Three of the uni2char() tables in nls_cp1251.c are incorrect, while charset2uni() matches the Unicode CP1251 mapping. page00 incorrectly maps eight U+00xx characters that are not part of CP1251 to 0xbb. page04 is off by one for U+0490..U+0492, causing U+0491 to be stored as 0xa5 and U+0492 to be stored as 0xb4. page20 also stops at U+203F, so U+20AC can be decoded but not encoded. Regenerate page00, page04 and page20 from charset2uni. glibc iconv agrees with the resulting mappings, and a full BMP round trip is now lossless. Signed-off-by: Ali Ahmet Memiş --- fs/nls/nls_cp1251.c | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/fs/nls/nls_cp1251.c b/fs/nls/nls_cp1251.c index 6f46d339f23c..3447df754432 100644 --- a/fs/nls/nls_cp1251.c +++ b/fs/nls/nls_cp1251.c @@ -122,14 +122,14 @@ static const unsigned char page00[256] = { 0x00, 0xa9, 0x00, 0xab, 0xac, 0xad, 0xae, 0x00, /* 0xa8-0xaf */ 0xb0, 0xb1, 0x00, 0x00, 0x00, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ - 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ - 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ - 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ - 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ - 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ - 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ - 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ - 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page04[256] = { @@ -152,7 +152,7 @@ static const unsigned char page04[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ - 0x00, 0xa5, 0xb4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0xa5, 0xb4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ }; static const unsigned char page20[256] = { @@ -164,6 +164,20 @@ static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x89, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x8b, 0x9b, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x88, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ }; static const unsigned char page21[256] = { -- 2.55.0