hi,
I've prepared the patch which completely removes compile-time
--enable-zend-multibyte configuration directive.
The configuration can be changed at run-tume using zend.multibyte=0/1.
The patch also fixes Unicode detection for phar archives.
I would like to commit it on Thursday.
Thanks. Dmitry.
Index: ext/standard/info.c
===================================================================
--- ext/standard/info.c (revision 305647)
+++ ext/standard/info.c (working copy)
@@ -759,11 +759,7 @@
php_info_print_table_row(2, "Zend Memory Manager",
is_zend_mm(TSRMLS_C) ? "enabled" : "disabled" );
-#ifdef ZEND_MULTIBYTE
- php_info_print_table_row(2, "Zend Multibyte Support",
"enabled");
-#else
- php_info_print_table_row(2, "Zend Multibyte Support",
"disabled");
-#endif
+ php_info_print_table_row(2, "Zend Multibyte Support",
CG(multibyte) ? "enabled" : "disabled");
#if HAVE_IPV6
php_info_print_table_row(2, "IPv6 Support", "enabled" );
Index: ext/phar/tests/zip/notphar.phpt
===================================================================
--- ext/phar/tests/zip/notphar.phpt (revision 305647)
+++ ext/phar/tests/zip/notphar.phpt (working copy)
@@ -4,6 +4,7 @@
<?php if (!extension_loaded("phar")) die("skip"); ?>
--INI--
phar.readonly=1
+detect_unicode=0
--FILE--
<?php
$fname = dirname(__FILE__) . '/' . basename(__FILE__, '.php') . '.phar.zip';
Index: ext/mbstring/tests/zend_multibyte-10.phpt
===================================================================
--- ext/mbstring/tests/zend_multibyte-10.phpt (revision 305647)
+++ ext/mbstring/tests/zend_multibyte-10.phpt (working copy)
@@ -11,6 +11,7 @@
<?php
declare(encoding="ISO-8859-15");
declare(encoding="ISO-8859-1");
+echo "ok\n";
?>
--EXPECTF--
-Fatal error: Encoding declaration pragma must be the very first statement in
the script in %s on line 3
+ok
Index: ext/mbstring/tests/zend_multibyte-11.phpt
===================================================================
--- ext/mbstring/tests/zend_multibyte-11.phpt (revision 305647)
+++ ext/mbstring/tests/zend_multibyte-11.phpt (working copy)
@@ -11,7 +11,8 @@
<?php
declare(encoding="ISO-8859-15") {
declare(encoding="ISO-8859-1");
+ echo "ok\n";
}
?>
--EXPECTF--
-Fatal error: Encoding declaration pragma must be the very first statement in
the script in %s on line 3
+ok
Index: ext/mbstring/mbstring.c
===================================================================
--- ext/mbstring/mbstring.c (revision 305647)
+++ ext/mbstring/mbstring.c (working copy)
@@ -77,9 +77,7 @@
#include "php_mbregex.h"
#endif
-#ifdef ZEND_MULTIBYTE
#include "zend_multibyte.h"
-#endif /* ZEND_MULTIBYTE */
#if HAVE_ONIG
#include "php_onig_compat.h"
@@ -98,12 +96,10 @@
static PHP_GINIT_FUNCTION(mbstring);
static PHP_GSHUTDOWN_FUNCTION(mbstring);
-#ifdef ZEND_MULTIBYTE
static size_t php_mb_oddlen(const unsigned char *string, size_t length, const
char *encoding TSRMLS_DC);
static int php_mb_encoding_converter(unsigned char **to, size_t *to_length,
const unsigned char *from, size_t from_length, const char *encoding_to, const
char *encoding_from TSRMLS_DC);
static char* php_mb_encoding_detector(const unsigned char *arg_string, size_t
arg_length, char *arg_list TSRMLS_DC);
static int php_mb_set_zend_encoding(TSRMLS_D);
-#endif
/* }}} */
/* {{{ php_mb_default_identify_list */
@@ -1126,12 +1122,14 @@
}
/* }}} */
-#ifdef ZEND_MULTIBYTE
/* {{{ static PHP_INI_MH(OnUpdate_mbstring_script_encoding) */
static PHP_INI_MH(OnUpdate_mbstring_script_encoding)
{
int *list, size;
+ if (!CG(multibyte)) {
+ return FAILURE;
+ }
if (php_mb_parse_encoding_list(new_value, new_value_length, &list,
&size, 1 TSRMLS_CC)) {
if (MBSTRG(script_encoding_list) != NULL) {
free(MBSTRG(script_encoding_list));
@@ -1150,7 +1148,6 @@
return SUCCESS;
}
/* }}} */
-#endif /* ZEND_MULTIBYTE */
/* {{{ static PHP_INI_MH(OnUpdate_mbstring_substitute_character) */
static PHP_INI_MH(OnUpdate_mbstring_substitute_character)
@@ -1249,9 +1246,7 @@
PHP_INI_ENTRY("mbstring.http_input", "pass", PHP_INI_ALL,
OnUpdate_mbstring_http_input)
PHP_INI_ENTRY("mbstring.http_output", "pass", PHP_INI_ALL,
OnUpdate_mbstring_http_output)
STD_PHP_INI_ENTRY("mbstring.internal_encoding", NULL, PHP_INI_ALL,
OnUpdate_mbstring_internal_encoding, internal_encoding_name,
zend_mbstring_globals, mbstring_globals)
-#ifdef ZEND_MULTIBYTE
