proxy_util.c

apache 安装教程 apache 安装教程

/* Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

/* Utility routines for Apache proxy */
#include "mod_proxy.h"
#include "http_main.h"
#include "ap_md5.h"
#include "multithread.h"
#include "http_log.h"
#include "util_uri.h"
#include "util_date.h"          /* get ap_checkmask() decl. */

static int proxy_match_ipaddr(struct dirconn_entry *This, request_rec *r);
static int proxy_match_domainname(struct dirconn_entry *This, request_rec *r);
static int proxy_match_hostname(struct dirconn_entry *This, request_rec *r);
static int proxy_match_word(struct dirconn_entry *This, request_rec *r);
static struct per_thread_data *get_per_thread_data(void);
/* already called in the knowledge that the characters are hex digits */
int ap_proxy_hex2c(const char *x)
{
    int i;
#ifndef CHARSET_EBCDIC
    int ch;

    ch = x[0];
    if (ap_isdigit(ch))
        i = ch - '0';
    else if (ap_isupper(ch))
        i = ch - ('A' - 10);
    else
        i = ch - ('a' - 10);
    i <<= 4;

    ch = x[1];
    if (ap_isdigit(ch))
        i += ch - '0';
    else if (ap_isupper(ch))
        i += ch - ('A' - 10);
    else
        i += ch - ('a' - 10);
    return i;
#else                           /* CHARSET_EBCDIC */
    return (1 == sscanf(x, "%2x", &i)) ? os_toebcdic[i & 0xFF] : 0;
#endif                          /* CHARSET_EBCDIC */
}

void ap_proxy_c2hex(int ch, char *x)
{
#ifndef CHARSET_EBCDIC
    int i;

    x[0] = '%';
    i = (ch & 0xF0) >> 4;
    if (i >= 10)
        x[1] = ('A' - 10) + i;
    else
        x[1] = '0' + i;

    i = ch & 0x0F;
    if (i >= 10)
        x[2] = ('A' - 10) + i;
    else
        x[2] = '0' + i;
#else                           /* CHARSET_EBCDIC */
    static const char ntoa[] = {"0123456789ABCDEF"};
    ch = os_toascii[ch & 0xFF];
    x[0] = '%';
    x[1] = ntoa[(ch >> 4) & 0x0F];
    x[2] = ntoa[ch & 0x0F];
    x[3] = '\0';
#endif                          /* CHARSET_EBCDIC */
}

/*
 * canonicalise a URL-encoded string
 */

/*
 * Convert a URL-encoded string to canonical form.
 * It decodes characters which need not be encoded,
 * and encodes those which must be encoded, and does not touch
 * those which must not be touched.
 */
char *ap_proxy_canonenc(pool *p, const char *x, int len, enum enctype t,
                             enum proxyreqtype isenc)
{
    int i, j, ch;
    char *y;
    const char *allowed;        /* characters which should not be encoded */
    const char *reserved;       /* characters which much not be en/de-coded */

/* N.B. in addition to :@&=, this allows ';' in an http path
 * and '?' in an ftp path -- this may be revised
 *
 * Also, it makes a '+' character in a search string reserved, as
 * it may be form-encoded. (Although RFC 1738 doesn't allow this -
 * it only permits ; / ? : @ = & as reserved chars.)
 */
    if (t == enc_path)
        allowed = "$-_.+!*'(),;:@&=";
    else if (t == enc_search)
        allowed = "$-_.!*'(),;:@&=";
    else if (t == enc_user)
        allowed = "$-_.+!*'(),;@&=";
    else if (t == enc_fpath)
        allowed = "$-_.+!*'(),?:@&=";
    else                        /* if (t == enc_parm) */
        allowed = "$-_.+!*'(),?/:@&=";

    if (t == enc_path)
        reserved = "/";
    else if (t == enc_search)
        reserved = "+";
    else
        reserved = "";

    y = ap_palloc(p, 3 * len + 1);

    for (i = 0, j = 0; i < len; i++, j++) {
/* always handle '/' first */
        ch = x[i];
        if (strchr(reserved, ch)) {
            y[j] = ch;
            continue;
        }
/* decode it if not already done */
        if (isenc != NOT_PROXY && ch == '%') {
            if (!ap_isxdigit(x[i + 1]) || !ap_isxdigit(x[i + 2]))
                return NULL;
            ch = ap_proxy_hex2c(&x[i + 1]);
            i += 2;
            if (ch != 0 && strchr(reserved, ch)) {      /* keep it encoded */
                ap_proxy_c2hex(ch, &y[j]);
                j += 2;
                continue;
            }
        }
/* recode it, if necessary */
        if (!ap_isalnum(ch) && !strchr(allowed, ch)) {
            ap_proxy_c2hex(ch, &y[j]);
            j += 2;
        }
        else
            y[j] = ch;
    }
    y[j] = '\0';
    return y;
}

