mod_include.c

apache简化版

/* ====================================================================
 * Copyright (c) 1995-1998 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/>.
 *
 */

/*
 * http_include.c: Handles the server-parsed HTML documents
 * 
 * Original by Rob McCool; substantial fixups by David Robinson;
 * incorporated into the Apache module framework by rst.
 * 
 */
/* 
 * sub key may be anything a Perl*Handler can be:
 * subroutine name, package name (defaults to package::handler),
 * Class->method call or anoymous sub {}
 *
 * Child <!--#perl sub="sub {print $$}" --> accessed
 * <!--#perl sub="sub {print ++$Access::Cnt }" --> times. <br>
 *
 * <!--#perl arg="one" sub="mymod::includer" -->
 *
 * -Doug MacEachern
 */

#ifdef USE_PERL_SSI
#include "config.h"
#undef VOIDUSED
#ifdef USE_SFIO
#undef USE_SFIO
#define USE_STDIO
#endif
#include "modules/perl/mod_perl.h"
#else
#include "httpd.h"
#include "http_config.h"
#include "http_request.h"
#include "http_core.h"
#include "http_protocol.h"
#include "http_log.h"
#include "http_main.h"
#include "util_script.h"
#endif

#define STARTING_SEQUENCE "<!--#"
#define ENDING_SEQUENCE "-->"
#define DEFAULT_ERROR_MSG "[an error occurred while processing this directive]"
#define DEFAULT_TIME_FORMAT "%A, %d-%b-%Y %H:%M:%S %Z"
#define SIZEFMT_BYTES 0
#define SIZEFMT_KMG 1
#ifdef CHARSET_EBCDIC
#define RAW_ASCII_CHAR(ch)  os_toebcdic[(unsigned char)ch]
#else /*CHARSET_EBCDIC*/
#define RAW_ASCII_CHAR(ch)  (ch)
#endif /*CHARSET_EBCDIC*/

module MODULE_VAR_EXPORT includes_module;

/* just need some arbitrary non-NULL pointer which can't also be a request_rec */
#define NESTED_INCLUDE_MAGIC	(&includes_module)

/* ------------------------ Environment function -------------------------- */

/* XXX: could use ap_table_overlap here */
static void add_include_vars(request_rec *r, char *timefmt)
{
#ifndef WIN32
    struct passwd *pw;
#endif /* ndef WIN32 */
    table *e = r->subprocess_env;
    char *t;
    time_t date = r->request_time;

    ap_table_setn(e, "DATE_LOCAL", ap_ht_time(r->pool, date, timefmt, 0));
    ap_table_setn(e, "DATE_GMT", ap_ht_time(r->pool, date, timefmt, 1));
    ap_table_setn(e, "LAST_MODIFIED",
              ap_ht_time(r->pool, r->finfo.st_mtime, timefmt, 0));
    ap_table_setn(e, "DOCUMENT_URI", r->uri);
    ap_table_setn(e, "DOCUMENT_PATH_INFO", r->path_info);
#ifndef WIN32
    pw = getpwuid(r->finfo.st_uid);
    if (pw) {
        ap_table_setn(e, "USER_NAME", ap_pstrdup(r->pool, pw->pw_name));
    }
    else {
        ap_table_setn(e, "USER_NAME", ap_psprintf(r->pool, "user#%lu",
                    (unsigned long) r->finfo.st_uid));
    }
#endif /* ndef WIN32 */

    if ((t = strrchr(r->filename, '/'))) {
        ap_table_setn(e, "DOCUMENT_NAME", ++t);
    }
    else {
        ap_table_setn(e, "DOCUMENT_NAME", r->uri);
    }
    if (r->args) {
        char *arg_copy = ap_pstrdup(r->pool, r->args);

        ap_unescape_url(arg_copy);
        ap_table_setn(e, "QUERY_STRING_UNESCAPED",
                  ap_escape_shell_cmd(r->pool, arg_copy));
    }
}