PHP_INI_ENTRY("mbstring.script_encoding", NULL, PHP_INI_ALL,
OnUpdate_mbstring_script_encoding)
-#endif /* ZEND_MULTIBYTE */
PHP_INI_ENTRY("mbstring.substitute_character", NULL, PHP_INI_ALL,
OnUpdate_mbstring_substitute_character)
STD_PHP_INI_ENTRY("mbstring.func_overload", "0",
PHP_INI_SYSTEM, OnUpdateLong, func_overload, zend_mbstring_globals,
mbstring_globals)
@@ -1278,10 +1273,8 @@
mbstring_globals->language = mbfl_no_language_uni;
mbstring_globals->internal_encoding = mbfl_no_encoding_invalid;
mbstring_globals->current_internal_encoding =
mbstring_globals->internal_encoding;
-#ifdef ZEND_MULTIBYTE
mbstring_globals->script_encoding_list = NULL;
mbstring_globals->script_encoding_list_size = 0;
-#endif /* ZEND_MULTIBYTE */
mbstring_globals->http_output_encoding = mbfl_no_encoding_pass;
mbstring_globals->current_http_output_encoding = mbfl_no_encoding_pass;
mbstring_globals->http_input_identify = mbfl_no_encoding_invalid;
@@ -1319,11 +1312,9 @@
if (mbstring_globals->http_input_list) {
free(mbstring_globals->http_input_list);
}
-#ifdef ZEND_MULTIBYTE
if (mbstring_globals->script_encoding_list) {
free(mbstring_globals->script_encoding_list);
}
-#endif /* ZEND_MULTIBYTE */
if (mbstring_globals->detect_order_list) {
free(mbstring_globals->detect_order_list);
}
@@ -1441,10 +1432,10 @@
#if HAVE_MBREGEX
PHP_RINIT(mb_regex) (INIT_FUNC_ARGS_PASSTHRU);
#endif
-#ifdef ZEND_MULTIBYTE
-
zend_multibyte_set_internal_encoding(mbfl_no_encoding2name(MBSTRG(internal_encoding))
TSRMLS_CC);
- php_mb_set_zend_encoding(TSRMLS_C);
-#endif /* ZEND_MULTIBYTE */
+ if (CG(multibyte)) {
+
zend_multibyte_set_internal_encoding(mbfl_no_encoding2name(MBSTRG(internal_encoding))
TSRMLS_CC);
+ php_mb_set_zend_encoding(TSRMLS_C);
+ }
return SUCCESS;
}
@@ -1568,12 +1559,10 @@
RETURN_FALSE;
} else {
MBSTRG(current_internal_encoding) = no_encoding;
-#ifdef ZEND_MULTIBYTE
/* TODO: make independent from
mbstring.encoding_translation? */
- if (MBSTRG(encoding_translation)) {
+ if (CG(multibyte) && MBSTRG(encoding_translation)) {
zend_multibyte_set_internal_encoding(name
TSRMLS_CC);
}
-#endif /* ZEND_MULTIBYTE */
RETURN_TRUE;
}
}
@@ -4116,9 +4105,7 @@
zval *row1, *row2;
const mbfl_language *lang = mbfl_no2language(MBSTRG(language));
enum mbfl_no_encoding *entry;
-#ifdef ZEND_MULTIBYTE
zval *row3;
-#endif /* ZEND_MULTIBYTE */
if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "|s", &typ,
&typ_len) == FAILURE) {
RETURN_FALSE;
@@ -4201,22 +4188,22 @@
} else {
add_assoc_string(return_value, "strict_detection",
"Off", 1);
}
-#ifdef ZEND_MULTIBYTE
- entry = MBSTRG(script_encoding_list);
- n = MBSTRG(script_encoding_list_size);
- if(n > 0) {
- MAKE_STD_ZVAL(row3);
- array_init(row3);
- while (n > 0) {
- if ((name = (char
*)mbfl_no_encoding2name(*entry)) != NULL) {
- add_next_index_string(row3, name, 1);
+ if (CG(multibyte)) {
+ entry = MBSTRG(script_encoding_list);
+ n = MBSTRG(script_encoding_list_size);
+ if(n > 0) {
+ MAKE_STD_ZVAL(row3);
+ array_init(row3);
+ while (n > 0) {
+ if ((name = (char
*)mbfl_no_encoding2name(*entry)) != NULL) {
+ add_next_index_string(row3,
name, 1);
+ }
+ entry++;
+ n--;
}
- entry++;
- n--;
+ add_assoc_zval(return_value, "script_encoding",
row3);
}
- add_assoc_zval(return_value, "script_encoding", row3);
}
-#endif /* ZEND_MULTIBYTE */
} else if (!strcasecmp("internal_encoding", typ)) {
if ((name = (char
*)mbfl_no_encoding2name(MBSTRG(current_internal_encoding))) != NULL) {
RETVAL_STRING(name, 1);
@@ -4303,8 +4290,7 @@
RETVAL_STRING("Off", 1);
}
} else {
-#ifdef ZEND_MULTIBYTE
- if (!strcasecmp("script_encoding", typ)) {
+ if (CG(multibyte) && !strcasecmp("script_encoding", typ)) {
entry = MBSTRG(script_encoding_list);
n = MBSTRG(script_encoding_list_size);
if(n > 0) {
@@ -4320,7 +4306,6 @@
}
return;
}
-#endif /* ZEND_MULTIBYTE */
RETURN_FALSE;
}
}
@@ -4706,7 +4691,6 @@
}
/* }}} */
-#ifdef ZEND_MULTIBYTE
/* {{{ php_mb_set_zend_encoding() */
static int php_mb_set_zend_encoding(TSRMLS_D)
{
@@ -4864,7 +4848,6 @@
return mbfl_oddlen(&mb_string);
}
/* }}} */
-#endif /* ZEND_MULTIBYTE */
#endif /* HAVE_MBSTRING */
Index: ext/mbstring/mbstring.h
===================================================================
--- ext/mbstring/mbstring.h (revision 305647)
+++ ext/mbstring/mbstring.h (working copy)
@@ -167,10 +167,8 @@
enum mbfl_no_language language;