/*
 * Parses network-location.
 *    urlp           on input the URL; on output the path, after the leading /
 *    user           NULL if no user/password permitted
 *    password       holder for password
 *    host           holder for host
 *    port           port number; only set if one is supplied.
 *
 * Returns an error string.
 */
char *
     ap_proxy_canon_netloc(pool *p, char **const urlp, char **userp,
                                char **passwordp, char **hostp, int *port)
{
    int i;
    char *strp, *host, *url = *urlp;
    char *user = NULL, *password = NULL;

    if (url[0] != '/' || url[1] != '/')
        return "Malformed URL";
    host = url + 2;
    url = strchr(host, '/');
    if (url == NULL)
        url = "";
    else
        *(url++) = '\0';        /* skip seperating '/' */

    /* find _last_ '@' since it might occur in user/password part */
    strp = strrchr(host, '@');

    if (strp != NULL) {
        *strp = '\0';
        user = host;
        host = strp + 1;

/* find password */
        strp = strchr(user, ':');
        if (strp != NULL) {
            *strp = '\0';
            password = ap_proxy_canonenc(p, strp + 1, strlen(strp + 1), enc_user, STD_PROXY);
            if (password == NULL)
                return "Bad %-escape in URL (password)";
        }

        user = ap_proxy_canonenc(p, user, strlen(user), enc_user, STD_PROXY);
        if (user == NULL)
            return "Bad %-escape in URL (username)";
    }
    if (userp != NULL) {
        *userp = user;
    }
    if (passwordp != NULL) {
        *passwordp = password;
    }

    strp = strrchr(host, ':');
    if (strp != NULL) {
        *(strp++) = '\0';

        for (i = 0; strp[i] != '\0'; i++)
            if (!ap_isdigit(strp[i]))
                break;

        /* if (i == 0) the no port was given; keep default */
        if (strp[i] != '\0') {
            return "Bad port number in URL";
        }
        else if (i > 0) {
            *port = atoi(strp);
            if (*port > 65535)
                return "Port number in URL > 65535";
        }
    }
    ap_str_tolower(host);       /* DNS names are case-insensitive */
    if (*host == '\0')
        return "Missing host in URL";
/* check hostname syntax */
    for (i = 0; host[i] != '\0'; i++)
        if (!ap_isdigit(host[i]) && host[i] != '.')
            break;
    /* must be an IP address */
#if defined(WIN32) || defined(NETWARE) || defined(TPF) || defined(BEOS)
    if (host[i] == '\0' && (inet_addr(host) == -1))
#else
    if (host[i] == '\0' && (ap_inet_addr(host) == -1 || inet_network(host) == -1))
#endif
    {
        return "Bad IP address in URL";
    }

    *urlp = url;
    *hostp = host;

    return NULL;
}

static const char *const lwday[7] =
{"Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"};

/*
 * If the date is a valid RFC 850 date or asctime() date, then it
 * is converted to the RFC 1123 format, otherwise it is not modified.
 * This routine is not very fast at doing conversions, as it uses
 * sscanf and sprintf. However, if the date is already correctly
 * formatted, then it exits very quickly.
 */
const char *
     ap_proxy_date_canon(pool *p, const char *x)
{
    int wk, mday, year, hour, min, sec, mon;
    char *q, month[4], zone[4], week[4];

