request.c

Apache HTTP Server 是一个功能强大的灵活的与HTTP/1.1相兼容的web服务器.这里给出的是Apache HTTP服务器的源码。

        if ((res = apr_stat(&fi, d, lfi->valid & ~(APR_FINFO_NAME 
                                                 | APR_FINFO_LINK), p)) 
                 != APR_SUCCESS) {
            return HTTP_FORBIDDEN;
        }

        /* Give back the target */
        memcpy(lfi, &fi, sizeof(fi));
        if (savename) {
            lfi->name = savename;
            lfi->valid |= APR_FINFO_NAME;
        }

        return OK;
    }

    /* OPT_SYM_OWNER only works if we can get the owner of
     * both the file and symlink.  First fill in a missing
     * owner of the symlink, then get the info of the target.
     */
    if (!(lfi->valid & APR_FINFO_OWNER)) {
        if ((res = apr_lstat(&fi, d, lfi->valid | APR_FINFO_OWNER, p))
            != APR_SUCCESS) {
            return HTTP_FORBIDDEN;
        }
    }

    if ((res = apr_stat(&fi, d, lfi->valid & ~(APR_FINFO_NAME), p))
        != APR_SUCCESS) {
        return HTTP_FORBIDDEN;
    }

    if (apr_compare_users(fi.user, lfi->user) != APR_SUCCESS) {
        return HTTP_FORBIDDEN;
    }

    /* Give back the target */
    memcpy(lfi, &fi, sizeof(fi));
    if (savename) {
        lfi->name = savename;
        lfi->valid |= APR_FINFO_NAME;
    }

    return OK;
}


/*
 * As we walk the directory configuration, the merged config won't
 * be 'rooted' to a specific vhost until the very end of the merge.
 *
 * We need a very fast mini-merge to a real, vhost-rooted merge
 * of core.opts and core.override, the only options tested within
 * directory_walk itself.
 *
 * See core.c::merge_core_dir_configs() for explanation.
 */

typedef struct core_opts_t {
        allow_options_t opts;
        allow_options_t add;
        allow_options_t remove;
        overrides_t override;
} core_opts_t;

static void core_opts_merge(const ap_conf_vector_t *sec, core_opts_t *opts)
{
    core_dir_config *this_dir = ap_get_module_config(sec, &core_module);

    if (!this_dir) {
        return;
    }

    if (this_dir->opts & OPT_UNSET) {
        opts->add = (opts->add & ~this_dir->opts_remove)
                   | this_dir->opts_add;
        opts->remove = (opts->remove & ~this_dir->opts_add)
                      | this_dir->opts_remove;
        opts->opts = (opts->opts & ~opts->remove) | opts->add;
    }
    else {
        opts->opts = this_dir->opts;
        opts->add = this_dir->opts_add;
        opts->remove = this_dir->opts_remove;
    }

    if (!(this_dir->override & OR_UNSET)) {
        opts->override = this_dir->override;
    }
}


/*****************************************************************
 *
 * Getting and checking directory configuration.  Also checks the
 * FollowSymlinks and FollowSymOwner stuff, since this is really the
 * only place that can happen (barring a new mid_dir_walk callout).
 *
 * We can't do it as an access_checker module function which gets
 * called with the final per_dir_config, since we could have a directory
 * with FollowSymLinks disabled, which contains a symlink to another
 * with a .htaccess file which turns FollowSymLinks back on --- and
 * access in such a case must be denied.  So, whatever it is that
 * checks FollowSymLinks needs to know the state of the options as
 * they change, all the way down.
 */

AP_DECLARE(int) ap_directory_walk(request_rec *r)
{
    ap_conf_vector_t *now_merged = NULL;
    core_server_config *sconf = ap_get_module_config(r->server->module_config,
                                                     &core_module);
    ap_conf_vector_t **sec_ent = (ap_conf_vector_t **) sconf->sec_dir->elts;
    int num_sec = sconf->sec_dir->nelts;
    walk_cache_t *cache;
    char *entry_dir;
    apr_status_t rv;

    /* XXX: Better (faster) tests needed!!!
     *
     * "OK" as a response to a real problem is not _OK_, but to allow broken
     * modules to proceed, we will permit the not-a-path filename to pass the
     * following two tests.  This behavior may be revoked in future versions
     * of Apache.  We still must catch it later if it's heading for the core
     * handler.  Leave INFO notes here for module debugging.
     */
    if (r->filename == NULL) {
        ap_log_rerror(APLOG_MARK, APLOG_INFO, 0, r,
                      "Module bug?  Request filename is missing for URI %s",
                      r->uri);
       return OK;
    }