enum mbfl_no_encoding internal_encoding;
enum mbfl_no_encoding current_internal_encoding;
-#ifdef ZEND_MULTIBYTE
enum mbfl_no_encoding *script_encoding_list;
int script_encoding_list_size;
-#endif /* ZEND_MULTIBYTE */
enum mbfl_no_encoding http_output_encoding;
enum mbfl_no_encoding current_http_output_encoding;
enum mbfl_no_encoding http_input_identify;
Index: Zend/zend.c
===================================================================
--- Zend/zend.c (revision 305647)
+++ Zend/zend.c (working copy)
@@ -92,9 +92,8 @@
ZEND_INI_BEGIN()
ZEND_INI_ENTRY("error_reporting", NULL,
ZEND_INI_ALL, OnUpdateErrorReporting)
STD_ZEND_INI_BOOLEAN("zend.enable_gc", "1",
ZEND_INI_ALL, OnUpdateGCEnabled, gc_enabled,
zend_gc_globals, gc_globals)
-#ifdef ZEND_MULTIBYTE
+ STD_ZEND_INI_BOOLEAN("zend.multibyte", "0", ZEND_INI_PERDIR,
OnUpdateBool, multibyte, zend_compiler_globals, compiler_globals)
STD_ZEND_INI_BOOLEAN("detect_unicode", "1", ZEND_INI_ALL, OnUpdateBool,
detect_unicode, zend_compiler_globals, compiler_globals)
-#endif
ZEND_INI_END()
Index: Zend/Zend.m4
===================================================================
--- Zend/Zend.m4 (revision 305647)
+++ Zend/Zend.m4 (working copy)
@@ -176,13 +176,6 @@
ZEND_INLINE_OPTIMIZATION=yes
])
-AC_ARG_ENABLE(zend-multibyte,
-[ --enable-zend-multibyte Compile with zend multibyte support], [
- ZEND_MULTIBYTE=$enableval
-],[
- ZEND_MULTIBYTE=no
-])
-
AC_MSG_CHECKING([virtual machine dispatch method])
AC_MSG_RESULT($PHP_ZEND_VM)
@@ -195,9 +188,6 @@
AC_MSG_CHECKING(whether to enable Zend debugging)
AC_MSG_RESULT($ZEND_DEBUG)
-AC_MSG_CHECKING(whether to enable Zend multibyte)
-AC_MSG_RESULT($ZEND_MULTIBYTE)
-
case $PHP_ZEND_VM in
SWITCH)
AC_DEFINE(ZEND_VM_KIND,ZEND_VM_KIND_SWITCH,[virtual machine dispatch
method])
@@ -232,10 +222,6 @@
LIBZEND_CPLUSPLUS_CHECKS
fi
-if test "$ZEND_MULTIBYTE" = "yes"; then
- AC_DEFINE(ZEND_MULTIBYTE, 1, [ ])
-fi
-
changequote({,})
if test -n "$GCC" && test "$ZEND_INLINE_OPTIMIZATION" != "yes"; then
INLINE_CFLAGS=`echo $ac_n "$CFLAGS $ac_c" | sed s/-O[0-9s]*//`
Index: Zend/zend_language_scanner.h
===================================================================
--- Zend/zend_language_scanner.h (revision 305647)
+++ Zend/zend_language_scanner.h (working copy)
@@ -36,7 +36,6 @@
uint lineno;
char *filename;
-#ifdef ZEND_MULTIBYTE
/* original (unfiltered) script */
unsigned char *script_org;
size_t script_org_size;
@@ -50,7 +49,6 @@
zend_encoding_filter output_filter;
zend_encoding *script_encoding;
zend_encoding *internal_encoding;
-#endif /* ZEND_MULTIBYTE */
} zend_lex_state;
Index: Zend/zend_language_scanner.l
===================================================================
--- Zend/zend_language_scanner.l (revision 305647)
+++ Zend/zend_language_scanner.l (working copy)
@@ -181,16 +181,16 @@
lex_state->filename = zend_get_compiled_filename(TSRMLS_C);
lex_state->lineno = CG(zend_lineno);
-#ifdef ZEND_MULTIBYTE
- lex_state->script_org = SCNG(script_org);
- lex_state->script_org_size = SCNG(script_org_size);
- lex_state->script_filtered = SCNG(script_filtered);
- lex_state->script_filtered_size = SCNG(script_filtered_size);
- lex_state->input_filter = SCNG(input_filter);
- lex_state->output_filter = SCNG(output_filter);
- lex_state->script_encoding = SCNG(script_encoding);
- lex_state->internal_encoding = SCNG(internal_encoding);
-#endif /* ZEND_MULTIBYTE */
+ if (CG(multibyte)) {
+ lex_state->script_org = SCNG(script_org);
+ lex_state->script_org_size = SCNG(script_org_size);
+ lex_state->script_filtered = SCNG(script_filtered);
+ lex_state->script_filtered_size = SCNG(script_filtered_size);
+ lex_state->input_filter = SCNG(input_filter);
+ lex_state->output_filter = SCNG(output_filter);
+ lex_state->script_encoding = SCNG(script_encoding);
+ lex_state->internal_encoding = SCNG(internal_encoding);
+ }
}
ZEND_API void zend_restore_lexical_state(zend_lex_state *lex_state TSRMLS_DC)
@@ -209,24 +209,24 @@
YYSETCONDITION(lex_state->yy_state);
CG(zend_lineno) = lex_state->lineno;
zend_restore_compiled_filename(lex_state->filename TSRMLS_CC);
-#ifdef ZEND_MULTIBYTE
- if (SCNG(script_org)) {
- efree(SCNG(script_org));
- SCNG(script_org) = NULL;
+ if (CG(multibyte)) {
+ if (SCNG(script_org)) {
+ efree(SCNG(script_org));
+ SCNG(script_org) = NULL;
+ }
+ if (SCNG(script_filtered)) {