/* --------------------------- Parser functions --------------------------- */

#define OUTBUFSIZE 4096
/* PUT_CHAR and FLUSH_BUF currently only work within the scope of 
 * find_string(); they are hacks to avoid calling rputc for each and
 * every character output.  A common set of buffering calls for this 
 * type of output SHOULD be implemented.
 */
#define PUT_CHAR(c,r) \
 { \
    outbuf[outind++] = c; \
    if (outind == OUTBUFSIZE) { \
        FLUSH_BUF(r) \
    }; \
 }

/* there SHOULD be some error checking on the return value of
 * rwrite, however it is unclear what the API for rwrite returning
 * errors is and little can really be done to help the error in 
 * any case.
 */
#define FLUSH_BUF(r) \
 { \
   ap_rwrite(outbuf, outind, r); \
   outind = 0; \
 }

/*
 * f: file handle being read from
 * c: character to read into
 * ret: return value to use if input fails
 * r: current request_rec
 *
 * This macro is redefined after find_string() for historical reasons
 * to avoid too many code changes.  This is one of the many things
 * that should be fixed.
 */
#define GET_CHAR(f,c,ret,r) \
 { \
   int i = getc(f); \
   if (i == EOF) { /* either EOF or error -- needs error handling if latter */ \
       if (ferror(f)) { \
           fprintf(stderr, "encountered error in GET_CHAR macro, " \
                   "mod_include.\n"); \
       } \
       FLUSH_BUF(r); \
       ap_pfclose(r->pool, f); \
       return ret; \
   } \
   c = (char)i; \
 }

static int find_string(FILE *in, const char *str, request_rec *r, int printing)
{
    int x, l = strlen(str), p;
    char outbuf[OUTBUFSIZE];
    int outind = 0;
    char c;

    p = 0;
    while (1) {
        GET_CHAR(in, c, 1, r);
        if (c == str[p]) {
            if ((++p) == l) {
                FLUSH_BUF(r);
                return 0;
            }
        }
        else {
            if (printing) {
                for (x = 0; x < p; x++) {
                    PUT_CHAR(str[x], r);
                }
                PUT_CHAR(c, r);
            }
            p = 0;
        }
    }
}

#undef FLUSH_BUF
#undef PUT_CHAR
#undef GET_CHAR
#define GET_CHAR(f,c,r,p) \
 { \
   int i = getc(f); \
   if (i == EOF) { /* either EOF or error -- needs error handling if latter */ \
       if (ferror(f)) { \
           fprintf(stderr, "encountered error in GET_CHAR macro, " \
                   "mod_include.\n"); \
       } \
       ap_pfclose(p, f); \
       return r; \
   } \
   c = (char)i; \
 }

/*
 * decodes a string containing html entities or numeric character references.
 * 's' is overwritten with the decoded string.
 * If 's' is syntatically incorrect, then the followed fixups will be made:
 *   unknown entities will be left undecoded;
 *   references to unused numeric characters will be deleted.
 *   In particular, &#00; will not be decoded, but will be deleted.
 *
 * drtr
 */

/* maximum length of any ISO-LATIN-1 HTML entity name. */
#define MAXENTLEN (6)

/* The following is a shrinking transformation, therefore safe. */

static void decodehtml(char *s)
{
    int val, i, j;
    char *p = s;
    const char *ents;
    static const char * const entlist[MAXENTLEN + 1] =
    {
        NULL,                   /* 0 */
        NULL,                   /* 1 */
        "lt\074gt\076",         /* 2 */
        "amp\046ETH\320eth\360",        /* 3 */
        "quot\042Auml\304Euml\313Iuml\317Ouml\326Uuml\334auml\344euml\353\
iuml\357ouml\366uuml\374yuml\377",      /* 4 */
        "Acirc\302Aring\305AElig\306Ecirc\312Icirc\316Ocirc\324Ucirc\333\
THORN\336szlig\337acirc\342aring\345aelig\346ecirc\352icirc\356ocirc\364\
ucirc\373thorn\376",            /* 5 */
        "Agrave\300Aacute\301Atilde\303Ccedil\307Egrave\310Eacute\311\
Igrave\314Iacute\315Ntilde\321Ograve\322Oacute\323Otilde\325Oslash\330\
Ugrave\331Uacute\332Yacute\335agrave\340aacute\341atilde\343ccedil\347\
egrave\350eacute\351igrave\354iacute\355ntilde\361ograve\362oacute\363\
otilde\365oslash\370ugrave\371uacute\372yacute\375"     /* 6 */
    };

