[788] in BarnOwl Developers
[D-O-H] r792 - branches/barnowl_unicode/owl
daemon@ATHENA.MIT.EDU (asedeno@MIT.EDU)
Thu Oct 29 18:09:44 2009
Resent-From: nelhage@mit.edu
Resent-To: barnowl-dev-mtg@charon.mit.edu
To: dirty-owl-hackers@mit.edu
From: asedeno@MIT.EDU
Reply-to: dirty-owl-hackers@MIT.EDU
Date: Wed, 2 Jan 2008 02:42:06 -0500 (EST)
Author: asedeno
Date: 2008-01-02 02:42:05 -0500 (Wed, 02 Jan 2008)
New Revision: 792
Added:
branches/barnowl_unicode/owl/wcwidth.c
Modified:
branches/barnowl_unicode/owl/Makefile.in
branches/barnowl_unicode/owl/editwin.c
branches/barnowl_unicode/owl/fmtext.c
branches/barnowl_unicode/owl/functions.c
branches/barnowl_unicode/owl/keymap.c
branches/barnowl_unicode/owl/message.c
branches/barnowl_unicode/owl/owl.c
branches/barnowl_unicode/owl/text.c
branches/barnowl_unicode/owl/viewwin.c
Log:
unicode / glib branch
text entry:
* first pass at utf-8 text entry. This is not yet complete, and it certainly has bugs.
The following is an incomplete list of functions that will probably misbehave if you use them.
- owl_editwin_move_to_nextword()
- owl_editwin_move_to_previousword()
- owl_editwin_delete_nextword()
- owl_editwin_delete_previousword()
- owl_editwin_delete_to_endofline()
- owl_editwin_fill_paragraph()
format text:
* owl_fmtext_curs_waddstr() contract restored to match trunk.
* owl_fmtext_curs_waddstr_without_search() added.
misc:
* Importing Markus Kuhn's wcwidth.c from
http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
* Change wcwidth() calls to mk_wcwidth()
Modified: branches/barnowl_unicode/owl/Makefile.in
===================================================================
--- branches/barnowl_unicode/owl/Makefile.in 2008-01-01 03:38:43 UTC (rev 791)
+++ branches/barnowl_unicode/owl/Makefile.in 2008-01-02 07:42:05 UTC (rev 792)
@@ -25,7 +25,7 @@
regex.c history.c view.c dict.c variable.c filterelement.c pair.c \
keypress.c keymap.c keybinding.c cmd.c context.c zcrypt.c \
aim.c buddy.c buddylist.c timer.c style.c stylefunc.c errqueue.c \
- zbuddylist.c muxevents.c popexec.c obarray.c
+ zbuddylist.c muxevents.c popexec.c obarray.c wcwidth.c
OWL_SRC = owl.c
TESTER_SRC = tester.c
Modified: branches/barnowl_unicode/owl/editwin.c
===================================================================
--- branches/barnowl_unicode/owl/editwin.c 2008-01-01 03:38:43 UTC (rev 791)
+++ branches/barnowl_unicode/owl/editwin.c 2008-01-02 07:42:05 UTC (rev 792)
@@ -142,10 +142,11 @@
e->buffx=0;
e->buffy=0;
owl_editwin_overwrite_string(e, text);
+ owl_editwin_overwrite_char(e, '\0');
e->lock=strlen(text);
/* if (text[e->lock-1]=='\n') e->lock--; */
- e->buffx=x;
- e->buffy=y;
+ /* e->buffx=x; */
+ /* e->buffy=y; */
owl_editwin_adjust_for_locktext(e);
owl_editwin_redisplay(e, 0);
}
@@ -250,60 +251,89 @@
wmove(e->curswin, 0, 0);
/* start at topline */
- ptr1=e->buff;
- for (i=0; i<e->topline; i++) {
- ptr2=strchr(ptr1, '\n');
+ ptr1 = e->buff;
+ for (i = 0; i < e->topline; i++) {
+ ptr2 = strchr(ptr1, '\n');
if (!ptr2) {
/* we're already on the last line */
break;
}
- ptr1=ptr2+1;
+ ptr1 = ptr2 + 1;
}
/* ptr1 now stores the starting point */
/* find the ending point and store it in ptr3 */
- ptr2=ptr1;
- ptr3=ptr1;