+ efree(SCNG(script_filtered));
+ SCNG(script_filtered) = NULL;
+ }
+ SCNG(script_org) = lex_state->script_org;
+ SCNG(script_org_size) = lex_state->script_org_size;
+ SCNG(script_filtered) = lex_state->script_filtered;
+ SCNG(script_filtered_size) = lex_state->script_filtered_size;
+ SCNG(input_filter) = lex_state->input_filter;
+ SCNG(output_filter) = lex_state->output_filter;
+ SCNG(script_encoding) = lex_state->script_encoding;
+ SCNG(internal_encoding) = lex_state->internal_encoding;
}
- if (SCNG(script_filtered)) {
- efree(SCNG(script_filtered));
- SCNG(script_filtered) = NULL;
- }
- SCNG(script_org) = lex_state->script_org;
- SCNG(script_org_size) = lex_state->script_org_size;
- SCNG(script_filtered) = lex_state->script_filtered;
- SCNG(script_filtered_size) = lex_state->script_filtered_size;
- SCNG(input_filter) = lex_state->input_filter;
- SCNG(output_filter) = lex_state->output_filter;
- SCNG(script_encoding) = lex_state->script_encoding;
- SCNG(internal_encoding) = lex_state->internal_encoding;
-#endif /* ZEND_MULTIBYTE */
}
ZEND_API void zend_destroy_file_handle(zend_file_handle *file_handle TSRMLS_DC)
@@ -269,32 +269,33 @@
SCNG(yy_start) = NULL;
if (size != -1) {
-#ifdef ZEND_MULTIBYTE
- if (zend_multibyte_read_script((unsigned char *)buf, size
TSRMLS_CC) != 0) {
- return FAILURE;
- }
+ if (CG(multibyte)) {
+ if (zend_multibyte_read_script((unsigned char *)buf,
size TSRMLS_CC) != 0) {
+ return FAILURE;
+ }
- SCNG(yy_in) = NULL;
+ SCNG(yy_in) = NULL;
- zend_multibyte_set_filter(NULL TSRMLS_CC);
+ zend_multibyte_set_filter(NULL TSRMLS_CC);
- if (!SCNG(input_filter)) {
- SCNG(script_filtered) = (unsigned
char*)emalloc(SCNG(script_org_size)+1);
- memcpy(SCNG(script_filtered), SCNG(script_org),
SCNG(script_org_size)+1);
- SCNG(script_filtered_size) = SCNG(script_org_size);
- } else {
- SCNG(input_filter)(&SCNG(script_filtered),
&SCNG(script_filtered_size), SCNG(script_org), SCNG(script_org_size) TSRMLS_CC);
- if (SCNG(script_filtered) == NULL) {
- zend_error_noreturn(E_COMPILE_ERROR, "Could not
convert the script from the detected "
- "encoding \"%s\" to a
compatible encoding", LANG_SCNG(script_encoding)->name);
+ if (!SCNG(input_filter)) {
+ SCNG(script_filtered) = (unsigned
char*)emalloc(SCNG(script_org_size)+1);
+ memcpy(SCNG(script_filtered), SCNG(script_org),
SCNG(script_org_size)+1);
+// SCNG(script_filtered)[SCNG(script_org_size)+1]
= 0;
+ SCNG(script_filtered_size) =
SCNG(script_org_size);
+ } else {
+ SCNG(input_filter)(&SCNG(script_filtered),
&SCNG(script_filtered_size), SCNG(script_org), SCNG(script_org_size) TSRMLS_CC);
+ if (SCNG(script_filtered) == NULL) {
+ zend_error_noreturn(E_COMPILE_ERROR,
"Could not convert the script from the detected "
+ "encoding \"%s\" to a
compatible encoding", LANG_SCNG(script_encoding)->name);
+ }
}
+ SCNG(yy_start) = SCNG(script_filtered) - offset;
+ yy_scan_buffer((char *)SCNG(script_filtered),
SCNG(script_filtered_size) TSRMLS_CC);
+ } else {
+ SCNG(yy_start) = buf - offset;
+ yy_scan_buffer(buf, size TSRMLS_CC);
}
- SCNG(yy_start) = SCNG(script_filtered) - offset;
- yy_scan_buffer((char *)SCNG(script_filtered),
SCNG(script_filtered_size) TSRMLS_CC);
-#else /* !ZEND_MULTIBYTE */
- SCNG(yy_start) = buf - offset;
- yy_scan_buffer(buf, size TSRMLS_CC);
-#endif /* ZEND_MULTIBYTE */
} else {
zend_error_noreturn(E_COMPILE_ERROR, "zend_stream_mmap()
failed");
}
@@ -437,25 +438,25 @@
SCNG(yy_in)=NULL;
SCNG(yy_start) = NULL;
-#ifdef ZEND_MULTIBYTE
- SCNG(script_org) = (unsigned char *)estrdup(str->value.str.val);
- SCNG(script_org_size) = str->value.str.len;
+ if (CG(multibyte)) {
+ SCNG(script_org) = (unsigned char *)estrdup(str->value.str.val);
+ SCNG(script_org_size) = str->value.str.len;
- zend_multibyte_set_filter(CG(internal_encoding) TSRMLS_CC);
+ zend_multibyte_set_filter(CG(internal_encoding) TSRMLS_CC);
- if (!SCNG(input_filter)) {
- SCNG(script_filtered) = (unsigned
char*)emalloc(SCNG(script_org_size)+1);
- memcpy(SCNG(script_filtered), SCNG(script_org),
SCNG(script_org_size)+1);
- SCNG(script_filtered_size) = SCNG(script_org_size);
+ if (!SCNG(input_filter)) {
+ SCNG(script_filtered) = (unsigned
char*)emalloc(SCNG(script_org_size)+1);
+ memcpy(SCNG(script_filtered), SCNG(script_org),
SCNG(script_org_size)+1);
+ SCNG(script_filtered_size) = SCNG(script_org_size);
+ } else {
