protocol.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。

/* Copyright 2001-2005 The Apache Software Foundation or its licensors, as
 * applicable.
 *
 * Licensed 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.
 */

/*
 * http_protocol.c --- routines which directly communicate with the client.
 *
 * Code originally by Rob McCool; much redone by Robert S. Thau
 * and the Apache Software Foundation.
 */

#include "apr.h"
#include "apr_strings.h"
#include "apr_buckets.h"
#include "apr_lib.h"
#include "apr_signal.h"
#include "apr_strmatch.h"

#define APR_WANT_STDIO          /* for sscanf */
#define APR_WANT_STRFUNC
#define APR_WANT_MEMFUNC
#include "apr_want.h"

#define CORE_PRIVATE
#include "util_filter.h"
#include "ap_config.h"
#include "httpd.h"
#include "http_config.h"
#include "http_core.h"
#include "http_protocol.h"
#include "http_main.h"
#include "http_request.h"
#include "http_vhost.h"
#include "http_log.h"           /* For errors detected in basic auth common
                                 * support code... */
#include "mod_core.h"
#include "util_charset.h"
#include "util_ebcdic.h"
#include "scoreboard.h"

#if APR_HAVE_STDARG_H
#include <stdarg.h>
#endif
#if APR_HAVE_UNISTD_H
#include <unistd.h>
#endif


APR_HOOK_STRUCT(
    APR_HOOK_LINK(post_read_request)
    APR_HOOK_LINK(log_transaction)
    APR_HOOK_LINK(http_method)
    APR_HOOK_LINK(default_port)
)

AP_DECLARE_DATA ap_filter_rec_t *ap_old_write_func = NULL;


/* Patterns to match in ap_make_content_type() */
static const char *needcset[] = {
    "text/plain",
    "text/html",
    NULL
};
static const apr_strmatch_pattern **needcset_patterns;
static const apr_strmatch_pattern *charset_pattern;

AP_DECLARE(void) ap_setup_make_content_type(apr_pool_t *pool)
{
    int i;
    for (i = 0; needcset[i]; i++) {
        continue;
    }
    needcset_patterns = (const apr_strmatch_pattern **)
        apr_palloc(pool, (i + 1) * sizeof(apr_strmatch_pattern *));
    for (i = 0; needcset[i]; i++) {
        needcset_patterns[i] = apr_strmatch_precompile(pool, needcset[i], 0);
    }
    needcset_patterns[i] = NULL;
    charset_pattern = apr_strmatch_precompile(pool, "charset=", 0);
}

/*
 * Builds the content-type that should be sent to the client from the
 * content-type specified.  The following rules are followed:
 *    - if type is NULL, type is set to ap_default_type(r)
 *    - if charset adding is disabled, stop processing and return type.
 *    - then, if there are no parameters on type, add the default charset
 *    - return type
 */
AP_DECLARE(const char *)ap_make_content_type(request_rec *r, const char *type)
{
    const apr_strmatch_pattern **pcset;
    core_dir_config *conf =
        (core_dir_config *)ap_get_module_config(r->per_dir_config,
                                                &core_module);
    apr_size_t type_len;

    if (!type) {
        type = ap_default_type(r);
    }

    if (conf->add_default_charset != ADD_DEFAULT_CHARSET_ON) {
        return type;
    }

    type_len = strlen(type);

    if (apr_strmatch(charset_pattern, type, type_len) != NULL) {
        /* already has parameter, do nothing */
        /* XXX we don't check the validity */
        ;
    }
    else {
        /* see if it makes sense to add the charset. At present,
         * we only add it if the Content-type is one of needcset[]
         */
        for (pcset = needcset_patterns; *pcset ; pcset++) {
            if (apr_strmatch(*pcset, type, type_len) != NULL) {
                struct iovec concat[3];
                concat[0].iov_base = (void *)type;
                concat[0].iov_len = type_len;
                concat[1].iov_base = (void *)"; charset=";
                concat[1].iov_len = sizeof("; charset=") - 1;
                concat[2].iov_base = (void *)(conf->add_default_charset_name);
                concat[2].iov_len = strlen(conf->add_default_charset_name);
                type = apr_pstrcatv(r->pool, concat, 3, NULL);
                break;
            }
        }
    }