    /* Canonicalize the file path without resolving filename case or aliases
     * so we can begin by checking the cache for a recent directory walk.
     * This call will ensure we have an absolute path in the same pass.
     */
    if ((rv = apr_filepath_merge(&entry_dir, NULL, r->filename,
                                 APR_FILEPATH_NOTRELATIVE, r->pool))
                  != APR_SUCCESS) {
        ap_log_rerror(APLOG_MARK, APLOG_INFO, 0, r,
                      "Module bug?  Request filename path %s is invalid or "
                      "or not absolute for uri %s",
                      r->filename, r->uri);
        return OK;
    }

    /* XXX Notice that this forces path_info to be canonical.  That might
     * not be desired by all apps.  However, some of those same apps likely
     * have significant security holes.
     */
    r->filename = entry_dir;

    cache = prep_walk_cache(AP_NOTE_DIRECTORY_WALK, r);

    /* If this is not a dirent subrequest with a preconstructed
     * r->finfo value, then we can simply stat the filename to
     * save burning mega-cycles with unneeded stats - if this is
     * an exact file match.  We don't care about failure... we
     * will stat by component failing this meager attempt.
     *
     * It would be nice to distinguish APR_ENOENT from other
     * types of failure, such as APR_ENOTDIR.  We can do something
     * with APR_ENOENT, knowing that the path is good.
     */
    if (!r->finfo.filetype || r->finfo.filetype == APR_LNK) {
        rv = apr_stat(&r->finfo, r->filename, APR_FINFO_MIN, r->pool);

        /* some OSs will return APR_SUCCESS/APR_REG if we stat
         * a regular file but we have '/' at the end of the name;
         *
         * other OSs will return APR_ENOTDIR for that situation;
         *
         * handle it the same everywhere by simulating a failure
         * if it looks like a directory but really isn't
         *
         * Also reset if the stat failed, just for safety.
         */
        if ((rv != APR_SUCCESS) ||
            (r->finfo.filetype &&
             (r->finfo.filetype != APR_DIR) &&
             (r->filename[strlen(r->filename) - 1] == '/'))) {
             r->finfo.filetype = 0; /* forget what we learned */
        }
    }

    if (r->finfo.filetype == APR_REG) {
        entry_dir = ap_make_dirstr_parent(r->pool, entry_dir);
    }
    else if (r->filename[strlen(r->filename) - 1] != '/') {
        entry_dir = apr_pstrcat(r->pool, r->filename, "/", NULL);
    }

    /* If we have a file already matches the path of r->filename,
     * and the vhost's list of directory sections hasn't changed,
     * we can skip rewalking the directory_walk entries.
     */
    if (cache->cached
        && ((r->finfo.filetype == APR_REG)
            || ((r->finfo.filetype == APR_DIR)
                && (!r->path_info || !*r->path_info)))
        && (cache->dir_conf_tested == sec_ent)
        && (strcmp(entry_dir, cache->cached) == 0)) {
        /* Well this looks really familiar!  If our end-result (per_dir_result)
         * didn't change, we have absolutely nothing to do :)
         * Otherwise (as is the case with most dir_merged/file_merged requests)
         * we must merge our dir_conf_merged onto this new r->per_dir_config.
         */
        if (r->per_dir_config == cache->per_dir_result) {
            return OK;
        }

        if (r->per_dir_config == cache->dir_conf_merged) {
            r->per_dir_config = cache->per_dir_result;
            return OK;
        }

        if (cache->walked->nelts) {
            now_merged = ((walk_walked_t*)cache->walked->elts)
                [cache->walked->nelts - 1].merged;
        }
    }
    else {
        /* We start now_merged from NULL since we want to build
         * a locations list that can be merged to any vhost.
         */
        int sec_idx;
        int matches = cache->walked->nelts;
        walk_walked_t *last_walk = (walk_walked_t*)cache->walked->elts;
        core_dir_config *this_dir;
        core_opts_t opts;
        apr_finfo_t thisinfo;
        char *save_path_info;
        apr_size_t buflen;
        char *buf;
        unsigned int seg, startseg;

