Commit:    0a974f14d13832838dcc7bae88b3271b7d035f46
Author:    Rui Hirokawa <hirok...@php.net>         Wed, 31 Jul 2013 08:46:54 
+0900
Parents:   1d7b6970f20a059c501e68927c9fb874bdb226bc
Branches:  PHP-5.4

Link:       
http://git.php.net/?p=php-src.git;a=commitdiff;h=0a974f14d13832838dcc7bae88b3271b7d035f46

Log:
MFH: fixed #65045: mb_convert_encoding breaks well-formed character.

Bugs:
https://bugs.php.net/65045

Changed paths:
  M  ext/mbstring/libmbfl/filters/mbfilter_utf8.c
  M  ext/mbstring/libmbfl/filters/mbfilter_utf8.h
  M  ext/mbstring/libmbfl/filters/mbfilter_utf8_mobile.c
  A  ext/mbstring/tests/bug65045.phpt
  M  ext/mbstring/tests/illformed_utf_sequences.phpt

diff --git a/ext/mbstring/libmbfl/filters/mbfilter_utf8.c 
b/ext/mbstring/libmbfl/filters/mbfilter_utf8.c
index fcee610..5539700 100644
--- a/ext/mbstring/libmbfl/filters/mbfilter_utf8.c
+++ b/ext/mbstring/libmbfl/filters/mbfilter_utf8.c
@@ -79,7 +79,7 @@ const struct mbfl_convert_vtbl vtbl_utf8_wchar = {
        mbfl_filt_conv_common_ctor,
        mbfl_filt_conv_common_dtor,
        mbfl_filt_conv_utf8_wchar,
-       mbfl_filt_conv_common_flush
+       mbfl_filt_conv_utf8_wchar_flush
 };
 
 const struct mbfl_convert_vtbl vtbl_wchar_utf8 = {
@@ -93,6 +93,17 @@ const struct mbfl_convert_vtbl vtbl_wchar_utf8 = {
 
 #define CK(statement)  do { if ((statement) < 0) return (-1); } while (0)
 
+int mbfl_filt_put_invalid_char(int c, mbfl_convert_filter *filter)
+{
+       int w;
+       w = c & MBFL_WCSGROUP_MASK;
+       w |= MBFL_WCSGROUP_THROUGH;
+       filter->status = 0;
+       filter->cache = 0;
+       CK((*filter->output_function)(w, filter->data));
+}
+
+
 /*
  * UTF-8 => wchar
  */
@@ -100,111 +111,104 @@ int mbfl_filt_conv_utf8_wchar(int c, 
mbfl_convert_filter *filter)
 {
        int s, c1, w = 0, flag = 0;
 