    return type;
}

AP_DECLARE(void) ap_set_content_length(request_rec *r, apr_off_t clength)
{
    r->clength = clength;
    apr_table_setn(r->headers_out, "Content-Length",
                   apr_off_t_toa(r->pool, clength));
}

/*
 * Return the latest rational time from a request/mtime (modification time)
 * pair.  We return the mtime unless it's in the future, in which case we
 * return the current time.  We use the request time as a reference in order
 * to limit the number of calls to time().  We don't check for futurosity
 * unless the mtime is at least as new as the reference.
 */
AP_DECLARE(apr_time_t) ap_rationalize_mtime(request_rec *r, apr_time_t mtime)
{
    apr_time_t now;

    /* For all static responses, it's almost certain that the file was
     * last modified before the beginning of the request.  So there's
     * no reason to call time(NULL) again.  But if the response has been
     * created on demand, then it might be newer than the time the request
     * started.  In this event we really have to call time(NULL) again
     * so that we can give the clients the most accurate Last-Modified.  If we
     * were given a time in the future, we return the current time - the
     * Last-Modified can't be in the future.
     */
    now = (mtime < r->request_time) ? r->request_time : apr_time_now();
    return (mtime > now) ? now : mtime;
}

/* Min # of bytes to allocate when reading a request line */
#define MIN_LINE_ALLOC 80

/* 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.
 *
 * If s is NULL, ap_rgetline_core will allocate necessary memory from r->pool.
 *
 * Returns APR_SUCCESS if there are no problems and sets *read to be
 * the full length of s.
 *
 * APR_ENOSPC is returned if there is not enough buffer space.
 * Other errors may be returned on other errors.
 *
 * The LF is *not* returned in the buffer.  Therefore, a *read of 0
 * indicates that an empty line was read.
 *
 * Notes: Because the buffer uses 1 char for NUL, the most we can return is
 *        (n - 1) actual characters.
 *
 *        If no LF is detected on the last line due to a dropped connection
 *        or a full buffer, that's considered an error.
 */
AP_DECLARE(apr_status_t) ap_rgetline_core(char **s, apr_size_t n,
                                          apr_size_t *read, request_rec *r,
                                          int fold, apr_bucket_brigade *bb)
{
    apr_status_t rv;
    apr_bucket *e;
    apr_size_t bytes_handled = 0, current_alloc = 0;
    char *pos, *last_char = *s;
    int do_alloc = (*s == NULL), saw_eos = 0;

    for (;;) {
    apr_brigade_cleanup(bb);
    rv = ap_get_brigade(r->input_filters, bb, AP_MODE_GETLINE,
                        APR_BLOCK_READ, 0);

    if (rv != APR_SUCCESS) {
        return rv;
    }

    /* Something horribly wrong happened.  Someone didn't block! */
    if (APR_BRIGADE_EMPTY(bb)) {
        return APR_EGENERAL;
    }

    APR_BRIGADE_FOREACH(e, bb) {
        const char *str;
        apr_size_t len;

        /* If we see an EOS, don't bother doing anything more. */
        if (APR_BUCKET_IS_EOS(e)) {
            saw_eos = 1;
            break;
        }

        rv = apr_bucket_read(e, &str, &len, APR_BLOCK_READ);

        if (rv != APR_SUCCESS) {
            return rv;
        }

        if (len == 0) {
            /* no use attempting a zero-byte alloc (hurts when
             * using --with-efence --enable-pool-debug) or
             * doing any of the other logic either
             */
            continue;
        }

