url_scanner_ex.c

php-4.4.7学习linux时下载的源代码

/* Generated by re2c 0.9.11 on Tue Feb 28 09:46:35 2006 */
/*
  +----------------------------------------------------------------------+
  | PHP Version 4                                                        |
  +----------------------------------------------------------------------+
  | Copyright (c) 1997-2007 The PHP Group                                |
  +----------------------------------------------------------------------+
  | This source file is subject to version 3.01 of the PHP license,      |
  | that is bundled with this package in the file LICENSE, and is        |
  | available through the world-wide-web at the following url:           |
  | http://www.php.net/license/3_01.txt                                  |
  | If you did not receive a copy of the PHP license and are unable to   |
  | obtain it through the world-wide-web, please send a note to          |
  | [e-mail] so we can mail you a copy immediately.               |
  +----------------------------------------------------------------------+
  | Author: Sascha Schumann <[e-mail]>                         |
  +----------------------------------------------------------------------+
*/

/* $Id: url_scanner_ex.c,v 1.72.2.15.2.6 2007/01/01 09:46:48 sebastian Exp $ */

#include "php.h"

#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#ifdef HAVE_LIMITS_H
#include <limits.h>
#endif

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include "php_ini.h"
#include "php_globals.h"
#define STATE_TAG SOME_OTHER_STATE_TAG
#include "basic_functions.h"
#include "url.h"
#undef STATE_TAG

#define url_scanner url_scanner_ex

#include "php_smart_str.h"

static PHP_INI_MH(OnUpdateTags)
{
	url_adapt_state_ex_t *ctx;
	char *key;
	char *lasts;
	char *tmp;
	
	ctx = &BG(url_adapt_state_ex);
	
	tmp = estrndup(new_value, new_value_length);
	
	if (ctx->tags)
		zend_hash_destroy(ctx->tags);
	else
		ctx->tags = malloc(sizeof(HashTable));
	
	zend_hash_init(ctx->tags, 0, NULL, NULL, 1);
	
	for (key = php_strtok_r(tmp, ",", &lasts);
			key;
			key = php_strtok_r(NULL, ",", &lasts)) {
		char *val;

		val = strchr(key, '=');
		if (val) {
			char *q;
			int keylen;
			
			*val++ = '\0';
			for (q = key; *q; q++)
				*q = tolower(*q);
			keylen = q - key;
			/* key is stored withOUT NUL
			   val is stored WITH    NUL */
			zend_hash_add(ctx->tags, key, keylen, val, strlen(val)+1, NULL);
		}
	}

	efree(tmp);

	return SUCCESS;
}

PHP_INI_BEGIN()
	STD_PHP_INI_ENTRY("url_rewriter.tags", "a=href,area=href,frame=src,form=,fieldset=", PHP_INI_ALL, OnUpdateTags, url_adapt_state_ex, php_basic_globals, basic_globals)
PHP_INI_END()



#define YYFILL(n) goto done
#define YYCTYPE unsigned char
#define YYCURSOR p
#define YYLIMIT q
#define YYMARKER r
	
static inline void append_modified_url(smart_str *url, smart_str *dest, smart_str *url_app, const char *separator)
{
	register const char *p, *q;
	const char *bash = NULL;
	const char *sep = "?";
	
	q = (p = url->c) + url->len;

scan:

{
	YYCTYPE yych;
	goto yy0;
	++YYCURSOR;
yy0:
	if(YYLIMIT == YYCURSOR) YYFILL(1);
	yych = *YYCURSOR;
	switch(yych){
	case '#':	goto yy6;
	case ':':	goto yy2;
	case '?':	goto yy4;
	default:	goto yy8;
	}
yy2:	++YYCURSOR;
	goto yy3;
yy3:
{ smart_str_append(dest, url); return; }
yy4:	++YYCURSOR;
	goto yy5;
yy5:
{ sep = separator; goto scan; }
yy6:	++YYCURSOR;
	goto yy7;
yy7:
{ bash = p - 1; goto done; }
yy8:	++YYCURSOR;
	if(YYLIMIT == YYCURSOR) YYFILL(1);
	yych = *YYCURSOR;
	goto yy9;
yy9:	switch(yych){
	case '#':	case ':':	case '?':	goto yy10;
	default:	goto yy8;
	}
yy10:
{ goto scan; }
}

done:
	