+ SCNG(input_filter)(&SCNG(script_filtered),
&SCNG(script_filtered_size), SCNG(script_org), SCNG(script_org_size) TSRMLS_CC);
+ }
+
+ yy_scan_buffer((char *)SCNG(script_filtered),
SCNG(script_filtered_size) TSRMLS_CC);
} else {
- SCNG(input_filter)(&SCNG(script_filtered),
&SCNG(script_filtered_size), SCNG(script_org), SCNG(script_org_size) TSRMLS_CC);
+ yy_scan_buffer(str->value.str.val, str->value.str.len
TSRMLS_CC);
}
- yy_scan_buffer((char *)SCNG(script_filtered),
SCNG(script_filtered_size) TSRMLS_CC);
-#else /* !ZEND_MULTIBYTE */
- yy_scan_buffer(str->value.str.val, str->value.str.len TSRMLS_CC);
-#endif /* ZEND_MULTIBYTE */
-
zend_set_compiled_filename(filename TSRMLS_CC);
CG(zend_lineno) = 1;
CG(increment_lineno) = 0;
@@ -466,7 +467,6 @@
ZEND_API size_t zend_get_scanned_file_offset(TSRMLS_D)
{
size_t offset = SCNG(yy_cursor) - SCNG(yy_start);
-#ifdef ZEND_MULTIBYTE
if (SCNG(input_filter)) {
size_t original_offset = offset, length = 0; do {
unsigned char *p = NULL;
@@ -482,7 +482,6 @@
}
} while (original_offset != length);
}
-#endif
return offset;
}
@@ -524,7 +523,6 @@
BEGIN(ST_IN_SCRIPTING);
compiler_result = zendparse(TSRMLS_C);
-#ifdef ZEND_MULTIBYTE
if (SCNG(script_org)) {
efree(SCNG(script_org));
SCNG(script_org) = NULL;
@@ -533,7 +531,6 @@
efree(SCNG(script_filtered));
SCNG(script_filtered) = NULL;
}
-#endif /* ZEND_MULTIBYTE */
if (compiler_result==1) {
CG(active_op_array) = original_active_op_array;
@@ -571,7 +568,6 @@
return FAILURE;
}
zend_highlight(syntax_highlighter_ini TSRMLS_CC);
-#ifdef ZEND_MULTIBYTE
if (SCNG(script_org)) {
efree(SCNG(script_org));
SCNG(script_org) = NULL;
@@ -580,7 +576,6 @@
efree(SCNG(script_filtered));
SCNG(script_filtered) = NULL;
}
-#endif /* ZEND_MULTIBYTE */
zend_destroy_file_handle(&file_handle TSRMLS_CC);
zend_restore_lexical_state(&original_lex_state TSRMLS_CC);
return SUCCESS;
@@ -600,7 +595,6 @@
}
BEGIN(INITIAL);
zend_highlight(syntax_highlighter_ini TSRMLS_CC);
-#ifdef ZEND_MULTIBYTE
if (SCNG(script_org)) {
efree(SCNG(script_org));
SCNG(script_org) = NULL;
@@ -609,16 +603,11 @@
efree(SCNG(script_filtered));
SCNG(script_filtered) = NULL;
}
-#endif /* ZEND_MULTIBYTE */
zend_restore_lexical_state(&original_lex_state TSRMLS_CC);
zval_dtor(str);
return SUCCESS;
}
-END_EXTERN_C()
-#ifdef ZEND_MULTIBYTE
-
-BEGIN_EXTERN_C()
ZEND_API void zend_multibyte_yyinput_again(zend_encoding_filter
old_input_filter, zend_encoding *old_encoding TSRMLS_DC)
{
size_t original_offset, offset, free_flag, new_len, length;
@@ -728,11 +717,6 @@
zendlval->value.str.val = (char *) estrndup(yytext, yyleng); \
zendlval->value.str.len = yyleng; \
}
-#else /* ZEND_MULTIBYTE */
-# define zend_copy_value(zendlval, yytext, yyleng) \
- zendlval->value.str.val = (char *)estrndup(yytext, yyleng); \
- zendlval->value.str.len = yyleng;
-#endif /* ZEND_MULTIBYTE */
static void zend_scan_escape_string(zval *zendlval, char *str, int len, char
quote_type TSRMLS_DC)
{
@@ -836,7 +820,6 @@
s++;
}
*t = 0;
-#ifdef ZEND_MULTIBYTE
if (SCNG(output_filter)) {
size_t sz = 0;
s = zendlval->value.str.val;
@@ -844,7 +827,6 @@
zendlval->value.str.len = sz;
efree(s);
}
-#endif /* ZEND_MULTIBYTE */
}
@@ -1690,7 +1672,6 @@
inline_html:
yyleng = YYCURSOR - SCNG(yy_text);
-#ifdef ZEND_MULTIBYTE
if (SCNG(output_filter)) {
int readsize;
size_t sz = 0;
@@ -1703,10 +1684,6 @@
zendlval->value.str.val = (char *) estrndup(yytext, yyleng);
zendlval->value.str.len = yyleng;
}
-#else /* !ZEND_MULTIBYTE */
- zendlval->value.str.val = (char *) estrndup(yytext, yyleng);
- zendlval->value.str.len = yyleng;
-#endif
zendlval->type = IS_STRING;
HANDLE_NEWLINES(yytext, yyleng);
return T_INLINE_HTML;
@@ -1913,7 +1890,6 @@
}
*t = 0;
-#ifdef ZEND_MULTIBYTE
if (SCNG(output_filter)) {
size_t sz = 0;
s = zendlval->value.str.val;
@@ -1921,7 +1897,6 @@
zendlval->value.str.len = sz;
efree(s);
}
-#endif /* ZEND_MULTIBYTE */
return T_CONSTANT_ENCAPSED_STRING;
}
Index: Zend/zend_highlight.c
===================================================================
--- Zend/zend_highlight.c (revision 305647)
+++ Zend/zend_highlight.c (working copy)
@@ -57,8 +57,6 @@
ZEND_API void zend_html_puts(const char *s, uint len TSRMLS_DC)
{
const char *ptr=s, *end=s+len;
-
-#ifdef ZEND_MULTIBYTE
char *filtered;
int filtered_len;
@@ -67,7 +65,6 @@
ptr = filtered;
end = filtered + filtered_len;
}
