Hi Axel!
On Wed, Feb 10, 2021 at 03:31:21PM +0100, Axel Beckert wrote:
> Hi Michael,
>
> On Wed, Feb 10, 2021 at 08:59:15AM -0500, Michael Schröder wrote:
> > diff --git a/src/encoding.c b/src/encoding.c
> > index 11c3c41..e1ea364 100644
> > --- a/src/encoding.c
> > +++ b/src/encoding.c
> > @@ -1164,7 +1164,9 @@ void utf8_handle_comb(unsigned int c, struct mchar
> > *mc)
> > if (c1 >= 0xd800 && c1 < 0xe000)
> > comb_tofront(root, c1 - 0xd800);
> > i = combchars[root]->prev;
> > - if (c1 == i + 0xd800) {
> > + if (i == (unsigned int)root)
> > + i = combchars[root ^ 1]->prev; /* steal from other
> > root */
> > + if (i == 0x800 || i == 0x801 || c1 == i + 0xd800) {
> > /* completely full, can't recycle */
> > mc->image = '?';
> > mc->font = 0;
>
> Thanks, but this seems to break the actual output.
But isn't the output broken anyway? Two years ago, the line
c = (c & 255) | (unsigned char)D_rend.font << 8;
was deleted from RAW_PUTCHAR, but the utf8_handle_comb function in
encode.c was not adapted. Since then, combining characters cannot
have worked. Do you have a local patch for this?
> With that patch I now get "ÿ " after every wide character in the
> output. The beginning now looks like this for me (in the hope it will
> be passed properly through mail):
>
> 円ᆆᆿÿ 忿ᇎᆿÿ 忘ᆿᆿÿ 忿ᆾᆿÿ 応ᆿᆿÿ 忿ᆷᆿÿ 忑ᆿᆿÿ 忿ᇠᆿÿ 冺ᆿᆿÿ 忿ᇇᆿÿ 忟ᆿᆿÿ 忿ᆺᆿÿ 忳ᆿᆿÿ 忿ᅳᆿÿ 忣ᆿᆿÿ
> 忿ᇯᆿÿ 忇ᆿᆿÿ 忿ᇅᆿÿ
>
> Which reminds me a lot of
> https://savannah.gnu.org/bugs/index.php?31336 aka
> https://bugs.debian.org/600246 but made worse.
The patch is actually not 100% correct. The double width combining chars
should only be in the 0xdf00 - 0xdfff range.
But there's also the underlying issue that comb_tofront() moves entries
between the two lists. So here's a revised patch:
diff --git a/src/display.c b/src/display.c
index 0ec6c33..8a85b90 100644
--- a/src/display.c
+++ b/src/display.c
@@ -437,7 +437,7 @@ static void RAW_PUTCHAR(uint32_t c)
if (D_x == D_width)
D_x += D_AM ? 1 : -1;
D_mbcs = 0;
- } else if (utf8_isdouble(c)) {
+ } else if (utf8_isdouble(c) || (c >= 0xdf00 && c < 0xe000)) {
D_mbcs = c;
D_x++;
return;
diff --git a/src/encoding.c b/src/encoding.c
index 11c3c41..ed24d64 100644
--- a/src/encoding.c
+++ b/src/encoding.c
@@ -35,7 +35,7 @@
static int encmatch(char *, char *);
static int recode_char(int, int, int);
static int recode_char_to_encoding(int, int);
-static void comb_tofront(int, int);
+static void comb_tofront(int);
static int recode_char_dw(int, int *, int, int);
static int recode_char_dw_to_encoding(int, int *, int);
@@ -1105,9 +1105,10 @@ bool utf8_iscomb(uint32_t c)
return bisearch(c, combining, ARRAY_SIZE(combining) - 1);
}
-static void comb_tofront(int root, int i)
+static void comb_tofront(int i)
{
for (;;) {
+ int root = i >= 0x700 ? 0x801 : 0x800;
combchars[combchars[i]->prev]->next = combchars[i]->next;
combchars[combchars[i]->next]->prev = combchars[i]->prev;
combchars[i]->next = combchars[root]->next;
@@ -1162,9 +1163,9 @@ void utf8_handle_comb(unsigned int c, struct mchar *mc)
if (i == combchars[root]->c2) {
/* full, recycle old entry */
if (c1 >= 0xd800 && c1 < 0xe000)
- comb_tofront(root, c1 - 0xd800);
+ comb_tofront(c1 - 0xd800);
i = combchars[root]->prev;
- if (c1 == i + 0xd800) {
+ if (i == 0x800 || i == 0x801 || c1 == i + 0xd800) {
/* completely full, can't recycle */
mc->image = '?';
mc->font = 0;
@@ -1180,9 +1181,9 @@ void utf8_handle_comb(unsigned int c, struct mchar *mc)
}
combchars[i]->c1 = c1;
combchars[i]->c2 = c;
- mc->image = i & 0xff;
- mc->font = (i >> 8) + 0xd8;
- comb_tofront(root, i);
+ mc->image = 0xd800 + i;
+ mc->font = 0;
+ comb_tofront(i);
}
static int encmatch(char *s1, char *s2)
Cheers,
Michael.
--
Michael Schroeder SUSE Software Solutions Germany GmbH
m...@suse.de GF: Felix Imendoerffer HRB 36809, AG Nuernberg
main(_){while(_=~getchar())putchar(~_-1/(~(_|32)/13*2-11)*13);}