        /* Would this overrun our buffer?  If so, we'll die. */
        if (n < bytes_handled + len) {
            *read = bytes_handled;
            if (*s) {
                /* ensure this string is NUL terminated */
                if (bytes_handled > 0) {
                    (*s)[bytes_handled-1] = '\0';
                }
                else {
                    (*s)[0] = '\0';
                }
            }
            return APR_ENOSPC;
        }

        /* Do we have to handle the allocation ourselves? */
        if (do_alloc) {
            /* We'll assume the common case where one bucket is enough. */
            if (!*s) {
                current_alloc = len;
                if (current_alloc < MIN_LINE_ALLOC) {
                    current_alloc = MIN_LINE_ALLOC;
                }
                *s = apr_palloc(r->pool, current_alloc);
            }
            else if (bytes_handled + len > current_alloc) {
                /* Increase the buffer size */
                apr_size_t new_size = current_alloc * 2;
                char *new_buffer;

                if (bytes_handled + len > new_size) {
                    new_size = (bytes_handled + len) * 2;
                }

                new_buffer = apr_palloc(r->pool, new_size);

                /* Copy what we already had. */
                memcpy(new_buffer, *s, bytes_handled);
                current_alloc = new_size;
                *s = new_buffer;
            }
        }

        /* Just copy the rest of the data to the end of the old buffer. */
        pos = *s + bytes_handled;
        memcpy(pos, str, len);
        last_char = pos + len - 1;

        /* We've now processed that new data - update accordingly. */
        bytes_handled += len;
    }

        /* If we got a full line of input, stop reading */
        if (last_char && (*last_char == APR_ASCII_LF)) {
            break;
        }
    }

    /* Now NUL-terminate the string at the end of the line; 
     * if the last-but-one character is a CR, terminate there */
    if (last_char > *s && last_char[-1] == APR_ASCII_CR) {
        last_char--;
    }
    *last_char = '\0';
    bytes_handled = last_char - *s;

    /* If we're folding, we have more work to do.
     *
     * Note that if an EOS was seen, we know we can't have another line.
     */
    if (fold && bytes_handled && !saw_eos) {
        for (;;) {
        const char *str;
        apr_size_t len;
        char c;

        /* Clear the temp brigade for this filter read. */
        apr_brigade_cleanup(bb);

        /* We only care about the first byte. */
        rv = ap_get_brigade(r->input_filters, bb, AP_MODE_SPECULATIVE,
                            APR_BLOCK_READ, 1);

        if (rv != APR_SUCCESS) {
            return rv;
        }

        if (APR_BRIGADE_EMPTY(bb)) {
                break;
        }

        e = APR_BRIGADE_FIRST(bb);

        /* If we see an EOS, don't bother doing anything more. */
        if (APR_BUCKET_IS_EOS(e)) {
                break;
        }

        rv = apr_bucket_read(e, &str, &len, APR_BLOCK_READ);

        if (rv != APR_SUCCESS) {
                apr_brigade_cleanup(bb);
            return rv;
        }

        /* Found one, so call ourselves again to get the next line.
         *
         * FIXME: If the folding line is completely blank, should we
         * stop folding?  Does that require also looking at the next
         * char?
         */
            /* When we call destroy, the buckets are deleted, so save that
             * one character we need.  This simplifies our execution paths
             * at the cost of one character read.
             */
            c = *str;
        if (c == APR_ASCII_BLANK || c == APR_ASCII_TAB) {
            /* Do we have enough space? We may be full now. */
                if (bytes_handled >= n) {
                    *read = n;
                    /* ensure this string is terminated */
                    (*s)[n-1] = '\0';
                    return APR_ENOSPC;
                }
                else {
                apr_size_t next_size, next_len;
                char *tmp;

                /* If we're doing the allocations for them, we have to
                 * give ourselves a NULL and copy it on return.
                 */
                if (do_alloc) {
                    tmp = NULL;
                } else {
                    /* We're null terminated. */