-       if (c < 0x80) {
-               if (filter->status != 0)  {
-                       w = (filter->cache & MBFL_WCSGROUP_MASK) | 
MBFL_WCSGROUP_THROUGH;
-                       CK((*filter->output_function)(w, filter->data));
-                       filter->status = 0;
-                       filter->cache = 0;
-               }
-               if (c >= 0) {
+retry:
+       switch (filter->status & 0xff) {
+       case 0x00:
+               if (c < 0x80) {
                        CK((*filter->output_function)(c, filter->data));
+               } else if (c >= 0xc2 && c <= 0xdf) { /* 2byte code first char: 
0xc2-0xdf */
+                       filter->status = 0x10;
+                       filter->cache = c & 0x1f;
+               } else if (c >= 0xe0 && c <= 0xef) { /* 3byte code first char: 
0xe0-0xef */
+                       filter->status = 0x20;
+                       filter->cache = c & 0xf;
+               } else if (c >= 0xf0 && c <= 0xf4) { /* 3byte code first char: 
0xf0-0xf4 */
+                       filter->status = 0x30;
+                       filter->cache = c & 0x7;
+               } else {
+                       mbfl_filt_put_invalid_char(c, filter);
                }
-       } else if (c < 0xc0) {
-               int status = filter->status & 0xff;
-               switch (status) {
-               case 0x10: /* 2byte code 2nd char: 0x80-0xbf */
-               case 0x21: /* 3byte code 3rd char: 0x80-0xbf */
-               case 0x32: /* 4byte code 4th char: 0x80-0xbf */
-                       filter->status = 0;
-                       s = filter->cache | (c & 0x3f);
+               break;
+       case 0x10: /* 2byte code 2nd char: 0x80-0xbf */
+       case 0x21: /* 3byte code 3rd char: 0x80-0xbf */
+       case 0x32: /* 4byte code 4th char: 0x80-0xbf */
+               filter->status = 0;
+               if (c >= 0x80 && c <= 0xbf) {
+                       s = (filter->cache<<6) | (c & 0x3f);                    
                        filter->cache = 0;
-                       if ((status == 0x10 && s >= 0x80) ||
-                           (status == 0x21 && s >= 0x800 && (s < 0xd800 || s > 
0xdfff)) ||
-                           (status == 0x32 && s >= 0x10000 && s < 0x110000)) {
-                               CK((*filter->output_function)(s, filter->data));
-                       } else {
-                               w = s & MBFL_WCSGROUP_MASK;
-                               flag = 1;
-                       }
-                       break;
-               case 0x20: /* 3byte code 2nd char: 
0:0xa0-0xbf,D:0x80-9F,1-C,E-F:0x80-0x9f */
-                       s = filter->cache | ((c & 0x3f) << 6);
-                       c1 = (s >> 12) & 0xf;
-                       if ((c1 == 0x0 && c >= 0xa0) || 
-                               (c1 == 0xd && c < 0xa0) || 
-                               (c1 > 0x0 && c1 != 0xd)) {
-                               filter->cache = s;
-                               filter->status++;
-                       } else {
-                               w = s & MBFL_WCSGROUP_MASK;
-                               flag = 1;
-                       }
-                       break;
-               case 0x31: /* 4byte code 3rd char: 0x80-0xbf */
-                       filter->cache |= ((c & 0x3f) << 6);
-                       filter->status++;
-                       break;
-               case 0x30: /* 4byte code 2nd char: 
0:0x90-0xbf,1-3:0x80-0xbf,4:0x80-0x8f */
-                       s = filter->cache | ((c & 0x3f) << 12);
-                       c1 = (s >> 18) & 0x7;
-                       if ((c1 == 0x0 && c >= 0x90) ||
-                               (c1 > 0x0 && c1 < 0x4) ||
-                               (c1 == 0x4 && c < 0x90)) {
-                               filter->cache = s;
-                               filter->status++;
-                       } else {
-                               w = s & MBFL_WCSGROUP_MASK;
-                               flag = 1;
-                       }
-                       break;
-               default:
-                       w = c & MBFL_WCSGROUP_MASK;
-                       flag = 1;
-                       break;
+                       CK((*filter->output_function)(s, filter->data));        
                