-#endif /* ZEND_MULTIBYTE */
while (ptr<end) {
if (*ptr==' ') {
@@ -79,11 +76,9 @@
}
}
-#ifdef ZEND_MULTIBYTE
if (LANG_SCNG(output_filter)) {
efree(filtered);
}
-#endif /* ZEND_MULTIBYTE */
}
Index: Zend/zend_multibyte.c
===================================================================
--- Zend/zend_multibyte.c (revision 305647)
+++ Zend/zend_multibyte.c (working copy)
@@ -24,7 +24,6 @@
#include "zend_operators.h"
#include "zend_multibyte.h"
-#ifdef ZEND_MULTIBYTE
static size_t zend_multibyte_encoding_filter(unsigned char **to, size_t
*to_length, const char *to_encoding, const unsigned char *from, size_t
from_length, const char *from_encoding TSRMLS_DC);
size_t sjis_input_filter(unsigned char **buf, size_t *length, const unsigned
char *sjis, size_t sjis_length TSRMLS_DC);
size_t sjis_output_filter(unsigned char **buf, size_t *length, const unsigned
char *sjis, size_t sjis_length TSRMLS_DC);
@@ -1080,6 +1079,7 @@
zend_encoding *script_encoding = NULL;
int bom_size;
unsigned char *script;
+ unsigned char *pos1, *pos2;
if (LANG_SCNG(script_org_size) < sizeof(BOM_UTF32_LE)-1) {
return NULL;
@@ -1115,7 +1115,14 @@
}
/* script contains NULL bytes -> auto-detection */
- if (memchr(LANG_SCNG(script_org), 0, LANG_SCNG(script_org_size))) {
+ if ((pos1 = memchr(LANG_SCNG(script_org), 0,
LANG_SCNG(script_org_size)))) {
+ /* check if the NULL byte is after the __HALT_COMPILER */
+ if (pos1 - LANG_SCNG(script_org) >= sizeof("__HALT_COMPILER")) {
+ pos2 = strstr(LANG_SCNG(script_org), "__HALT_COMPILER");
+ if (pos2 && pos2 < pos1) {
+ return NULL;
+ }
+ }
/* make best effort if BOM is missing */
return
zend_multibyte_detect_utf_encoding(LANG_SCNG(script_org),
LANG_SCNG(script_org_size) TSRMLS_CC);
}
@@ -1168,7 +1175,6 @@
return NULL;
}
-#endif /* ZEND_MULTIBYTE */
/*
* Local variables:
Index: Zend/zend_multibyte.h
===================================================================
--- Zend/zend_multibyte.h (revision 305647)
+++ Zend/zend_multibyte.h (working copy)
@@ -22,8 +22,6 @@
#ifndef ZEND_MULTIBYTE_H
#define ZEND_MULTIBYTE_H
-#ifdef ZEND_MULTIBYTE
-
#define BOM_UTF32_BE "\x00\x00\xfe\xff"
#define BOM_UTF32_LE "\xff\xfe\x00\x00"
#define BOM_UTF16_BE "\xfe\xff"
@@ -67,8 +65,6 @@
ZEND_API int zend_multibyte_read_script(unsigned char *buf, size_t n
TSRMLS_DC);
END_EXTERN_C()
-#endif /* ZEND_MULTIBYTE */
-
#endif /* ZEND_MULTIBYTE_H */
/*
Index: Zend/zend_compile.c
===================================================================
--- Zend/zend_compile.c (revision 305647)
+++ Zend/zend_compile.c (working copy)
@@ -27,10 +27,7 @@
#include "zend_API.h"
#include "zend_exceptions.h"
#include "tsrm_virtual_cwd.h"
-
-#ifdef ZEND_MULTIBYTE
#include "zend_multibyte.h"
-#endif /* ZEND_MULTIBYTE */
#define CONSTANT_EX(op_array, op) \
(op_array)->literals[op].constant
@@ -149,14 +146,12 @@
/* NULL, name length, filename length, last accepting char position
length */
result->value.str.len = 1+name_length+strlen(filename)+char_pos_len;
-#ifdef ZEND_MULTIBYTE
+
/* must be binary safe */
result->value.str.val = (char *) safe_emalloc(result->value.str.len, 1,
1);
result->value.str.val[0] = '\0';
sprintf(result->value.str.val+1, "%s%s%s", name, filename,
char_pos_buf);
-#else
- zend_spprintf(&result->value.str.val, 0, "%c%s%s%s", '\0', name,
filename, char_pos_buf);
-#endif /* ZEND_MULTIBYTE */
+
result->type = IS_STRING;
Z_SET_REFCOUNT_P(result, 1);
}
@@ -202,7 +197,6 @@
init_compiler_declarables(TSRMLS_C);
zend_stack_init(&CG(context_stack));
-#ifdef ZEND_MULTIBYTE
CG(script_encoding_list) = NULL;
CG(script_encoding_list_size) = 0;
CG(internal_encoding) = NULL;
@@ -210,7 +204,6 @@
CG(encoding_converter) = NULL;
CG(encoding_oddlen) = NULL;
CG(encoding_declared) = 0;
-#endif /* ZEND_MULTIBYTE */
}
/* }}} */
@@ -249,11 +242,9 @@
zend_llist_destroy(&CG(open_files));
zend_stack_destroy(&CG(context_stack));
-#ifdef ZEND_MULTIBYTE
if (CG(script_encoding_list)) {
efree(CG(script_encoding_list));
}
-#endif /* ZEND_MULTIBYTE */
}
/* }}} */
@@ -5835,11 +5826,7 @@
if (!zend_binary_strcasecmp(var->u.constant.value.str.val,
var->u.constant.value.str.len, "ticks", sizeof("ticks")-1)) {
convert_to_long(&val->u.constant);
CG(declarables).ticks = val->u.constant;
-#ifdef ZEND_MULTIBYTE
} else if (!zend_binary_strcasecmp(var->u.constant.value.str.val,
