的参数二（what）存在时进入15行处的分支，参数二不存在时进入68行处的分支。

没有参数二时，会去除空格、" "、" "、" "、""、"v"

即：(unsigned char)c[i] <= ' ' && (c[i] == ' ' || c[i] == ' ' || c[i] == ' ' || c[i] == ' ' || c[i] == 'v' || c[i] == '')

存在参数二时，会去除参数二中指定的字符。

其中函数 php_charmask() 用于处理 trim("abc123456fjsklsf", "a..z") 中 字符范围 a...z

static inline int php_charmask(unsigned char *input, size_t len, char *mask)
{
    unsigned char *end;
    unsigned char c;
    int result = SUCCESS;

    memset(mask, 0, 256);
    for (end = input+len; input < end; input++) {
        c=*input;
        if ((input+3 < end) && input[1] == '.' && input[2] == '.'
                && input[3] >= c) {
            memset(mask+c, 1, input[3] - c + 1);
            input+=3;
        } else if ((input+1 < end) && input[0] == '.' && input[1] == '.') {
            /* Error, try to be as helpful as possible:
               (a range ending/starting with '.' won't be captured here) */
            if (end-len >= input) { /* there was no 'left' char */
                php_error_docref(NULL, E_WARNING, "Invalid '..'-range, no character to the left of '..'");
                result = FAILURE;
                continue;
            }
            if (input+2 >= end) { /* there is no 'right' char */
                php_error_docref(NULL, E_WARNING, "Invalid '..'-range, no character to the right of '..'");
                result = FAILURE;
                continue;
            }
            if (input[-1] > input[2]) { /* wrong order */
                php_error_docref(NULL, E_WARNING, "Invalid '..'-range, '..'-range needs to be incrementing");
                result = FAILURE;
                continue;
            }
            /* FIXME: better error (a..b..c is the only left possibility?) */
            php_error_docref(NULL, E_WARNING, "Invalid '..'-range");
            result = FAILURE;
            continue;
        } else {
            mask[c]=1;
        }
    }
    return result;
}

第二个参数是字符范围的时候，源码中并没有严格限制成 a..z 这样的格式。

总的流程就是，待处理的字符串左侧（或右侧）逐字符去匹配是否在将要去除的字符中（第二个参数设置的字符 或者 默认的那6个字符），

如果字符匹配到则进行下一个比较，否则中断匹配查找。返回余下字符串。