+               } else {
+                       mbfl_filt_put_invalid_char(filter->cache, filter);
+                       goto retry;                     
                }
-       } else if (c < 0xc2) { /* invalid: 0xc0,0xc1 */
-               w = c & MBFL_WCSGROUP_MASK;
-               flag = 1;
-       } else if (c < 0xe0) { /* 2byte code first char: 0xc2-0xdf */
-               if (filter->status == 0x0) {
-                       filter->status = 0x10;
-                       filter->cache = (c & 0x1f) << 6;
+               break;
+       case 0x20: /* 3byte code 2nd char: 
0:0xa0-0xbf,D:0x80-9F,1-C,E-F:0x80-0x9f */
+               s = (filter->cache<<6) | (c & 0x3f);
+               c1 = filter->cache & 0xf;
+               
+               if ((c >= 0x80 && c <= 0xbf) &&
+                       ((c1 == 0x0 && c >= 0xa0) ||
+                        (c1 == 0xd && c < 0xa0) ||
+                        (c1 > 0x0 && c1 != 0xd))) {
+                       filter->cache = s;
+                       filter->status++;
                } else {
-                       w = c & MBFL_WCSGROUP_MASK;
-                       flag = 1;
+                       mbfl_filt_put_invalid_char(filter->cache, filter);
+                       goto retry;                                             
                }
-       } else if (c < 0xf0) { /* 3byte code first char: 0xe0-0xef */
-               if (filter->status == 0x0) {
-                       filter->status = 0x20;
-                       filter->cache = (c & 0xf) << 12;
+               break;
+       case 0x30: /* 4byte code 2nd char: 
0:0x90-0xbf,1-3:0x80-0xbf,4:0x80-0x8f */
+               s = (filter->cache<<6) | (c & 0x3f);
+               c1 = filter->cache & 0x7;
+               
+               if ((c >= 0x80 && c <= 0xbf) &&
+                       ((c1 == 0x0 && c >= 0x90) ||
+                        (c1 == 0x4 && c < 0x90) ||
+                        (c1 > 0x0 && c1 != 0x4))) {
+                       filter->cache = s;
+                       filter->status++;
                } else {
-                       w = c & MBFL_WCSGROUP_MASK;
-                       flag = 1;
+                       mbfl_filt_put_invalid_char(filter->cache, filter);
+                       goto retry;                                             
                }
-       } else if (c < 0xf5) { /* 4byte code first char: 0xf0-0xf4 */
-               if (filter->status == 0x0) {
-                       filter->status = 0x30;
-                       filter->cache = (c & 0x7) << 18;
+               break;
+       case 0x31: /* 4byte code 3rd char: 0x80-0xbf */
+               if (c >= 0x80 && c <= 0xbf) {
+                       filter->cache = (filter->cache<<6) | (c & 0x3f);
+                       filter->status++;
                } else {
-                       w = c & MBFL_WCSGROUP_MASK;
-                       flag = 1;
+                       mbfl_filt_put_invalid_char(filter->cache, filter);
+                       goto retry;                                             
                }
-       } else {
-               w = c & MBFL_WCSGROUP_MASK;
-               flag = 1;
-       }
-
-       if (flag) {
-               w |= MBFL_WCSGROUP_THROUGH;
-               CK((*filter->output_function)(w, filter->data));
+               break;
+       default:
                filter->status = 0;
-               filter->cache = 0;
+               break;
        }
 
        return c;
 }
 
+int mbfl_filt_conv_utf8_wchar_flush(mbfl_convert_filter *filter)
+{
+       int status, cache;
+
+       status = filter->status;
+       cache = filter->cache;
+
+       filter->status = 0;
+       filter->cache = 0;
+
+       if (status != 0) {
+               mbfl_filt_put_invalid_char(cache, filter);
+       }
+
+       if (filter->flush_function != NULL) {
+               (*filter->flush_function)(filter->data);
+       }
+       return 0;
+}
+
 /*
  * wchar => UTF-8
  */
diff --git a/ext/mbstring/libmbfl/filters/mbfilter_utf8.h 
b/ext/mbstring/libmbfl/filters/mbfilter_utf8.h
index 07bf655..970ace6 100644
--- a/ext/mbstring/libmbfl/filters/mbfilter_utf8.h
+++ b/ext/mbstring/libmbfl/filters/mbfilter_utf8.h
@@ -37,5 +37,6 @@ extern const struct mbfl_convert_vtbl vtbl_wchar_utf8;
 
 int mbfl_filt_conv_utf8_wchar(int c, mbfl_convert_filter *filter);
 int mbfl_filt_conv_wchar_utf8(int c, mbfl_convert_filter *filter);
+int mbfl_filt_conv_utf8_wchar_flush(mbfl_convert_filter *filter);
 