	/* Don't modify URLs of the format "#mark" */
	if (bash && bash - url->c == 0) {
		smart_str_append(dest, url);
		return;
	}

	if (bash)
		smart_str_appendl(dest, url->c, bash - url->c);
	else
		smart_str_append(dest, url);

	smart_str_appends(dest, sep);
	smart_str_append(dest, url_app);

	if (bash)
		smart_str_appendl(dest, bash, q - bash);
}


#undef YYFILL
#undef YYCTYPE
#undef YYCURSOR
#undef YYLIMIT
#undef YYMARKER

static inline void tag_arg(url_adapt_state_ex_t *ctx, char quotes, char type TSRMLS_DC)
{
	char f = 0;

	if (strncasecmp(ctx->arg.c, ctx->lookup_data, ctx->arg.len) == 0)
		f = 1;

	if (quotes)
		smart_str_appendc(&ctx->result, type);
	if (f) {
		append_modified_url(&ctx->val, &ctx->result, &ctx->url_app, PG(arg_separator).output);
	} else {
		smart_str_append(&ctx->result, &ctx->val);
	}
	if (quotes)
		smart_str_appendc(&ctx->result, type);
}

enum {
	STATE_PLAIN = 0,
	STATE_TAG,
	STATE_NEXT_ARG,
	STATE_ARG,
	STATE_BEFORE_VAL,
	STATE_VAL
};

#define YYFILL(n) goto stop
#define YYCTYPE unsigned char
#define YYCURSOR xp
#define YYLIMIT end
#define YYMARKER q
#define STATE ctx->state

#define STD_PARA url_adapt_state_ex_t *ctx, char *start, char *YYCURSOR TSRMLS_DC
#define STD_ARGS ctx, start, xp TSRMLS_CC

#if SCANNER_DEBUG
#define scdebug(x) printf x
#else
#define scdebug(x)
#endif

static inline void passthru(STD_PARA) 
{
	scdebug(("appending %d chars, starting with %c\n", YYCURSOR-start, *start));
	smart_str_appendl(&ctx->result, start, YYCURSOR - start);
}

/*
 * This function appends a hidden input field after a <form> or
 * <fieldset>.  The latter is important for XHTML.
 */

static void handle_form(STD_PARA) 
{
	int doit = 0;

	if (ctx->form_app.len > 0) {
		switch (ctx->tag.len) {

#define RECOGNIZE(x) do { 	\
	case sizeof(x)-1: \
		if (strncasecmp(ctx->tag.c, x, sizeof(x)-1) == 0) \
			doit = 1; \
		break; \
} while (0)
		
			RECOGNIZE("form");
			RECOGNIZE("fieldset");
		}

		if (doit)
			smart_str_append(&ctx->result, &ctx->form_app);
	}
}



/*
 *  HANDLE_TAG copies the HTML Tag and checks whether we 
 *  have that tag in our table. If we might modify it,
 *  we continue to scan the tag, otherwise we simply copy the complete
 *  HTML stuff to the result buffer.
 */

static inline void handle_tag(STD_PARA) 
{
	int ok = 0;
	int i;

	ctx->tag.len = 0;
	smart_str_appendl(&ctx->tag, start, YYCURSOR - start);
	for (i = 0; i < ctx->tag.len; i++)
		ctx->tag.c[i] = tolower((int)(unsigned char)ctx->tag.c[i]);
	if (zend_hash_find(ctx->tags, ctx->tag.c, ctx->tag.len, (void **) &ctx->lookup_data) == SUCCESS)
		ok = 1;
	STATE = ok ? STATE_NEXT_ARG : STATE_PLAIN;
}

static inline void handle_arg(STD_PARA) 
{
	ctx->arg.len = 0;
	smart_str_appendl(&ctx->arg, start, YYCURSOR - start);
}

static inline void handle_val(STD_PARA, char quotes, char type) 
{
	smart_str_setl(&ctx->val, start + quotes, YYCURSOR - start - quotes * 2);
	tag_arg(ctx, quotes, type TSRMLS_CC);
}

static inline void xx_mainloop(url_adapt_state_ex_t *ctx, const char *newdata, size_t newlen TSRMLS_DC)
{
	char *end, *q;
	char *xp;
	char *start;
	int rest;

	smart_str_appendl(&ctx->buf, newdata, newlen);
	
	YYCURSOR = ctx->buf.c;
	YYLIMIT = ctx->buf.c + ctx->buf.len;

	switch (STATE) {
		case STATE_PLAIN: goto state_plain;
		case STATE_TAG: goto state_tag;
		case STATE_NEXT_ARG: goto state_next_arg;
		case STATE_ARG: goto state_arg;
		case STATE_BEFORE_VAL: goto state_before_val;
		case STATE_VAL: goto state_val;
	}
	

state_plain_begin:
	STATE = STATE_PLAIN;
	
state_plain:
	start = YYCURSOR;