    q = strchr(x, ',');
    /* check for RFC 850 date */
    if (q != NULL && q - x > 3 && q[1] == ' ') {
        *q = '\0';
        for (wk = 0; wk < 7; wk++)
            if (strcmp(x, lwday[wk]) == 0)
                break;
        *q = ',';
        if (wk == 7)
            return x;           /* not a valid date */
        if (q[4] != '-' || q[8] != '-' || q[11] != ' ' || q[14] != ':' ||
            q[17] != ':' || strcmp(&q[20], " GMT") != 0)
            return x;
        if (sscanf(q + 2, "%u-%3s-%u %u:%u:%u %3s", &mday, month, &year,
                   &hour, &min, &sec, zone) != 7)
            return x;
        if (year < 70)
            year += 2000;
        else
            year += 1900;
    }
    else {
/* check for acstime() date */
        if (x[3] != ' ' || x[7] != ' ' || x[10] != ' ' || x[13] != ':' ||
            x[16] != ':' || x[19] != ' ' || x[24] != '\0')
            return x;
        if (sscanf(x, "%3s %3s %u %u:%u:%u %u", week, month, &mday, &hour,
                   &min, &sec, &year) != 7)
            return x;
        for (wk = 0; wk < 7; wk++)
            if (strcmp(week, ap_day_snames[wk]) == 0)
                break;
        if (wk == 7)
            return x;
    }

/* check date */
    for (mon = 0; mon < 12; mon++)
        if (strcmp(month, ap_month_snames[mon]) == 0)
            break;
    if (mon == 12)
        return x;

    q = ap_palloc(p, 30);
    ap_snprintf(q, 30, "%s, %.2d %s %d %.2d:%.2d:%.2d GMT", ap_day_snames[wk], mday,
                ap_month_snames[mon], year, hour, min, sec);
    return q;
}


/*
 * Reads headers from a buffer and returns an array of headers.
 * Returns NULL on file error
 * This routine tries to deal with too long lines and continuation lines.
 *
 * Note: Currently the headers are passed through unmerged. This has to be
 * done so that headers which react badly to merging (such as Set-Cookie
 * headers, which contain commas within the date field) do not get stuffed
 * up.
 */
table *ap_proxy_read_headers(request_rec *r, char *buffer, int size, BUFF *f)
{
    table *resp_hdrs;
    int len;
    char *value, *end;
    char field[MAX_STRING_LEN];

    resp_hdrs = ap_make_table(r->pool, 20);

    /*
     * Read header lines until we get the empty separator line, a read error,
     * the connection closes (EOF), or we timeout.
     */
    while ((len = ap_getline(buffer, size, f, 1)) > 0) {

        if (!(value = strchr(buffer, ':'))) {   /* Find the colon separator */

            /*
             * Buggy MS IIS servers sometimes return invalid headers (an
             * extra "HTTP/1.0 200, OK" line sprinkled in between the usual
             * MIME headers). Try to deal with it in a sensible way, but log
             * the fact. XXX: The mask check is buggy if we ever see an
             * HTTP/1.10
             */

            if (!ap_checkmask(buffer, "HTTP/#.# ###*")) {
                /* Nope, it wasn't even an extra HTTP header. Give up. */
                return NULL;
            }

            ap_log_error(APLOG_MARK, APLOG_WARNING | APLOG_NOERRNO, r->server,
                         "proxy: Ignoring duplicate HTTP status line "
                         "returned by buggy server %s (%s)", r->uri, r->method);
            continue;
        }

        *value = '\0';
        ++value;
        /*
         * XXX: RFC2068 defines only SP and HT as whitespace, this test is
         * wrong... and so are many others probably.
         */
        while (ap_isspace(*value))
            ++value;            /* Skip to start of value   */

        /* should strip trailing whitespace as well */
        for (end = &value[strlen(value) - 1]; end > value && ap_isspace(*end); --end)
            *end = '\0';

        /* make sure we add so as not to destroy duplicated headers */
        ap_table_add(resp_hdrs, buffer, value);

        /* the header was too long; at the least we should skip extra data */
        if (len >= size - 1) {
            while ((len = ap_getline(field, MAX_STRING_LEN, f, 1))
                   >= MAX_STRING_LEN - 1) {
                /* soak up the extra data */
            }
            if (len == 0)       /* time to exit the larger loop as well */
                break;
        }
    }
    return resp_hdrs;
}

/* read data from (socket BUFF*) f, write it to:
 * - c->fp, if it is open
 * - r->connection->client, if nowrite == 0
 */

long int ap_proxy_send_fb(BUFF *f, request_rec *r, cache_req *c, off_t len, int nowrite, int chunked, size_t recv_buffer_size)
{
    int ok, end_of_chunk;
    char *buf;
    size_t buf_size;
    long remaining = 0;