 #endif /* MBFL_MBFILTER_UTF8_H */
diff --git a/ext/mbstring/libmbfl/filters/mbfilter_utf8_mobile.c 
b/ext/mbstring/libmbfl/filters/mbfilter_utf8_mobile.c
index 62feca4..f9b643c 100644
--- a/ext/mbstring/libmbfl/filters/mbfilter_utf8_mobile.c
+++ b/ext/mbstring/libmbfl/filters/mbfilter_utf8_mobile.c
@@ -37,6 +37,7 @@
 #include "mbfilter_sjis_mobile.h"
 
 extern int mbfl_filt_ident_utf8(int c, mbfl_identify_filter *filter);
+extern int mbfl_filt_conv_utf8_wchar_flush(mbfl_convert_filter *filter);
 
 extern const unsigned char mblen_table_utf8[];
 
@@ -115,7 +116,7 @@ const struct mbfl_convert_vtbl vtbl_utf8_docomo_wchar = {
        mbfl_filt_conv_common_ctor,
        mbfl_filt_conv_common_dtor,
        mbfl_filt_conv_utf8_mobile_wchar,
-       mbfl_filt_conv_common_flush
+       mbfl_filt_conv_utf8_wchar_flush
 };
 
 const struct mbfl_convert_vtbl vtbl_wchar_utf8_docomo = {
@@ -133,7 +134,7 @@ const struct mbfl_convert_vtbl vtbl_utf8_kddi_a_wchar = {
        mbfl_filt_conv_common_ctor,
        mbfl_filt_conv_common_dtor,
        mbfl_filt_conv_utf8_mobile_wchar,
-       mbfl_filt_conv_common_flush
+       mbfl_filt_conv_utf8_wchar_flush
 };
 
 const struct mbfl_convert_vtbl vtbl_wchar_utf8_kddi_a = {
@@ -151,7 +152,7 @@ const struct mbfl_convert_vtbl vtbl_utf8_kddi_b_wchar = {
        mbfl_filt_conv_common_ctor,
        mbfl_filt_conv_common_dtor,
        mbfl_filt_conv_utf8_mobile_wchar,
-       mbfl_filt_conv_common_flush
+       mbfl_filt_conv_utf8_wchar_flush
 };
 
 const struct mbfl_convert_vtbl vtbl_wchar_utf8_kddi_b = {
@@ -169,7 +170,7 @@ const struct mbfl_convert_vtbl vtbl_utf8_sb_wchar = {
        mbfl_filt_conv_common_ctor,
        mbfl_filt_conv_common_dtor,
        mbfl_filt_conv_utf8_mobile_wchar,
-       mbfl_filt_conv_common_flush
+       mbfl_filt_conv_utf8_wchar_flush
 };
 
 const struct mbfl_convert_vtbl vtbl_wchar_utf8_sb = {
@@ -191,119 +192,97 @@ int mbfl_filt_conv_utf8_mobile_wchar(int c, 
mbfl_convert_filter *filter)
        int s, w = 0, flag = 0;
        int s1 = 0, c1 = 0, snd = 0;
 