var->u.constant.value.str.len, "encoding", sizeof("encoding")-1)) {
- zend_encoding *new_encoding, *old_encoding;
- zend_encoding_filter old_input_filter;
-
if ((Z_TYPE(val->u.constant) & IS_CONSTANT_TYPE_MASK) ==
IS_CONSTANT) {
zend_error(E_COMPILE_ERROR, "Cannot use constants as
encoding");
}
@@ -5863,31 +5850,31 @@
zend_error(E_COMPILE_ERROR, "Encoding
declaration pragma must be the very first statement in the script");
}
}
- CG(encoding_declared) = 1;
- convert_to_string(&val->u.constant);
- new_encoding =
zend_multibyte_fetch_encoding(val->u.constant.value.str.val);
- if (!new_encoding) {
- zend_error(E_COMPILE_WARNING, "Unsupported encoding
[%s]", val->u.constant.value.str.val);
- } else {
- old_input_filter = LANG_SCNG(input_filter);
- old_encoding = LANG_SCNG(script_encoding);
- zend_multibyte_set_filter(new_encoding TSRMLS_CC);
+ if (CG(multibyte)) {
+ zend_encoding *new_encoding, *old_encoding;
+ zend_encoding_filter old_input_filter;
- /* need to re-scan if input filter changed */
- if (old_input_filter != LANG_SCNG(input_filter) ||
- ((old_input_filter ==
zend_multibyte_script_encoding_filter) &&
- (new_encoding != old_encoding))) {
- zend_multibyte_yyinput_again(old_input_filter,
old_encoding TSRMLS_CC);
+ CG(encoding_declared) = 1;
+
+ convert_to_string(&val->u.constant);
+ new_encoding =
zend_multibyte_fetch_encoding(val->u.constant.value.str.val);
+ if (!new_encoding) {
+ zend_error(E_COMPILE_WARNING, "Unsupported
encoding [%s]", val->u.constant.value.str.val);
+ } else {
+ old_input_filter = LANG_SCNG(input_filter);
+ old_encoding = LANG_SCNG(script_encoding);
+ zend_multibyte_set_filter(new_encoding
TSRMLS_CC);
+
+ /* need to re-scan if input filter changed */
+ if (old_input_filter != LANG_SCNG(input_filter)
||
+ ((old_input_filter ==
zend_multibyte_script_encoding_filter) &&
+ (new_encoding != old_encoding))) {
+
zend_multibyte_yyinput_again(old_input_filter, old_encoding TSRMLS_CC);
+ }
}
}
- efree(val->u.constant.value.str.val);
-#else /* !ZEND_MULTIBYTE */
- } else if (!zend_binary_strcasecmp(var->u.constant.value.str.val,
var->u.constant.value.str.len, "encoding", sizeof("encoding")-1)) {
- /* Do not generate any kind of warning for encoding declares */
- /* zend_error(E_COMPILE_WARNING, "Declare encoding [%s] not
supported", val->u.constant.value.str.val); */
zval_dtor(&val->u.constant);
-#endif /* ZEND_MULTIBYTE */
} else {
zend_error(E_COMPILE_WARNING, "Unsupported declare '%s'",
var->u.constant.value.str.val);
zval_dtor(&val->u.constant);
Index: Zend/tests/multibyte/multibyte_encoding_002.phpt
===================================================================
--- Zend/tests/multibyte/multibyte_encoding_002.phpt (revision 305647)
+++ Zend/tests/multibyte/multibyte_encoding_002.phpt (working copy)
@@ -10,6 +10,7 @@
}
?>
--INI--
+zend.multibyte=1
mbstring.internal_encoding=iso-8859-1
--FILE--
ï>¿<?php
Index: Zend/tests/multibyte/multibyte_encoding_003.phpt
===================================================================
--- Zend/tests/multibyte/multibyte_encoding_003.phpt (revision 305647)
+++ Zend/tests/multibyte/multibyte_encoding_003.phpt (working copy)
@@ -10,6 +10,7 @@
}
?>
--INI--
+zend.multibyte=1
mbstring.internal_encoding=iso-8859-1
--FILE--
ÿþ<
@@ -18,5 +19,5 @@
--EXPECT--
-H
-
\ No newline at end of file
+Hello World
+===DONE===
\ No newline at end of file
Index: Zend/tests/multibyte/multibyte_encoding_004.phpt
===================================================================
--- Zend/tests/multibyte/multibyte_encoding_004.phpt (revision 305647)
+++ Zend/tests/multibyte/multibyte_encoding_004.phpt (working copy)
@@ -10,6 +10,7 @@
}
?>
--INI--
+zend.multibyte=1
mbstring.script_encoding=Shift_JIS
mbstring.internal_encoding=Shift_JIS
--FILE--
Index: Zend/tests/multibyte/multibyte_encoding_005.phpt
===================================================================
--- Zend/tests/multibyte/multibyte_encoding_005.phpt (revision 305647)
+++ Zend/tests/multibyte/multibyte_encoding_005.phpt (working copy)
@@ -10,6 +10,7 @@
}
?>
--INI--
+zend.multibyte=1
mbstring.encoding_translation = On
mbstring.script_encoding=Shift_JIS
mbstring.internal_encoding=UTF-8
Index: Zend/tests/multibyte/multibyte_encoding_006.phpt
===================================================================
Cannot display: file marked as a binary type.
