From 1ed8a2b3c501bedd4b35130c8a52662ccf78abad Mon Sep 17 00:00:00 2001 From: Egmont Koblinger Date: Sat, 23 Jun 2007 17:16:27 -0700 Subject: [PATCH] console UTF-8 fixes (fix) Recently my console UTF-8 patch went mainline. Here is an additional patch that fixes two nasty issues and improves a third one, namely: 1. My patch changed the behavior if a glyph is not found in the Unicode mapping table. Previously for Unicode values less than 256 or 512 the kernel tried to display the glyph from that position of the glyph table, which could lead to a different accented letter being displayed. I removed this fallback possibility and changed it to display the replacement symbol. As Behdad pointed out, some fonts (e.g. sun12x22 from the kbd package) lack Unicode mapping information, hence all you get is lots of question marks. Though theoretically it's actually a user-space bug (the font should be fixed), Behdad and I both believe that it'd be good to work around in the kernel by re-introducing the fallback solution for ASCII characters only. This sounds a quite reasonable decision, since all fonts ship the ASCII characters in the first 128 positions. This way users won't be surprised by lots of question marks just because s/he issued a not-so-perfectly parameterized setfont command. As this fallback is only re-introduced for code points below 128, you still won't see an accented letter replaced by another, but at least you'll always get the English letters right. 2. My patch introduced "question mark with inverted color attributes" as a last resort fallback glyph. Though it perfectly works on VGA console, on framebuffer you may end up with question marks that are highlighed but shouldn't be, and normal characters that are accidentally highlighed. This is caused by missing FLUSHes when changing the color attribute. 3. I've updated the table of double-width character based on Markus's updated version. Only ten new code poings (one interval) is added. Signed-off-by: Egmont Koblinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/vt.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/char/vt.c b/drivers/char/vt.c index bbd9fc412877..6650ae1c088f 100644 --- a/drivers/char/vt.c +++ b/drivers/char/vt.c @@ -1956,7 +1956,7 @@ char con_buf[CON_BUF_SIZE]; DEFINE_MUTEX(con_buf_mtx); /* is_double_width() is based on the wcwidth() implementation by - * Markus Kuhn -- 2003-05-20 (Unicode 4.0) + * Markus Kuhn -- 2007-05-26 (Unicode 5.0) * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c */ struct interval { @@ -1988,8 +1988,8 @@ static int is_double_width(uint32_t ucs) static const struct interval double_width[] = { { 0x1100, 0x115F }, { 0x2329, 0x232A }, { 0x2E80, 0x303E }, { 0x3040, 0xA4CF }, { 0xAC00, 0xD7A3 }, { 0xF900, 0xFAFF }, - { 0xFE30, 0xFE6F }, { 0xFF00, 0xFF60 }, { 0xFFE0, 0xFFE6 }, - { 0x20000, 0x2FFFD }, { 0x30000, 0x3FFFD } + { 0xFE10, 0xFE19 }, { 0xFE30, 0xFE6F }, { 0xFF00, 0xFF60 }, + { 0xFFE0, 0xFFE6 }, { 0x20000, 0x2FFFD }, { 0x30000, 0x3FFFD } }; return bisearch(ucs, double_width, sizeof(double_width) / sizeof(*double_width) - 1); @@ -2187,9 +2187,12 @@ static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int co continue; /* nothing to display */ } /* Glyph not found */ - if (!(vc->vc_utf && !vc->vc_disp_ctrl) && !(c & ~charmask)) { + if ((!(vc->vc_utf && !vc->vc_disp_ctrl) || c < 128) && !(c & ~charmask)) { /* In legacy mode use the glyph we get by a 1:1 mapping. - This would make absolutely no sense with Unicode in mind. */ + This would make absolutely no sense with Unicode in mind, + but do this for ASCII characters since a font may lack + Unicode mapping info and we don't want to end up with + having question marks only. */ tc = c; } else { /* Display U+FFFD. If it's not found, display an inverse question mark. */ @@ -2213,6 +2216,7 @@ static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int co } else { vc_attr = ((vc->vc_attr) & 0x88) | (((vc->vc_attr) & 0x70) >> 4) | (((vc->vc_attr) & 0x07) << 4); } + FLUSH } while (1) { @@ -2246,6 +2250,10 @@ static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int co if (tc < 0) tc = ' '; } + if (inverse) { + FLUSH + } + if (rescan) { rescan = 0; inverse = 0; -- GitLab