ngx_string.c

Nginx是一个高性能的HTTP和反向代理服务器

        u &= 0x1f;
        valid = 0x7f;
        len = 1;

    } else {
        (*p)++;
        return 0xffffffff;
    }

    if (n - 1 < len) {
        return 0xfffffffe;
    }

    (*p)++;

    while (len) {
        i = *(*p)++;

        if (i < 0x80) {
            return 0xffffffff;
        }

        u = (u << 6) | (i & 0x3f);

        len--;
    }

    if (u > valid) {
        return u;
    }

    return 0xffffffff;
}


size_t
ngx_utf_length(u_char *p, size_t n)
{
    u_char      c;
    size_t      len;
    ngx_uint_t  i;

    for (len = 0, i = 0; i < n; len++, i++) {

        c = p[i];

        if (c < 0x80) {
            continue;
        }

        if (c >= 0xc0) {
            for (c <<= 1; c & 0x80; c <<= 1) {
                i++;
            }

            continue;
        }

        /* invalid utf */

        return n;
    }

    return len;
}


u_char *
ngx_utf_cpystrn(u_char *dst, u_char *src, size_t n)
{
    u_char  c;

    if (n == 0) {
        return dst;
    }

    for ( /* void */ ; --n; dst++, src++) {

        c = *src;
        *dst = c;

        if (c < 0x80) {
            if (*dst != '\0') {
                continue;
            }

            return dst;
        }

        if (c >= 0xc0) {
            for (c <<= 1; c & 0x80; c <<= 1) {
               *++dst = *++src;
            }

            continue;
        }

        /* invalid utf */
    }

    *dst = '\0';

    return dst;
}


uintptr_t
ngx_escape_uri(u_char *dst, u_char *src, size_t size, ngx_uint_t type)
{
    ngx_uint_t      i, n;
    uint32_t       *escape;
    static u_char   hex[] = "0123456789abcdef";

                    /* " ", "#", "%", "?", %00-%1F, %7F-%FF */

    static uint32_t   uri[] = {
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */

                    /* ?>=< ;:98 7654 3210  /.-, +*)( '&%$ #"!  */
        0x80000029, /* 1000 0000 0000 0000  0000 0000 0010 1001 */

                    /* _^]\ [ZYX WVUT SRQP  ONML KJIH GFED CBA@ */
        0x00000000, /* 0000 0000 0000 0000  0000 0000 0000 0000 */

                    /*  ~}| {zyx wvut srqp  onml kjih gfed cba` */
        0x80000000, /* 1000 0000 0000 0000  0000 0000 0000 0000 */

        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff  /* 1111 1111 1111 1111  1111 1111 1111 1111 */
    };

                    /* " ", "#", "%", "+", "?", %00-%1F, %7F-%FF */

    static uint32_t   args[] = {
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */

                    /* ?>=< ;:98 7654 3210  /.-, +*)( '&%$ #"!  */
        0x80000829, /* 1000 0000 0000 0000  0000 1000 0010 1001 */

                    /* _^]\ [ZYX WVUT SRQP  ONML KJIH GFED CBA@ */
        0x00000000, /* 0000 0000 0000 0000  0000 0000 0000 0000 */

                    /*  ~}| {zyx wvut srqp  onml kjih gfed cba` */
        0x80000000, /* 1000 0000 0000 0000  0000 0000 0000 0000 */

        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff  /* 1111 1111 1111 1111  1111 1111 1111 1111 */
    };

                    /* " ", "#", """, "%", "'", %00-%1F, %7F-%FF */

    static uint32_t   html[] = {
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */

                    /* ?>=< ;:98 7654 3210  /.-, +*)( '&%$ #"!  */
        0x000000ad, /* 0000 0000 0000 0000  0000 0000 1010 1101 */