-       if (c < 0x80) {
-               if (c >= 0) {
+retry:
+       switch (filter->status & 0xff) {
+       case 0x00:
+               if (c < 0x80) {
                        CK((*filter->output_function)(c, filter->data));
+               } else if (c >= 0xc2 && c <= 0xdf) { /* 2byte code first char: 
0xc2-0xdf */
+                       filter->status = 0x10;
+                       filter->cache = c & 0x1f;
+               } else if (c >= 0xe0 && c <= 0xef) { /* 3byte code first char: 
0xe0-0xef */
+                       filter->status = 0x20;
+                       filter->cache = c & 0xf;
+               } else if (c >= 0xf0 && c <= 0xf4) { /* 3byte code first char: 
0xf0-0xf4 */
+                       filter->status = 0x30;
+                       filter->cache = c & 0x7;
+               } else {
+                       mbfl_filt_put_invalid_char(c, filter);
                }
+               break;
+       case 0x10: /* 2byte code 2nd char: 0x80-0xbf */
+       case 0x21: /* 3byte code 3rd char: 0x80-0xbf */
+       case 0x32: /* 4byte code 4th char: 0x80-0xbf */
                filter->status = 0;
-       } else if (c < 0xc0) {
-               int status = filter->status & 0xff;
-               switch (status) {
-               case 0x10: /* 2byte code 2nd char: 0x80-0xbf */
-               case 0x21: /* 3byte code 3rd char: 0x80-0xbf */
-               case 0x32: /* 4byte code 4th char: 0x80-0xbf */
-                       filter->status = 0;
-                       s = filter->cache | (c & 0x3f);
+               if (c >= 0x80 && c <= 0xbf) {
+                       s = (filter->cache<<6) | (c & 0x3f);                    
                        filter->cache = 0;
-                       if ((status == 0x10 && s >= 0x80) ||
-                           (status == 0x21 && s >= 0x800 && (s < 0xd800 || s > 
0xdfff)) ||
-                           (status == 0x32 && s >= 0x10000 && s < 0x110000)) {
-                               
-                               if (filter->from->no_encoding == 
mbfl_no_encoding_utf8_docomo &&
-                                       mbfilter_conv_r_map_tbl(s, &s1, 
mbfl_docomo2uni_pua, 4) > 0) {
-                                       s = 
mbfilter_sjis_emoji_docomo2unicode(s1, &snd);
-                               } else if (filter->from->no_encoding == 
mbfl_no_encoding_utf8_kddi_a &&
-                                                  mbfilter_conv_r_map_tbl(s, 
&s1, mbfl_kddi2uni_pua, 7) > 0) {
-                                       s = 
mbfilter_sjis_emoji_kddi2unicode(s1, &snd);
-                               } else if (filter->from->no_encoding == 
mbfl_no_encoding_utf8_kddi_b &&
-                                                  mbfilter_conv_r_map_tbl(s, 
&s1, mbfl_kddi2uni_pua_b, 8) > 0) {
-                                       s = 
mbfilter_sjis_emoji_kddi2unicode(s1, &snd);
-                               } else if (filter->from->no_encoding == 
mbfl_no_encoding_utf8_sb &&
-                                                  mbfilter_conv_r_map_tbl(s, 
&s1, mbfl_sb2uni_pua, 6) > 0) {
-                                       s = mbfilter_sjis_emoji_sb2unicode(s1, 
&snd);
-                               }
-
-                               if (snd > 0) {
-                                       CK((*filter->output_function)(snd, 
filter->data));
-                               }
-                               CK((*filter->output_function)(s, filter->data));
-                       } else {
-                               w = s & MBFL_WCSGROUP_MASK;
-                               flag = 1;
-                       }
-                       break;
-               case 0x20: /* 3byte code 2nd char: 
0:0xa0-0xbf,D:0x80-9F,1-C,E-F:0x80-0x9f */
-                       s = filter->cache | ((c & 0x3f) << 6);
-                       c1 = (s >> 12) & 0xf;
-                       if ((c1 == 0x0 && c >= 0xa0) || 
-                               (c1 == 0xd && c < 0xa0) || 
-                               (c1 > 0x0 && c1 != 0xd)) {
-                               filter->cache = s;
-                               filter->status++;
-                       } else {
-                               w = s & MBFL_WCSGROUP_MASK;
-                               flag = 1;
+
+                       if (filter->from->no_encoding == 
mbfl_no_encoding_utf8_docomo &&
+                               mbfilter_conv_r_map_tbl(s, &s1, 
mbfl_docomo2uni_pua, 4) > 0) {
+                               s = mbfilter_sjis_emoji_docomo2unicode(s1, 
&snd);
+                       } else if (filter->from->no_encoding == 
mbfl_no_encoding_utf8_kddi_a &&
+                                          mbfilter_conv_r_map_tbl(s, &s1, 
mbfl_kddi2uni_pua, 7) > 0) {
+                               s = mbfilter_sjis_emoji_kddi2unicode(s1, &snd);
+                       } else if (filter->from->no_encoding == 
mbfl_no_encoding_utf8_kddi_b &&
+                                          mbfilter_conv_r_map_tbl(s, &s1, 
mbfl_kddi2uni_pua_b, 8) > 0) {