svn:mime-type = application/octet-stream
Index: Zend/tests/multibyte/multibyte_encoding_001.phpt
===================================================================
--- Zend/tests/multibyte/multibyte_encoding_001.phpt (revision 305647)
+++ Zend/tests/multibyte/multibyte_encoding_001.phpt (working copy)
@@ -10,6 +10,7 @@
}
?>
--INI--
+zend.multibyte=1
mbstring.internal_encoding=SJIS
--FILE--
<?php
Index: Zend/tests/declare_001.phpt
===================================================================
--- Zend/tests/declare_001.phpt (revision 305647)
+++ Zend/tests/declare_001.phpt (working copy)
@@ -1,16 +1,23 @@
--TEST--
Testing declare statement with several type values
+--SKIPIF--
+<?php
+if (ini_get("zend.multibyte")) {
+ die("skip Requires zend.multibyte=0");
+}
+?>
--FILE--
<?php
declare(encoding = 1);
declare(encoding = 1123131232131312321);
declare(encoding = NULL);
+declare(encoding = 'utf-8');
declare(encoding = M_PI);
-declare(encoding = 'utf-8');
print 'DONE';
?>
---EXPECT--
-DONE
+--EXPECTF--
+Fatal error: Cannot use constants as encoding in %sdeclare_001.php on line 7
+
Index: Zend/tests/declare_002.phpt
===================================================================
--- Zend/tests/declare_002.phpt (revision 0)
+++ Zend/tests/declare_002.phpt (revision 0)
@@ -0,0 +1,28 @@
+--TEST--
+Testing declare statement with several type values
+--SKIPIF--
+<?php
+if (!ini_get("zend.multibyte")) {
+ die("skip Requires zend.multibyte=1");
+}
+?>
+--FILE--
+<?php
+
+declare(encoding = 1);
+declare(encoding = 1123131232131312321);
+declare(encoding = NULL);
+declare(encoding = 'utf-8');
+declare(encoding = M_PI);
+
+print 'DONE';
+
+?>
+--EXPECTF--
+Warning: Unsupported encoding [%d] in %sdeclare_002.php on line 3
+
+Warning: Unsupported encoding [%f] in %sdeclare_002.php on line 4
+
+Warning: Unsupported encoding [] in %sdeclare_002.php on line 5
+
+Fatal error: Cannot use constants as encoding in %sdeclare_002.php on line 7
Index: Zend/zend_globals.h
===================================================================
--- Zend/zend_globals.h (revision 305647)
+++ Zend/zend_globals.h (working copy)
@@ -35,10 +35,7 @@
#include "zend_objects_API.h"
#include "zend_modules.h"
#include "zend_float.h"
-
-#ifdef ZEND_MULTIBYTE
#include "zend_multibyte.h"
-#endif /* ZEND_MULTIBYTE */
/* Define ZTS if you want a thread-safe Zend */
/*#undef ZTS*/
@@ -150,9 +147,9 @@
HashTable interned_strings;
-#ifdef ZEND_MULTIBYTE
zend_encoding **script_encoding_list;
size_t script_encoding_list_size;
+ zend_bool multibyte;
zend_bool detect_unicode;
zend_bool encoding_declared;
@@ -162,7 +159,6 @@
zend_encoding_detector encoding_detector;
zend_encoding_converter encoding_converter;
zend_encoding_oddlen encoding_oddlen;
-#endif /* ZEND_MULTIBYTE */
#ifdef ZTS
zval ***static_members_table;
@@ -308,7 +304,6 @@
int yy_state;
zend_stack state_stack;
-#ifdef ZEND_MULTIBYTE
/* original (unfiltered) script */
unsigned char *script_org;
size_t script_org_size;
@@ -322,7 +317,6 @@
zend_encoding_filter output_filter;
zend_encoding *script_encoding;
zend_encoding *internal_encoding;
-#endif /* ZEND_MULTIBYTE */
};
#endif /* ZEND_GLOBALS_H */
Index: main/main.c
===================================================================
--- main/main.c (revision 305647)
+++ main/main.c (working copy)
@@ -1980,11 +1980,6 @@
REGISTER_MAIN_LONG_CONSTANT("PHP_MAXPATHLEN", MAXPATHLEN,
CONST_PERSISTENT | CONST_CS);
REGISTER_MAIN_LONG_CONSTANT("PHP_INT_MAX", LONG_MAX, CONST_PERSISTENT |
CONST_CS);
REGISTER_MAIN_LONG_CONSTANT("PHP_INT_SIZE", sizeof(long),
CONST_PERSISTENT | CONST_CS);
-#ifdef ZEND_MULTIBYTE
- REGISTER_MAIN_LONG_CONSTANT("ZEND_MULTIBYTE", 1, CONST_PERSISTENT |
CONST_CS);
-#else
- REGISTER_MAIN_LONG_CONSTANT("ZEND_MULTIBYTE", 0, CONST_PERSISTENT |
CONST_CS);
-#endif
#ifdef PHP_WIN32
REGISTER_MAIN_LONG_CONSTANT("PHP_WINDOWS_VERSION_MAJOR",
EG(windows_version_info).dwMajorVersion, CONST_PERSISTENT | CONST_CS);
Index: win32/build/config.w32
===================================================================
--- win32/build/config.w32 (revision 305647)
+++ win32/build/config.w32 (working copy)
@@ -377,12 +377,6 @@
ARG_ENABLE('fd-setsize', "Set maximum number of sockets for select(2)", "256");
ADD_FLAG("CFLAGS", "/D FD_SETSIZE=" + parseInt(PHP_FD_SETSIZE));
-ARG_ENABLE("zend-multibyte", "Enable Zend multibyte encoding support", "no");
-if (PHP_ZEND_MULTIBYTE == "yes") {
- STDOUT.WriteLine("Enabling Zend multibyte encoding support");
- AC_DEFINE('ZEND_MULTIBYTE', 1);
-}
-
AC_DEFINE('HAVE_USLEEP', 1);
AC_DEFINE('HAVE_STRCOLL', 1);
--
PHP Internals - PHP Runtime Development Mailing List
To unsubscribe, visit: http://www.php.net/unsub.php