        /* Invariant: from the first time filename_len is set until
         * it goes out of scope, filename_len==strlen(r->filename)
         */
        apr_size_t filename_len;
#ifdef CASE_BLIND_FILESYSTEM
        apr_size_t canonical_len;
#endif

        /*
         * We must play our own mini-merge game here, for the few
         * running dir_config values we care about within dir_walk.
         * We didn't start the merge from r->per_dir_config, so we
         * accumulate opts and override as we merge, from the globals.
         */
        this_dir = ap_get_module_config(r->per_dir_config, &core_module);
        opts.opts = this_dir->opts;
        opts.add = this_dir->opts_add;
        opts.remove = this_dir->opts_remove;
        opts.override = this_dir->override;

        /* Set aside path_info to merge back onto path_info later.
         * If r->filename is a directory, we must remerge the path_info,
         * before we continue!  [Directories cannot, by defintion, have
         * path info.  Either the next segment is not-found, or a file.]
         *
         * r->path_info tracks the unconsumed source path.
         * r->filename  tracks the path as we process it
         */
        if ((r->finfo.filetype == APR_DIR) && r->path_info && *r->path_info)
        {
            if ((rv = apr_filepath_merge(&r->path_info, r->filename,
                                         r->path_info,
                                         APR_FILEPATH_NOTABOVEROOT, r->pool))
                != APR_SUCCESS) {
                ap_log_rerror(APLOG_MARK, APLOG_ERR, rv, r,
                              "dir_walk error, path_info %s is not relative "
                              "to the filename path %s for uri %s",
                              r->path_info, r->filename, r->uri);
                return HTTP_INTERNAL_SERVER_ERROR;
            }

            save_path_info = NULL;
        }
        else {
            save_path_info = r->path_info;
            r->path_info = r->filename;
        }

#ifdef CASE_BLIND_FILESYSTEM

        canonical_len = 0;
        while (r->canonical_filename && r->canonical_filename[canonical_len]
               && (r->canonical_filename[canonical_len]
                   == r->path_info[canonical_len])) {
             ++canonical_len;
        }

        while (canonical_len
               && ((r->canonical_filename[canonical_len - 1] != '/'
                   && r->canonical_filename[canonical_len - 1])
                   || (r->path_info[canonical_len - 1] != '/'
                       && r->path_info[canonical_len - 1]))) {
            --canonical_len;
        }

        /*
         * Now build r->filename component by component, starting
         * with the root (on Unix, simply "/").  We will make a huge
         * assumption here for efficiency, that any canonical path
         * already given included a canonical root.
         */
        rv = apr_filepath_root((const char **)&r->filename,
                               (const char **)&r->path_info,
                               canonical_len ? 0 : APR_FILEPATH_TRUENAME,
                               r->pool);
        filename_len = strlen(r->filename);

        /*
         * Bad assumption above?  If the root's length is longer
         * than the canonical length, then it cannot be trusted as
         * a truename.  So try again, this time more seriously.
         */
        if ((rv == APR_SUCCESS) && canonical_len
            && (filename_len > canonical_len)) {
            rv = apr_filepath_root((const char **)&r->filename,
                                   (const char **)&r->path_info,
                                   APR_FILEPATH_TRUENAME, r->pool);
            filename_len = strlen(r->filename);
            canonical_len = 0;
        }

#else /* ndef CASE_BLIND_FILESYSTEM, really this simple for Unix today; */

        rv = apr_filepath_root((const char **)&r->filename,
                               (const char **)&r->path_info,
                               0, r->pool);
        filename_len = strlen(r->filename);

#endif

        if (rv != APR_SUCCESS) {
            ap_log_rerror(APLOG_MARK, APLOG_ERR, rv, r,
                          "dir_walk error, could not determine the root "
                          "path of filename %s%s for uri %s",
                          r->filename, r->path_info, r->uri);
            return HTTP_INTERNAL_SERVER_ERROR;
        }

        /* Working space for terminating null and an extra / is required.
         */
        buflen = filename_len + strlen(r->path_info) + 2;
        buf = apr_palloc(r->pool, buflen);
        memcpy(buf, r->filename, filename_len + 1);
        r->filename = buf;
        thisinfo.valid = APR_FINFO_TYPE;
        thisinfo.filetype = APR_DIR; /* It's the root, of course it's a dir */

        /*
         * seg keeps track of which segment we've copied.
         * sec_idx keeps track of which section we're on, since sections are