                    /* _^]\ [ZYX WVUT SRQP  ONML KJIH GFED CBA@ */
        0x00000000, /* 0000 0000 0000 0000  0000 0000 0000 0000 */

                    /*  ~}| {zyx wvut srqp  onml kjih gfed cba` */
        0x80000000, /* 1000 0000 0000 0000  0000 0000 0000 0000 */

        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff  /* 1111 1111 1111 1111  1111 1111 1111 1111 */
    };

                    /* " ", """, "%", "'", %00-%1F, %7F-%FF */

    static uint32_t   refresh[] = {
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */

                    /* ?>=< ;:98 7654 3210  /.-, +*)( '&%$ #"!  */
        0x00000085, /* 0000 0000 0000 0000  0000 0000 1000 0101 */

                    /* _^]\ [ZYX WVUT SRQP  ONML KJIH GFED CBA@ */
        0x00000000, /* 0000 0000 0000 0000  0000 0000 0000 0000 */

                    /*  ~}| {zyx wvut srqp  onml kjih gfed cba` */
        0x80000000, /* 1000 0000 0000 0000  0000 0000 0000 0000 */

        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
        0xffffffff  /* 1111 1111 1111 1111  1111 1111 1111 1111 */
    };

                    /* " ", "%", %00-%1F */

    static uint32_t   memcached[] = {
        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */

                    /* ?>=< ;:98 7654 3210  /.-, +*)( '&%$ #"!  */
        0x00000021, /* 0000 0000 0000 0000  0000 0000 0010 0001 */

                    /* _^]\ [ZYX WVUT SRQP  ONML KJIH GFED CBA@ */
        0x00000000, /* 0000 0000 0000 0000  0000 0000 0000 0000 */

                    /*  ~}| {zyx wvut srqp  onml kjih gfed cba` */
        0x00000000, /* 0000 0000 0000 0000  0000 0000 0000 0000 */

        0x00000000, /* 0000 0000 0000 0000  0000 0000 0000 0000 */
        0x00000000, /* 0000 0000 0000 0000  0000 0000 0000 0000 */
        0x00000000, /* 0000 0000 0000 0000  0000 0000 0000 0000 */
        0x00000000, /* 0000 0000 0000 0000  0000 0000 0000 0000 */
    };

                    /* mail_auth is the same as memcached */

    static uint32_t  *map[] =
        { uri, args, html, refresh, memcached, memcached };


    escape = map[type];

    if (dst == NULL) {

        /* find the number of the characters to be escaped */

        n  = 0;

        for (i = 0; i < size; i++) {
            if (escape[*src >> 5] & (1 << (*src & 0x1f))) {
                n++;
            }
            src++;
        }

        return (uintptr_t) n;
    }

    for (i = 0; i < size; i++) {
        if (escape[*src >> 5] & (1 << (*src & 0x1f))) {
            *dst++ = '%';
            *dst++ = hex[*src >> 4];
            *dst++ = hex[*src & 0xf];
            src++;

        } else {
            *dst++ = *src++;
        }
    }

    return (uintptr_t) dst;
}


void
ngx_unescape_uri(u_char **dst, u_char **src, size_t size, ngx_uint_t type)
{
    u_char  *d, *s, ch, c, decoded;
    enum {
        sw_usual = 0,
        sw_quoted,
        sw_quoted_second
    } state;

    d = *dst;
    s = *src;

    state = 0;
    decoded = 0;

    while (size--) {

        ch = *s++;

        switch (state) {
        case sw_usual:
            if (ch == '?'
                && (type & (NGX_UNESCAPE_URI|NGX_UNESCAPE_REDIRECT)))
            {
                *d++ = ch;
                goto done;
            }

            if (ch == '%') {
                state = sw_quoted;
                break;
            }

            *d++ = ch;
            break;

        case sw_quoted:

            if (ch >= '0' && ch <= '9') {
                decoded = (u_char) (ch - '0');
                state = sw_quoted_second;
                break;
            }

            c = (u_char) (ch | 0x20);
            if (c >= 'a' && c <= 'f') {
                decoded = (u_char) (c - 'a' + 10);
                state = sw_quoted_second;
                break;
            }