+                               s = mbfilter_sjis_emoji_kddi2unicode(s1, &snd);
+                       } else if (filter->from->no_encoding == 
mbfl_no_encoding_utf8_sb &&
+                                          mbfilter_conv_r_map_tbl(s, &s1, 
mbfl_sb2uni_pua, 6) > 0) {
+                               s = mbfilter_sjis_emoji_sb2unicode(s1, &snd);
                        }
-                       break;
-               case 0x31: /* 4byte code 3rd char: 0x80-0xbf */
-                       filter->cache |= ((c & 0x3f) << 6);
-                       filter->status++;
-                       break;
-               case 0x30: /* 4byte code 2nd char: 
0:0x90-0xbf,1-3:0x80-0xbf,4:0x80-0x8f */
-                       s = filter->cache | ((c & 0x3f) << 12);
-                       c1 = (s >> 18) & 0x7;
-                       if ((c1 == 0x0 && c >= 0x90) ||
-                               (c1 > 0x0 && c1 < 0x4) ||
-                               (c1 == 0x4 && c < 0x90)) {
-                               filter->cache = s;
-                               filter->status++;
-                       } else {
-                               w = s & MBFL_WCSGROUP_MASK;
-                               flag = 1;
+                       
+                       if (snd > 0) {
+                               CK((*filter->output_function)(snd, 
filter->data));
                        }
-                       break;
-               default:
-                       w = c & MBFL_WCSGROUP_MASK;
-                       flag = 1;
-                       break;
+                       CK((*filter->output_function)(s, filter->data));
+               } else {
+                       mbfl_filt_put_invalid_char(filter->cache, filter);
+                       goto retry;                     
                }
-       } else if (c < 0xc2) { /* invalid: 0xc0,0xc1 */
-               w = c & MBFL_WCSGROUP_MASK;
-               flag = 1;
-       } else if (c < 0xe0) { /* 2byte code first char: 0xc2-0xdf */
-               if (filter->status == 0x0) {
-                       filter->status = 0x10;
-                       filter->cache = (c & 0x1f) << 6;
+               break;
+       case 0x20: /* 3byte code 2nd char: 
0:0xa0-0xbf,D:0x80-9F,1-C,E-F:0x80-0x9f */
+               s = (filter->cache<<6) | (c & 0x3f);
+               c1 = filter->cache & 0xf;
+               
+               if ((c >= 0x80 && c <= 0xbf) &&
+                       ((c1 == 0x0 && c >= 0xa0) ||
+                        (c1 == 0xd && c < 0xa0) ||
+                        (c1 > 0x0 && c1 != 0xd))) {
+                       filter->cache = s;
+                       filter->status++;
                } else {
-                       w = c & MBFL_WCSGROUP_MASK;
-                       flag = 1;
+                       mbfl_filt_put_invalid_char(filter->cache, filter);
+                       goto retry;                                             
                }
-       } else if (c < 0xf0) { /* 3byte code first char: 0xe0-0xef */
-               if (filter->status == 0x0) {
-                       filter->status = 0x20;
-                       filter->cache = (c & 0xf) << 12;
+               break;
+       case 0x30: /* 4byte code 2nd char: 
0:0x90-0xbf,1-3:0x80-0xbf,4:0x80-0x8f */
+               s = (filter->cache<<6) | (c & 0x3f);
+               c1 = filter->cache & 0x7;
+               
+               if ((c >= 0x80 && c <= 0xbf) &&
+                       ((c1 == 0x0 && c >= 0x90) ||
+                        (c1 == 0x4 && c < 0x90) ||
+                        (c1 > 0x0 && c1 != 0x4))) {
+                       filter->cache = s;
+                       filter->status++;
                } else {
-                       w = c & MBFL_WCSGROUP_MASK;
-                       flag = 1;
+                       mbfl_filt_put_invalid_char(filter->cache, filter);
+                       goto retry;                                             
                }
-       } else if (c < 0xf5) { /* 4byte code first char: 0xf0-0xf4 */
-               if (filter->status == 0x0) {
-                       filter->status = 0x30;
-                       filter->cache = (c & 0x7) << 18;
+               break;
+       case 0x31: /* 4byte code 3rd char: 0x80-0xbf */
+               if (c >= 0x80 && c <= 0xbf) {
+                       filter->cache = (filter->cache<<6) | (c & 0x3f);
+                       filter->status++;
                } else {
-                       w = c & MBFL_WCSGROUP_MASK;
-                       flag = 1;
+                       mbfl_filt_put_invalid_char(filter->cache, filter);
+                       goto retry;                                             
                }
-       } else {
-               w = c & MBFL_WCSGROUP_MASK;
-               flag = 1;
-       }
-
-       if (flag) {
-               w |= MBFL_WCSGROUP_THROUGH;
-               CK((*filter->output_function)(w, filter->data));
+               break;
+       default:
                filter->status = 0;
-               filter->cache = 0;
+               break;
        }
 