{
	YYCTYPE yych;
	goto yy11;
	++YYCURSOR;
yy11:
	if(YYLIMIT == YYCURSOR) YYFILL(1);
	yych = *YYCURSOR;
	switch(yych){
	case '<':	goto yy13;
	default:	goto yy15;
	}
yy13:	++YYCURSOR;
	goto yy14;
yy14:
{ passthru(STD_ARGS); STATE = STATE_TAG; goto state_tag; }
yy15:	++YYCURSOR;
	if(YYLIMIT == YYCURSOR) YYFILL(1);
	yych = *YYCURSOR;
	goto yy16;
yy16:	switch(yych){
	case '<':	goto yy17;
	default:	goto yy15;
	}
yy17:
{ passthru(STD_ARGS); goto state_plain; }
}


state_tag:	
	start = YYCURSOR;

{
	YYCTYPE yych;
	goto yy18;
	++YYCURSOR;
yy18:
	if((YYLIMIT - YYCURSOR) < 2) YYFILL(2);
	yych = *YYCURSOR;
	switch(yych){
	case 'A':
	case 'B':
	case 'C':
	case 'D':
	case 'E':
	case 'F':
	case 'G':
	case 'H':
	case 'I':
	case 'J':
	case 'K':
	case 'L':
	case 'M':
	case 'N':
	case 'O':
	case 'P':
	case 'Q':
	case 'R':
	case 'S':
	case 'T':
	case 'U':
	case 'V':
	case 'W':
	case 'X':
	case 'Y':
	case 'Z':	case 'a':
	case 'b':
	case 'c':
	case 'd':
	case 'e':
	case 'f':
	case 'g':
	case 'h':
	case 'i':
	case 'j':
	case 'k':
	case 'l':
	case 'm':
	case 'n':
	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':
	case 'u':
	case 'v':
	case 'w':
	case 'x':
	case 'y':
	case 'z':	goto yy20;
	default:	goto yy22;
	}
yy20:	++YYCURSOR;
	yych = *YYCURSOR;
	goto yy25;
yy21:
{ handle_tag(STD_ARGS); /* Sets STATE */; passthru(STD_ARGS); if (STATE == STATE_PLAIN) goto state_plain; else goto state_next_arg; }
yy22:	++YYCURSOR;
	goto yy23;
yy23:
{ passthru(STD_ARGS); goto state_plain_begin; }
yy24:	++YYCURSOR;
	if(YYLIMIT == YYCURSOR) YYFILL(1);
	yych = *YYCURSOR;
	goto yy25;
yy25:	switch(yych){
	case 'A':
	case 'B':
	case 'C':
	case 'D':
	case 'E':
	case 'F':
	case 'G':
	case 'H':
	case 'I':
	case 'J':
	case 'K':
	case 'L':
	case 'M':
	case 'N':
	case 'O':
	case 'P':
	case 'Q':
	case 'R':
	case 'S':
	case 'T':
	case 'U':
	case 'V':
	case 'W':
	case 'X':
	case 'Y':
	case 'Z':	case 'a':
	case 'b':
	case 'c':
	case 'd':
	case 'e':
	case 'f':
	case 'g':
	case 'h':
	case 'i':
	case 'j':
	case 'k':
	case 'l':
	case 'm':
	case 'n':
	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':
	case 'u':
	case 'v':
	case 'w':
	case 'x':
	case 'y':
	case 'z':	goto yy24;
	default:	goto yy21;
	}
}


state_next_arg_begin:
	STATE = STATE_NEXT_ARG;
	
state_next_arg:
	start = YYCURSOR;

{
	YYCTYPE yych;
	goto yy26;
	++YYCURSOR;
yy26:
	if((YYLIMIT - YYCURSOR) < 2) YYFILL(2);
	yych = *YYCURSOR;
	switch(yych){
	case 0x09:
	case 0x0A:
	case 0x0B:	case 0x0D:	case ' ':	goto yy30;
	case '>':	goto yy28;
	case 'A':
	case 'B':
	case 'C':
	case 'D':
	case 'E':
	case 'F':
	case 'G':
	case 'H':
	case 'I':
	case 'J':
	case 'K':
	case 'L':
	case 'M':
	case 'N':
	case 'O':
	case 'P':
	case 'Q':
	case 'R':
	case 'S':
	case 'T':
	case 'U':
	case 'V':
	case 'W':
	case 'X':
	case 'Y':
	case 'Z':	case 'a':
	case 'b':
	case 'c':
	case 'd':
	case 'e':
	case 'f':
	case 'g':
	case 'h':
	case 'i':
	case 'j':
	case 'k':
	case 'l':
	case 'm':
	case 'n':
	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':