Merge branch 'pull-request/1094'

* pull-request/1094:
  added php_mb_check_code_point for mb_substitute_character
  news entry for PR #1094

NEWS

@@ -62,6 +62,7 @@ PHP                                                                        NEWS
     handles multibyte replacement char nicely). (Masakielastic, Yasuo)
   . Added array input support to mb_convert_encoding(). (Yasuo)
   . Added array input support to mb_check_encoding(). (Yasuo)
+  . Fixed bug #69079 (enhancement for mb_substitute_character). (masakielastic)
 
 - Mcrypt:
   . The deprecated mcrypt extension has been moved to PECL. (leigh)

ext/mbstring/mbstring.c

@@ -104,6 +104,11 @@ static void php_mb_gpc_get_detect_order(const zend_encoding ***list, size_t *lis
 
 static void php_mb_gpc_set_input_encoding(const zend_encoding *encoding);
 
+static inline zend_bool php_mb_is_unsupported_no_encoding(enum mbfl_no_encoding no_enc);
+
+static inline zend_bool php_mb_is_no_encoding_unicode(enum mbfl_no_encoding no_enc);
+
+static inline zend_bool php_mb_is_no_encoding_utf8(enum mbfl_no_encoding no_enc);
 /* }}} */
 
 /* {{{ php_mb_default_identify_list */
@@ -1992,6 +1997,73 @@ PHP_FUNCTION(mb_detect_order)
 }
 /* }}} */
 
+static inline int php_mb_check_code_point(long cp)
+{
+	enum mbfl_no_encoding no_enc;
+	char* buf;
+	char buf_len;
+
+	no_enc = MBSTRG(current_internal_encoding)->no_encoding;
+
+	if (php_mb_is_no_encoding_utf8(no_enc)) {
+
+		if ((cp > 0 && 0xd800 > cp) || (cp > 0xdfff && 0x110000 > cp)) {
+			return 1;
+		}
+
+		return 0;
+	} else if (php_mb_is_no_encoding_unicode(no_enc)) {
+
+		if (0 > cp || cp > 0x10ffff) {
+			return 0;
+		}
+
+		return 1;
+
+	// backward compatibility
+	} else if (php_mb_is_unsupported_no_encoding(no_enc)) {
+		return cp < 0xffff && cp > 0x0;
+	}
+
+	if (cp < 0x100) {
+		buf_len = 1;
+		buf = (char *) safe_emalloc(buf_len, 1, 1);
+		buf[0] = cp;
+		buf[1] = 0;
+	} else if (cp < 0x10000) {
+		buf_len = 2;
+		buf = (char *) safe_emalloc(buf_len, 1, 1);
+		buf[0] = cp >> 8;
+		buf[1] = cp & 0xff;
+		buf[2] = 0;
+	} else if (cp < 0x1000000) {
+		buf_len = 3;
+		buf = (char *) safe_emalloc(buf_len, 1, 1);
+		buf[0] = cp >> 16;
+		buf[1] = (cp >> 8) & 0xff;
+		buf[2] = cp & 0xff;
+		buf[3] = 0;
+	} else {
+		buf_len = 4;
+		buf = (char *) safe_emalloc(buf_len, 1, 1);
+		buf[0] = cp >> 24;
+		buf[1] = (cp >> 16) & 0xff;
+		buf[2] = (cp >> 8) & 0xff;
+		buf[3] = cp & 0xff;
+		buf[4] = 0;
+	}
+
+	if (php_mb_check_encoding(buf, buf_len, NULL)) {
+		efree(buf);
+
+		return 1;
+	}
+
+	efree(buf);
+
+	return 0;
+}
+
 /* {{{ proto mixed mb_substitute_character([mixed substchar])
    Sets the current substitute_character or returns the current substitute_character */
 PHP_FUNCTION(mb_substitute_character)
@@ -2026,7 +2098,7 @@ PHP_FUNCTION(mb_substitute_character)
 				} else {
 					convert_to_long_ex(arg1);
 
-					if (Z_LVAL_P(arg1) < 0xffff && Z_LVAL_P(arg1) > 0x0) {
+					if (php_mb_check_code_point(Z_LVAL_P(arg1))) {
 						MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
 						MBSTRG(current_filter_illegal_substchar) = Z_LVAL_P(arg1);
 					} else {
@@ -2037,7 +2109,7 @@ PHP_FUNCTION(mb_substitute_character)
 				break;
 			default:
 				convert_to_long_ex(arg1);
-				if (Z_LVAL_P(arg1) < 0xffff && Z_LVAL_P(arg1) > 0x0) {
+				if (php_mb_check_code_point(Z_LVAL_P(arg1))) {
 					MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
 					MBSTRG(current_filter_illegal_substchar) = Z_LVAL_P(arg1);
 				} else {
@@ -3124,7 +3196,7 @@ PHP_FUNCTION(mb_strimwidth)
 	if (from < 0) {
 		from += swidth;
 	}
-		
+
 	if (from < 0 || (size_t)from > str_len) {
 		php_error_docref(NULL, E_WARNING, "Start position is out of range");
 		RETURN_FALSE;

ext/mbstring/tests/bug69079.phpt

@@ -0,0 +1,14 @@
+--TEST--
+Bug #69079 (enhancement for mb_substitute_character)
+--SKIPIF--
+<?php extension_loaded('mbstring') or die('skip mbstring not available'); ?>
+--FILE--
+<?php
+mb_internal_encoding('UTF-8');
+var_dump(mb_substitute_character(0x1f600));
+mb_internal_encoding('EUC-JP-2004');
+var_dump(mb_substitute_character(0x8fa1ef));
+?>
+--EXPECT--
+bool(true)
+bool(true)