Mercurial > sdl-ios-xcode
view build-scripts/makedep.sh @ 4388:1524d3237820 SDL-1.2
Fixed bug #896
John Popplewell 2009-12-08 23:05:50 PST
Originally reported by AKFoerster on the mailing list.
Error decoding UTF8 Russian text to UTF-16LE on Windows, but specifically on
platforms without iconv support (the default on Windows).
Valid UTF8 characters are flagged as being overlong and then substituted by the
UNKNOWN_UNICODE character.
After studying the testiconv.c example program, reading the RFCs and putting
some printf statements in SDL_iconv.c the problem is in a test for 'Maximum
overlong sequences', specifically 4.2.1, which is carried out by the following
code:
} else if ( p[0] >= 0xC0 ) {
if ( (p[0] & 0xE0) != 0xC0 ) {
/* Skip illegal sequences
return SDL_ICONV_EILSEQ;
*/
ch = UNKNOWN_UNICODE;
} else {
if ( (p[0] & 0xCE) == 0xC0 ) { <<<<<<<< here
overlong = SDL_TRUE;
}
ch = (Uint32)(p[0] & 0x1F);
left = 1;
}
} else {
Here is the 2-byte encoding of a character in range 00000080 - 000007FF
110xxxxx 10xxxxxx
The line in question is supposed to be checking for an overlong sequence which
would be less than
11000001 10111111
which should be represented as a single byte.
BUT, the mask value (0xCE) is wrong, it isn't checking the top-most bit:
11000001 value
11001110 mask (incorrect)
^
and should be (0xDE):
11000001 value
11011110 mask (correct)
making the above code:
} else if ( p[0] >= 0xC0 ) {
if ( (p[0] & 0xE0) != 0xC0 ) {
/* Skip illegal sequences
return SDL_ICONV_EILSEQ;
*/
ch = UNKNOWN_UNICODE;
} else {
if ( (p[0] & 0xDE) == 0xC0 ) { <<<<<<<< here
overlong = SDL_TRUE;
}
ch = (Uint32)(p[0] & 0x1F);
left = 1;
}
} else {
I can supply a test program and/or a patch if required,
best regards,
John Popplewell
author | Sam Lantinga <slouken@libsdl.org> |
---|---|
date | Fri, 11 Dec 2009 08:00:57 +0000 |
parents | 5e6f2972f963 |
children | 93994f65c74c d2517c0de52b |
line wrap: on
line source
#!/bin/sh # # Generate dependencies from a list of source files # Check to make sure our environment variables are set if test x"$INCLUDE" = x -o x"$SOURCES" = x -o x"$output" = x; then echo "SOURCES, INCLUDE, and output needs to be set" exit 1 fi cache_prefix=".#$$" generate_var() { echo $1 | sed -e 's|^.*/||' -e 's|\.|_|g' } search_deps() { base=`echo $1 | sed 's|/[^/]*$||'` grep '#include "' <$1 | sed -e 's|.*"\([^"]*\)".*|\1|' | \ while read file do cache=${cache_prefix}_`generate_var $file` if test -f $cache; then : # We already ahve this cached else : >$cache for path in $base `echo $INCLUDE | sed 's|-I||g'` do dep="$path/$file" if test -f "$dep"; then echo " $dep \\" >>$cache search_deps $dep >>$cache break fi done fi cat $cache done } :>${output}.new for src in $SOURCES do echo "Generating dependencies for $src" ext=`echo $src | sed 's|.*\.\(.*\)|\1|'` if test x"$ext" = x"rc"; then obj=`echo $src | sed "s|^.*/\([^ ]*\)\..*|\1.o|g"` else obj=`echo $src | sed "s|^.*/\([^ ]*\)\..*|\1.lo|g"` fi echo "\$(objects)/$obj: $src \\" >>${output}.new search_deps $src | sort | uniq >>${output}.new case $ext in c) cat >>${output}.new <<__EOF__ \$(LIBTOOL) --mode=compile \$(CC) \$(CFLAGS) \$(EXTRA_CFLAGS) -c $src -o \$@ __EOF__ ;; cc) cat >>${output}.new <<__EOF__ \$(LIBTOOL) --mode=compile \$(CC) \$(CFLAGS) \$(EXTRA_CFLAGS) -c $src -o \$@ __EOF__ ;; m) cat >>${output}.new <<__EOF__ \$(LIBTOOL) --mode=compile \$(CC) \$(CFLAGS) \$(EXTRA_CFLAGS) -c $src -o \$@ __EOF__ ;; asm) cat >>${output}.new <<__EOF__ \$(LIBTOOL) --tag=CC --mode=compile \$(auxdir)/strip_fPIC.sh \$(NASM) $src -o \$@ __EOF__ ;; S) cat >>${output}.new <<__EOF__ \$(LIBTOOL) --mode=compile \$(CC) \$(CFLAGS) \$(EXTRA_CFLAGS) -c $src -o \$@ __EOF__ ;; rc) cat >>${output}.new <<__EOF__ \$(WINDRES) $src \$@ __EOF__ ;; *) echo "Unknown file extension: $ext";; esac echo "" >>${output}.new done mv ${output}.new ${output} rm -f ${cache_prefix}*