proxy_util.c

apache简化版

/* ====================================================================
 * Copyright (c) 1996-1998 The Apache Group.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer. 
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. All advertising materials mentioning features or use of this
 *    software must display the following acknowledgment:
 *    "This product includes software developed by the Apache Group
 *    for use in the Apache HTTP server project (http://www.apache.org/)."
 *
 * 4. The names "Apache Server" and "Apache Group" must not be used to
 *    endorse or promote products derived from this software without
 *    prior written permission. For written permission, please contact
 *    [e-mail].
 *
 * 5. Products derived from this software may not be called "Apache"
 *    nor may "Apache" appear in their names without prior written
 *    permission of the Apache Group.
 *
 * 6. Redistributions of any form whatsoever must retain the following
 *    acknowledgment:
 *    "This product includes software developed by the Apache Group
 *    for use in the Apache HTTP server project (http://www.apache.org/)."
 *
 * THIS SOFTWARE IS PROVIDED BY THE APACHE GROUP ``AS IS'' AND ANY
 * EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE APACHE GROUP OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
 * OF THE POSSIBILITY OF SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Group and was originally based
 * on public domain software written at the National Center for
 * Supercomputing Applications, University of Illinois, Urbana-Champaign.
 * For more information on the Apache Group and the Apache HTTP server
 * project, please see <http://www.apache.org/>.
 *
 */

/* 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);

/* already called in the knowledge that the characters are hex digits */
int ap_proxy_hex2c(const char *x)
{
    int i, ch;

#ifndef CHARSET_EBCDIC
    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 &= 0xFF;
    x[0] = '%';
    x[1] = ntoa[(os_toascii[ch]>>4)&0x0F];
    x[2] = ntoa[os_toascii[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, int 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 && ch == '%') {
	    if (!isxdigit(x[i + 1]) || !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, 1);
	    if (password == NULL)
		return "Bad %-escape in URL (password)";
	}

	user = ap_proxy_canonenc(p, user, strlen(user), enc_user, 1);
	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 || strp[i] != '\0')
	    return "Bad port number in URL";
	*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 */
#ifdef WIN32
    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";
    }

/*    if (strchr(host,'.') == NULL && domain != NULL)
   host = pstrcat(p, host, domain, NULL);
 */
    *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;
}


/* NOTE: This routine is taken from http_protocol::getline()
 * because the old code found in the proxy module was too
 * difficult to understand and maintain.
 */
/* Get a line of protocol input, including any continuation lines
 * caused by MIME folding (or broken clients) if fold != 0, and place it
 * in the buffer s, of size n bytes, without the ending newline.
 *
 * Returns -1 on error, or the length of s.
 *
 * Note: Because bgets uses 1 char for newline and 1 char for NUL,
 *       the most we can get is (n - 2) actual characters if it
 *       was ended by a newline, or (n - 1) characters if the line
 *       length exceeded (n - 1).  So, if the result == (n - 1),
 *       then the actual input line exceeded the buffer length,
 *       and it would be a good idea for the caller to puke 400 or 414.
 */
static int proxy_getline(char *s, int n, BUFF *in, int fold)
{
    char *pos, next;
    int retval;
    int total = 0;

    pos = s;

    do {
        retval = ap_bgets(pos, n, in);     /* retval == -1 if error, 0 if EOF */

        if (retval <= 0)
            return ((retval < 0) && (total == 0)) ? -1 : total;

        /* retval is the number of characters read, not including NUL      */

        n -= retval;            /* Keep track of how much of s is full     */
        pos += (retval - 1);    /* and where s ends                        */
        total += retval;        /* and how long s has become               */

        if (*pos == '\n') {     /* Did we get a full line of input?        */
            *pos = '\0';
            --total;
            ++n;
        }
        else
            return total;       /* if not, input line exceeded buffer size */

        /* Continue appending if line folding is desired and
         * the last line was not empty and we have room in the buffer and
         * the next line begins with a continuation character.
         */
    } while (fold && (retval != 1) && (n > 1)
                  && (ap_blookc(&next, in) == 1)
                  && ((next == ' ') || (next == '\t')));

    return total;
}


/*
 * 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.
 * @@@: XXX: FIXME: currently the headers are passed thru un-merged.