mod_proxy.c

Apache官方在今天放出产品系列2.2的最新版本2.2.11的源码包 最流行的HTTP服务器软件之一

    }
    return NULL;
}

static int alias_match(const char *uri, const char *alias_fakename)
{
    const char *end_fakename = alias_fakename + strlen(alias_fakename);
    const char *aliasp = alias_fakename, *urip = uri;
    const char *end_uri = uri + strlen(uri);

    while (aliasp < end_fakename && urip < end_uri) {
        if (*aliasp == '/') {
            /* any number of '/' in the alias matches any number in
             * the supplied URI, but there must be at least one...
             */
            if (*urip != '/')
                return 0;

            while (*aliasp == '/')
                ++aliasp;
            while (*urip == '/')
                ++urip;
        }
        else {
            /* Other characters are compared literally */
            if (*urip++ != *aliasp++)
                return 0;
        }
    }

    /* fixup badly encoded stuff (e.g. % as last character) */
    if (aliasp > end_fakename) {
        aliasp = end_fakename;
    }
    if (urip > end_uri) {
        urip = end_uri;
    }

   /* We reach the end of the uri before the end of "alias_fakename"
    * for example uri is "/" and alias_fakename "/examples"
    */
   if (urip == end_uri && aliasp!=end_fakename) {
       return 0;
   }

    /* Check last alias path component matched all the way */
    if (aliasp[-1] != '/' && *urip != '\0' && *urip != '/')
        return 0;

    /* Return number of characters from URI which matched (may be
     * greater than length of alias, since we may have matched
     * doubled slashes)
     */

    return urip - uri;
}

/* Detect if an absoluteURI should be proxied or not.  Note that we
 * have to do this during this phase because later phases are
 * "short-circuiting"... i.e. translate_names will end when the first
 * module returns OK.  So for example, if the request is something like:
 *
 * GET http://othervhost/cgi-bin/printenv HTTP/1.0
 *
 * mod_alias will notice the /cgi-bin part and ScriptAlias it and
 * short-circuit the proxy... just because of the ordering in the
 * configuration file.
 */
static int proxy_detect(request_rec *r)
{
    void *sconf = r->server->module_config;
    proxy_server_conf *conf =
        (proxy_server_conf *) ap_get_module_config(sconf, &proxy_module);

    /* Ick... msvc (perhaps others) promotes ternary short results to int */

    if (conf->req && r->parsed_uri.scheme) {
        /* but it might be something vhosted */
        if (!(r->parsed_uri.hostname
              && !strcasecmp(r->parsed_uri.scheme, ap_http_scheme(r))
              && ap_matches_request_vhost(r, r->parsed_uri.hostname,
                                          (apr_port_t)(r->parsed_uri.port_str ? r->parsed_uri.port
                                                       : ap_default_port(r))))) {
            r->proxyreq = PROXYREQ_PROXY;
            r->uri = r->unparsed_uri;
            r->filename = apr_pstrcat(r->pool, "proxy:", r->uri, NULL);
            r->handler = "proxy-server";
        }
    }
    /* We need special treatment for CONNECT proxying: it has no scheme part */
    else if (conf->req && r->method_number == M_CONNECT
             && r->parsed_uri.hostname
             && r->parsed_uri.port_str) {
        r->proxyreq = PROXYREQ_PROXY;
        r->uri = r->unparsed_uri;
        r->filename = apr_pstrcat(r->pool, "proxy:", r->uri, NULL);
        r->handler = "proxy-server";
    }
    return DECLINED;
}

static const char *proxy_interpolate(request_rec *r, const char *str)
{
    /* Interpolate an env str in a configuration string
     * Syntax ${var} --> value_of(var)
     * Method: replace one var, and recurse on remainder of string
     * Nothing clever here, and crap like nested vars may do silly things
     * but we'll at least avoid sending the unwary into a loop
     */
    const char *start;
    const char *end;
    const char *var;
    const char *val;
    const char *firstpart;

    start = ap_strstr_c(str, "${");
    if (start == NULL) {
        return str;
    }
    end = ap_strchr_c(start+2, '}');
    if (end == NULL) {
        return str;
    }
    /* OK, this is syntax we want to interpolate.  Is there such a var ? */
    var = apr_pstrndup(r->pool, start+2, end-(start+2));
    val = apr_table_get(r->subprocess_env, var);
    firstpart = apr_pstrndup(r->pool, str, (start-str));

