archive/php-src
1
0
Fork 0
mirror of https://github.com/php/php-src.git synced 2025-08-21 01:45:16 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

UTF-16 text conversion handles truncated characters as illegal

Browse source 
This broke one old test (Zend/tests/multibyte_encoding_003.phpt), which used
a PHP script encoded as UTF-16. The problem was that to terminate the test
script, we need the text: "\n--EXPECT--". Out of that text, the terminating
newline (0x0A byte) becomes part of the resulting test script; but a bare
0x0A byte with no 0x00 is not valid UTF-16.

Since we now treat truncated UTF-16 characters as erroneous, an extra '?' is
appended to the output as an 'illegal character' marker.

Really, if we are running PHP scripts which are treated as encoded in UTF-16
or some other arbitrary text encoding (not ASCII), and the script is not
actually a valid string in that encoding, inserting '?' characters into the
code which the PHP interpreter runs is a bad thing to do. In such cases, the
script shouldn't be treated as UTF-16 (or whatever) at all.

I wonder if mbstring's encoding detection is being used in 'non-strict' mode?
This commit is contained in:
Alex Dowad 2020-10-13 15:17:00 +02:00
parent 9bfb158872
commit d9ddeb6e85
2 changed files with 22 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

BIN
Zend/tests/multibyte/multibyte_encoding_003.phpt
View file

Binary file not shown.

25
ext/mbstring/libmbfl/filters/mbfilter_utf16.c
View file

@ -33,6 +33,7 @@
static int mbfl_filt_ident_utf16(int c, mbfl_identify_filter *filter); static int mbfl_filt_ident_utf16(int c, mbfl_identify_filter *filter);
static int mbfl_filt_ident_utf16le(int c, mbfl_identify_filter *filter); static int mbfl_filt_ident_utf16le(int c, mbfl_identify_filter *filter);
static int mbfl_filt_ident_utf16be(int c, mbfl_identify_filter *filter); static int mbfl_filt_ident_utf16be(int c, mbfl_identify_filter *filter);
static int mbfl_filt_conv_utf16_wchar_flush(mbfl_convert_filter *filter);
static const char *mbfl_encoding_utf16_aliases[] = {"utf16", NULL}; static const char *mbfl_encoding_utf16_aliases[] = {"utf16", NULL};
@ -93,7 +94,7 @@ const struct mbfl_convert_vtbl vtbl_utf16_wchar = {
mbfl_filt_conv_common_ctor, mbfl_filt_conv_common_ctor,
NULL, NULL,
mbfl_filt_conv_utf16_wchar, mbfl_filt_conv_utf16_wchar,
mbfl_filt_conv_common_flush, mbfl_filt_conv_utf16_wchar_flush,
NULL, NULL,
}; };
@ -113,7 +114,7 @@ const struct mbfl_convert_vtbl vtbl_utf16be_wchar = {
mbfl_filt_conv_common_ctor, mbfl_filt_conv_common_ctor,
NULL, NULL,
mbfl_filt_conv_utf16be_wchar, mbfl_filt_conv_utf16be_wchar,
mbfl_filt_conv_common_flush, mbfl_filt_conv_utf16_wchar_flush,
NULL, NULL,
}; };
@ -133,7 +134,7 @@ const struct mbfl_convert_vtbl vtbl_utf16le_wchar = {
mbfl_filt_conv_common_ctor, mbfl_filt_conv_common_ctor,
NULL, NULL,
mbfl_filt_conv_utf16le_wchar, mbfl_filt_conv_utf16le_wchar,
mbfl_filt_conv_common_flush, mbfl_filt_conv_utf16_wchar_flush,
NULL, NULL,
}; };
@ -343,6 +344,24 @@ int mbfl_filt_conv_wchar_utf16le(int c, mbfl_convert_filter *filter)
return c; return c;
} }
static int mbfl_filt_conv_utf16_wchar_flush(mbfl_convert_filter *filter)
{
int status = filter->status;
int cache = filter->cache;
filter->status = filter->cache = 0;
if (status & 0xF) {
/* Input string was truncated */
CK((*filter->output_function)(cache | MBFL_WCSGROUP_THROUGH, filter->data));
}
if (filter->flush_function) {
(*filter->flush_function)(filter->data);
}
return 0;
}
static int mbfl_filt_ident_utf16(int c, mbfl_identify_filter *filter) static int mbfl_filt_ident_utf16(int c, mbfl_identify_filter *filter)
{ {
if (filter->status == 0) { if (filter->status == 0) {