    for (; *s != '\0'; s++, p++) {
        if (*s != '&') {
            *p = *s;
            continue;
        }
        /* find end of entity */
        for (i = 1; s[i] != ';' && s[i] != '\0'; i++) {
            continue;
        }

        if (s[i] == '\0') {     /* treat as normal data */
            *p = *s;
            continue;
        }

        /* is it numeric ? */
        if (s[1] == '#') {
            for (j = 2, val = 0; j < i && ap_isdigit(s[j]); j++) {
                val = val * 10 + s[j] - '0';
            }
            s += i;
            if (j < i || val <= 8 || (val >= 11 && val <= 31) ||
                (val >= 127 && val <= 160) || val >= 256) {
                p--;            /* no data to output */
            }
            else {
                *p = RAW_ASCII_CHAR(val);
            }
        }
        else {
            j = i - 1;
            if (j > MAXENTLEN || entlist[j] == NULL) {
                /* wrong length */
                *p = '&';
                continue;       /* skip it */
            }
            for (ents = entlist[j]; *ents != '\0'; ents += i) {
                if (strncmp(s + 1, ents, j) == 0) {
                    break;
                }
            }

            if (*ents == '\0') {
                *p = '&';       /* unknown */
            }
            else {
                *p = RAW_ASCII_CHAR(((const unsigned char *) ents)[j]);
                s += i;
            }
        }
    }

    *p = '\0';
}

/*
 * extract the next tag name and value.
 * if there are no more tags, set the tag name to 'done'
 * the tag value is html decoded if dodecode is non-zero
 */

static char *get_tag(pool *p, FILE *in, char *tag, int tagbuf_len, int dodecode)
{
    char *t = tag, *tag_val, c, term;

    /* makes code below a little less cluttered */
    --tagbuf_len;

    do {                        /* skip whitespace */
        GET_CHAR(in, c, NULL, p);
    } while (ap_isspace(c));

    /* tags can't start with - */
    if (c == '-') {
        GET_CHAR(in, c, NULL, p);
        if (c == '-') {
            do {
                GET_CHAR(in, c, NULL, p);
            } while (ap_isspace(c));
            if (c == '>') {
                ap_cpystrn(tag, "done", tagbuf_len);
                return tag;
            }
        }
        return NULL;            /* failed */
    }

    /* find end of tag name */
    while (1) {
        if (t - tag == tagbuf_len) {
            *t = '\0';
            return NULL;
        }
        if (c == '=' || ap_isspace(c)) {
            break;
        }
        *(t++) = ap_tolower(c);
        GET_CHAR(in, c, NULL, p);
    }

    *t++ = '\0';
    tag_val = t;

    while (ap_isspace(c)) {
        GET_CHAR(in, c, NULL, p);       /* space before = */
    }
    if (c != '=') {
        ungetc(c, in);
        return NULL;
    }

    do {
        GET_CHAR(in, c, NULL, p);       /* space after = */
    } while (ap_isspace(c));

    /* we should allow a 'name' as a value */

    if (c != '"' && c != '\'') {
        return NULL;
    }
    term = c;
    while (1) {
        GET_CHAR(in, c, NULL, p);
        if (t - tag == tagbuf_len) {
            *t = '\0';
            return NULL;
        }
/* Want to accept \" as a valid character within a string. */
        if (c == '\\') {
            *(t++) = c;         /* Add backslash */
            GET_CHAR(in, c, NULL, p);