        return c;
diff --git a/ext/mbstring/tests/bug65045.phpt b/ext/mbstring/tests/bug65045.phpt
new file mode 100644
index 0000000..03a090d
--- /dev/null
+++ b/ext/mbstring/tests/bug65045.phpt
@@ -0,0 +1,29 @@
+--TEST--
+Bug #65045: mb_convert_encoding breaks well-formed character
+--SKIPIF--
+<?php extension_loaded('mbstring') or die('skip mbstring not available'); ?>
+--FILE--
+<?php
+
+//declare(encoding = 'UTF-8');
+mb_internal_encoding('UTF-8');
+
+$str = "\xF0\xA4\xAD".  "\xF0\xA4\xAD\xA2"."\xF0\xA4\xAD\xA2";
+$expected = "\xEF\xBF\xBD"."\xF0\xA4\xAD\xA2"."\xF0\xA4\xAD\xA2";
+
+$str2 = "\xF0\xA4\xAD\xA2"."\xF0\xA4\xAD\xA2"."\xF0\xA4\xAD";
+$expected2 = "\xF0\xA4\xAD\xA2"."\xF0\xA4\xAD\xA2"."\xEF\xBF\xBD";
+
+mb_substitute_character(0xFFFD);
+var_dump(
+    $expected === htmlspecialchars_decode(htmlspecialchars($str, 
ENT_SUBSTITUTE, 'UTF-8')),
+    $expected2 === htmlspecialchars_decode(htmlspecialchars($str2, 
ENT_SUBSTITUTE, 'UTF-8')), 
+    $expected === mb_convert_encoding($str, 'UTF-8', 'UTF-8'),
+    $expected2 === mb_convert_encoding($str2, 'UTF-8', 'UTF-8')
+);
+
+--EXPECT--
+bool(true)
+bool(true)
+bool(true)
+bool(true)
\ No newline at end of file
diff --git a/ext/mbstring/tests/illformed_utf_sequences.phpt 
b/ext/mbstring/tests/illformed_utf_sequences.phpt
index b5b9d94..378b956 100644
--- a/ext/mbstring/tests/illformed_utf_sequences.phpt
+++ b/ext/mbstring/tests/illformed_utf_sequences.phpt
@@ -25,28 +25,28 @@ var_dump(chk_enc("\x31\x32\x33", 0));
 var_dump(chk_enc("\x41\x42\x43", 0));
 var_dump(chk_enc("\xc0\xb1\xc0\xb2\xc0\xb3", 6));
 var_dump(chk_enc("\xc1\x81\xc1\x82\xc1\x83", 6));
-var_dump(chk_enc("\xe0\x80\xb1\xe0\x80\xb2\xe0\x80\xb3", 6));
-var_dump(chk_enc("\xe0\x81\x81\xe0\x81\x82\xe0\x81\x83", 6));
-var_dump(chk_enc("\xf0\x80\x80\xb1\xf0\x80\x80\xb2\xf0\x80\x80\xb3", 9));
-var_dump(chk_enc("\xf0\x80\x81\x81\xf0\x80\x81\x82\xf0\x81\x83", 8));
+var_dump(chk_enc("\xe0\x80\xb1\xe0\x80\xb2\xe0\x80\xb3", 9));
+var_dump(chk_enc("\xe0\x81\x81\xe0\x81\x82\xe0\x81\x83", 9));
+var_dump(chk_enc("\xf0\x80\x80\xb1\xf0\x80\x80\xb2\xf0\x80\x80\xb3", 12));
+var_dump(chk_enc("\xf0\x80\x81\x81\xf0\x80\x81\x82\xf0\x81\x83", 11));
 