    if (val == NULL) {
        return apr_pstrcat(r->pool, firstpart,
                           proxy_interpolate(r, end+1), NULL);
    }
    else {
        return apr_pstrcat(r->pool, firstpart, val,
                           proxy_interpolate(r, end+1), NULL);
    }
}
static apr_array_header_t *proxy_vars(request_rec *r,
                                      apr_array_header_t *hdr)
{
    int i;
    apr_array_header_t *ret = apr_array_make(r->pool, hdr->nelts,
                                             sizeof (struct proxy_alias));
    struct proxy_alias *old = (struct proxy_alias *) hdr->elts;

    for (i = 0; i < hdr->nelts; ++i) {
        struct proxy_alias *newcopy = apr_array_push(ret);
        newcopy->fake = (old[i].flags & PROXYPASS_INTERPOLATE)
                        ? proxy_interpolate(r, old[i].fake) : old[i].fake;
        newcopy->real = (old[i].flags & PROXYPASS_INTERPOLATE)
                        ? proxy_interpolate(r, old[i].real) : old[i].real;
    }
    return ret;
}
static int proxy_trans(request_rec *r)
{
    void *sconf = r->server->module_config;
    proxy_server_conf *conf =
    (proxy_server_conf *) ap_get_module_config(sconf, &proxy_module);
    int i, len;
    struct proxy_alias *ent = (struct proxy_alias *) conf->aliases->elts;
    proxy_dir_conf *dconf = ap_get_module_config(r->per_dir_config,
                                                 &proxy_module);
    const char *fake;
    const char *real;
    ap_regmatch_t regm[AP_MAX_REG_MATCH];
    ap_regmatch_t reg1[AP_MAX_REG_MATCH];
    char *found = NULL;
    int mismatch = 0;

    if (r->proxyreq) {
        /* someone has already set up the proxy, it was possibly ourselves
         * in proxy_detect
         */
        return OK;
    }

    /* XXX: since r->uri has been manipulated already we're not really
     * compliant with RFC1945 at this point.  But this probably isn't
     * an issue because this is a hybrid proxy/origin server.
     */

    for (i = 0; i < conf->aliases->nelts; i++) {
        unsigned int nocanon = ent[i].flags & PROXYPASS_NOCANON;
        const char *use_uri = nocanon ? r->unparsed_uri : r->uri;
        if ((dconf->interpolate_env == 1)
            && (ent[i].flags & PROXYPASS_INTERPOLATE)) {
            fake = proxy_interpolate(r, ent[i].fake);
            real = proxy_interpolate(r, ent[i].real);
        }
        else {
            fake = ent[i].fake;
            real = ent[i].real;
        }
        if (ent[i].regex) {
            if (!ap_regexec(ent[i].regex, r->uri, AP_MAX_REG_MATCH, regm, 0)) {
                if ((real[0] == '!') && (real[1] == '\0')) {
                    return DECLINED;
                }
                /* test that we haven't reduced the URI */
                if (nocanon && ap_regexec(ent[i].regex, r->unparsed_uri,
                                          AP_MAX_REG_MATCH, reg1, 0)) {
                    mismatch = 1;
                    use_uri = r->uri;
                }
                found = ap_pregsub(r->pool, real, use_uri, AP_MAX_REG_MATCH,
                                   (use_uri == r->uri) ? regm : reg1);
                /* Note: The strcmp() below catches cases where there
                 * was no regex substitution. This is so cases like:
                 *
                 *    ProxyPassMatch \.gif balancer://foo
                 *
                 * will work "as expected". The upshot is that the 2
                 * directives below act the exact same way (ie: $1 is implied):
                 *
                 *    ProxyPassMatch ^(/.*\.gif)$ balancer://foo
                 *    ProxyPassMatch ^(/.*\.gif)$ balancer://foo$1
                 *
                 * which may be confusing.
                 */
                if (found && strcmp(found, real)) {
                    found = apr_pstrcat(r->pool, "proxy:", found, NULL);
                }
                else {
                    found = apr_pstrcat(r->pool, "proxy:", real,
                                        use_uri, NULL);
                }
            }
        }
        else {
            len = alias_match(r->uri, fake);