            /* the invalid quoted character */

            state = sw_usual;

            *d++ = ch;

            break;

        case sw_quoted_second:

            state = sw_usual;

            if (ch >= '0' && ch <= '9') {
                ch = (u_char) ((decoded << 4) + ch - '0');

                if (type & NGX_UNESCAPE_REDIRECT) {
                    if (ch > '%' && ch < 0x7f) {
                        *d++ = ch;
                        break;
                    }

                    *d++ = '%'; *d++ = *(s - 2); *d++ = *(s - 1);

                    break;
                }

                *d++ = ch;

                break;
            }

            c = (u_char) (ch | 0x20);
            if (c >= 'a' && c <= 'f') {
                ch = (u_char) ((decoded << 4) + c - 'a' + 10);

                if (type & NGX_UNESCAPE_URI) {
                    if (ch == '?') {
                        *d++ = ch;
                        goto done;
                    }

                    *d++ = ch;
                    break;
                }

                if (type & NGX_UNESCAPE_REDIRECT) {
                    if (ch == '?') {
                        *d++ = ch;
                        goto done;
                    }

                    if (ch > '%' && ch < 0x7f) {
                        *d++ = ch;
                        break;
                    }

                    *d++ = '%'; *d++ = *(s - 2); *d++ = *(s - 1);
                    break;
                }

                *d++ = ch;

                break;
            }

            /* the invalid quoted character */

            break;
        }
    }

done:

    *dst = d;
    *src = s;
}


uintptr_t
ngx_escape_html(u_char *dst, u_char *src, size_t size)
{
    u_char      ch;
    ngx_uint_t  i, len;

    if (dst == NULL) {

        len = 0;

        for (i = 0; i < size; i++) {
            switch (*src++) {

            case '<':
                len += sizeof("&lt;") - 2;
                break;

            case '>':
                len += sizeof("&gt;") - 2;
                break;

            case '&':
                len += sizeof("&amp;") - 2;
                break;

            default:
                break;
            }
        }

        return (uintptr_t) len;
    }

    for (i = 0; i < size; i++) {
        ch = *src++;

        switch (ch) {

        case '<':
            *dst++ = '&'; *dst++ = 'l'; *dst++ = 't'; *dst++ = ';';
            break;

        case '>':
            *dst++ = '&'; *dst++ = 'g'; *dst++ = 't'; *dst++ = ';';
            break;

        case '&':
            *dst++ = '&'; *dst++ = 'a'; *dst++ = 'm'; *dst++ = 'p';
            *dst++ = ';';
            break;

        default:
            *dst++ = ch;
            break;
        }
    }

    return (uintptr_t) dst;
}


/* ngx_sort() is implemented as insertion sort because we need stable sort */

void
ngx_sort(void *base, size_t n, size_t size,
    ngx_int_t (*cmp)(const void *, const void *))
{
    u_char  *p1, *p2, *p;

    p = ngx_alloc(size, ngx_cycle->log);
    if (p == NULL) {
        return;
    }

    for (p1 = (u_char *) base + size;
         p1 < (u_char *) base + n * size;
         p1 += size)
    {
        ngx_memcpy(p, p1, size);

        for (p2 = p1;
             p2 > (u_char *) base && cmp(p2 - size, p) > 0;
             p2 -= size)
        {
            ngx_memcpy(p2, p2 - size, size);
        }

        ngx_memcpy(p2, p, size);
    }

    ngx_free(p);
}


#if (NGX_MEMCPY_LIMIT)

void *
ngx_memcpy(void *dst, void *src, size_t n)
{
    if (n > NGX_MEMCPY_LIMIT) {
        ngx_log_error(NGX_LOG_ALERT, ngx_cycle->log, 0, "memcpy %uz bytes", n);
        ngx_debug_point();
    }

    return memcpy(dst, src, n);
}

#endif