var_dump(chk_enc("\xf8\x80\x80\x80\xb1\xf8\x80\x80\x80\xb2\xf8\x80\x80\x80\xb3",
 15));
 
var_dump(chk_enc("\xf8\x80\x80\x81\x81\xf8\x80\x80\x81\x82\xf8\x80\x80\x81\x83",
 15));
 
var_dump(chk_enc("\xfc\x80\x80\x80\x80\xb1\xfc\x80\x80\x80\x80\xb2\xfc\x80\x80\x80\x80\xb3",
 18));
 
var_dump(chk_enc("\xfc\x80\x80\x80\x81\x81\xfc\x80\x80\x80\x81\x82\xfc\x80\x80\x80\x81\x83",
 18));
 
 var_dump(chk_enc("\xc2\xa2\xc2\xa3\xc2\xa5", 0));
-var_dump(chk_enc("\xe0\x82\xa2\xe0\x82\xa3\xe0\x82\xa5", 6));
-var_dump(chk_enc("\xf0\x80\x82\xa2\xf0\x80\x82\xa3\xf0\x80\x82\xa5", 9));
+var_dump(chk_enc("\xe0\x82\xa2\xe0\x82\xa3\xe0\x82\xa5", 9));
+var_dump(chk_enc("\xf0\x80\x82\xa2\xf0\x80\x82\xa3\xf0\x80\x82\xa5", 12));
 
var_dump(chk_enc("\xf8\x80\x80\x82\xa2\xf8\x80\x80\x82\xa3\xf8\x80\x80\x82\xa5",
 15));
 
var_dump(chk_enc("\xfc\x80\x80\x80\x82\xa2\xfc\x80\x80\x80\x82\xa3\xfc\x80\x80\x80\x82\xa5",
 18));
 
 var_dump(chk_enc("\xc1\xbf", 2));
 var_dump(chk_enc("\xc2\x80", 0));
 var_dump(chk_enc("\xdf\xbf", 0));
-var_dump(chk_enc("\xe0\x9f\xff", 2));
+var_dump(chk_enc("\xe0\x9f\xff", 3));
 var_dump(chk_enc("\xe0\xa0\x80", 2));
 var_dump(chk_enc("\xef\xbf\xbf", 0));
-var_dump(chk_enc("\xf0\x8f\xbf\xbf", 3));
+var_dump(chk_enc("\xf0\x8f\xbf\xbf", 4));
 var_dump(chk_enc("\xf0\x90\x80\x80", 0));
 var_dump(chk_enc("\xf7\xbf\xbf\xbf", 4));
 var_dump(chk_enc("\xf8\x87\xbf\xbf\xbf", 5));
@@ -61,7 +61,7 @@ echo "UTF-8 and surrogates area\n";
 $out = '';
 $cnt = 0;
 for ($i = 0xd7ff; $i <= 0xe000; ++$i) {
-       $s = chk_enc(pack('C3', 0xe0 | ($i >> 12), 0x80 | ($i >> 6) & 0x3f, 
0x80 | $i & 0x3f), 2);
+       $s = chk_enc(pack('C3', 0xe0 | ($i >> 12), 0x80 | ($i >> 6) & 0x3f, 
0x80 | $i & 0x3f), 3);
        if ($s === false) {
                $cnt++;
        } else {
-- 
PHP CVS Mailing List (http://www.php.net/)
To unsubscribe, visit: http://www.php.net/unsub.php

Reply via email to