            if (len != 0) {
                if ((real[0] == '!') && (real[1] == '\0')) {
                    return DECLINED;
                }
                if (nocanon
                    && len != alias_match(r->unparsed_uri, ent[i].fake)) {
                    mismatch = 1;
                    use_uri = r->uri;
                }
                found = apr_pstrcat(r->pool, "proxy:", real,
                                    use_uri + len, NULL);
            }
        }
        if (mismatch) {
            /* We made a reducing transformation, so we can't safely use
             * unparsed_uri.  Safe fallback is to ignore nocanon.
             */
            ap_log_rerror(APLOG_MARK, APLOG_WARNING, 0, r,
                          "Unescaped URL path matched ProxyPass; ignoring unsafe nocanon");
        }

        if (found) {
            r->filename = found;
            r->handler = "proxy-server";
            r->proxyreq = PROXYREQ_REVERSE;
            if (nocanon && !mismatch) {
                /* mod_proxy_http needs to be told.  Different module. */
                apr_table_setn(r->notes, "proxy-nocanon", "1");
            }
            return OK;
        }
    }
    return DECLINED;
}

static int proxy_walk(request_rec *r)
{
    proxy_server_conf *sconf = ap_get_module_config(r->server->module_config,
                                                    &proxy_module);
    ap_conf_vector_t *per_dir_defaults = r->server->lookup_defaults;
    ap_conf_vector_t **sec_proxy = (ap_conf_vector_t **) sconf->sec_proxy->elts;
    ap_conf_vector_t *entry_config;
    proxy_dir_conf *entry_proxy;
    int num_sec = sconf->sec_proxy->nelts;
    /* XXX: shouldn't we use URI here?  Canonicalize it first?
     * Pass over "proxy:" prefix
     */
    const char *proxyname = r->filename + 6;
    int j;

    for (j = 0; j < num_sec; ++j)
    {
        entry_config = sec_proxy[j];
        entry_proxy = ap_get_module_config(entry_config, &proxy_module);

        /* XXX: What about case insensitive matching ???
         * Compare regex, fnmatch or string as appropriate
         * If the entry doesn't relate, then continue
         */
        if (entry_proxy->r
              ? ap_regexec(entry_proxy->r, proxyname, 0, NULL, 0)
              : (entry_proxy->p_is_fnmatch
                   ? apr_fnmatch(entry_proxy->p, proxyname, 0)
                   : strncmp(proxyname, entry_proxy->p,
                                        strlen(entry_proxy->p)))) {
            continue;
        }
        per_dir_defaults = ap_merge_per_dir_configs(r->pool, per_dir_defaults,
                                                             entry_config);
    }

    r->per_dir_config = per_dir_defaults;

    return OK;
}

static int proxy_map_location(request_rec *r)
{
    int access_status;

    if (!r->proxyreq || !r->filename || strncmp(r->filename, "proxy:", 6) != 0)
        return DECLINED;

    /* Don't let the core or mod_http map_to_storage hooks handle this,
     * We don't need directory/file_walk, and we want to TRACE on our own.
     */
    if ((access_status = proxy_walk(r))) {
        ap_die(access_status, r);
        return access_status;
    }

    return OK;
}

/* -------------------------------------------------------------- */
/* Fixup the filename */

/*
 * Canonicalise the URL
 */
static int proxy_fixup(request_rec *r)
{
    char *url, *p;
    int access_status;
    proxy_dir_conf *dconf = ap_get_module_config(r->per_dir_config,
                                                 &proxy_module);

    if (!r->proxyreq || !r->filename || strncmp(r->filename, "proxy:", 6) != 0)
        return DECLINED;

    /* XXX: Shouldn't we try this before we run the proxy_walk? */
    url = &r->filename[6];

    if ((dconf->interpolate_env == 1) && (r->proxyreq == PROXYREQ_REVERSE)) {
        /* create per-request copy of reverse proxy conf,
         * and interpolate vars in it
         */
        proxy_req_conf *rconf = apr_palloc(r->pool, sizeof(proxy_req_conf));
        ap_set_module_config(r->request_config, &proxy_module, rconf);
        rconf->raliases = proxy_vars(r, dconf->raliases);
        rconf->cookie_paths = proxy_vars(r, dconf->cookie_paths);
        rconf->cookie_domains = proxy_vars(r, dconf->cookie_domains);
    }

    /* canonicalise each specific scheme */
    if ((access_status = proxy_run_canon_handler(r, url))) {
        return access_status;
    }

    p = strchr(url, ':');
    if (p == NULL || p == url)
        return HTTP_BAD_REQUEST;

    return OK;      /* otherwise; we've done the best we can */
}
/* Send a redirection if the request contains a hostname which is not */
/* fully qualified, i.e. doesn't have a domain name appended. Some proxy */