- for (i=0; i<e->winlines; i++) {
- ptr3=strchr(ptr2, '\n');
+ ptr2 = ptr1;
+ ptr3 = ptr1;
+ for (i = 0; i < e->winlines; i++) {
+ ptr3 = strchr(ptr2, '\n');
if (!ptr3) {
/* we've hit the last line */
/* print everything to the end */
- ptr3=e->buff+e->bufflen-1;
+ ptr3 = e->buff + e->bufflen - 1;
ptr3--;
break;
}
- ptr2=ptr3+1;
+ ptr2 = ptr3 + 1;
}
- ptr3+=2;
+ ptr3 += 2;
- buff=owl_malloc(ptr3-ptr1+50);
- strncpy(buff, ptr1, ptr3-ptr1);
- buff[ptr3-ptr1]='\0';
- if (e->echochar=='\0') {
+ buff = owl_malloc(ptr3 - ptr1 + 50);
+ strncpy(buff, ptr1, ptr3 - ptr1);
+ buff[ptr3 - ptr1] = '\0';
+ if (e->echochar == '\0') {
waddstr(e->curswin, buff);
} else {
/* translate to echochar, *except* for the locktext */
int len;
- int dolocklen=e->lock-(ptr1-e->buff);
+ int dolocklen = e->lock - (ptr1 - e->buff);
- for (i=0; i<dolocklen; i++) {
+ for (i = 0; i < dolocklen; i++) {
waddch(e->curswin, buff[i]);
}
- len=strlen(buff);
- for (i=0; i<len-dolocklen; i++) {
+ len = strlen(buff);
+ for (i = 0; i < len-dolocklen; i++) {
waddch(e->curswin, e->echochar);
}
}
- wmove(e->curswin, e->buffy-e->topline, e->buffx);
+ wmove(e->curswin, e->buffy-e->topline, e->buffx + _owl_editwin_cursor_adjustment(e));
wnoutrefresh(e->curswin);
- if (update==1) {
+ if (update == 1) {
doupdate();
}
owl_free(buff);
}
+/* Remove n bytes at cursor. */
+void _owl_editwin_remove_bytes(owl_editwin *e, int n) /*noproto*/
+{
+ int i = _owl_editwin_get_index_from_xy(e) + n;
+ for (; i < e->bufflen; i++) {
+ e->buff[i-n] = e->buff[i];
+ }
+
+ e->bufflen -= n;
+ e->buff[e->bufflen] = '\0';
+}
+/* Insert n bytes at cursor.*/
+void _owl_editwin_insert_bytes(owl_editwin *e, int n) /*noproto*/
+{
+ int i, z;
+
+ if ((e->bufflen + n) > (e->allocated - 5)) {
+ _owl_editwin_addspace(e);
+ }
+ e->bufflen += n;
+ e->buff[e->bufflen] = '\0';
+
+ z = _owl_editwin_get_index_from_xy(e);
+ for (i = e->bufflen - 1; i > z; i--) {
+ e->buff[i] = e->buff[i - n];
+ }
+}
+
+
/* linewrap the word just before the cursor.
* returns 0 on success
* returns -1 if we could not wrap.
@@ -312,19 +342,19 @@
{
int i, z;
- z=_owl_editwin_get_index_from_xy(e);
+ z = _owl_editwin_get_index_from_xy(e);
/* move back and line wrap the previous word */
- for (i=z-1; ; i--) {
+ for (i = z - 1; ; i--) {
/* move back until you find a space or hit the beginning of the line */
- if (e->buff[i]==' ') {
+ if (e->buff[i] == ' ') {
/* replace the space with a newline */
- e->buff[i]='\n';
+ e->buff[i] = '\n';
e->buffy++;
- e->buffx=z-i-1;
+ e->buffx = z - i - 1;
/* were we on the last line */
return(0);
- } else if (e->buff[i]=='\n' || i<=e->lock) {
- /* we hit the begginning of the line or the buffer, we cannot
+ } else if (e->buff[i] == '\n' || i <= e->lock) {
+ /* we hit the beginning of the line or the buffer, we cannot
* wrap.
*/
return(-1);
@@ -335,102 +365,108 @@
/* insert a character at the current point (shift later
* characters over)
*/
-void owl_editwin_insert_char(owl_editwin *e, char c)
+void owl_editwin_insert_char(owl_editwin *e, gunichar c)
{
+ int z, i, ret, len;
+ char tmp[6];
+ memset(tmp, '\0', 6);
- int z, i, ret;
-
/* \r is \n */
- if (c=='\r') {
- c='\n';
+ if (c == '\r') {
+ c = '\n';
}
- if (c=='\n' && e->style==OWL_EDITWIN_STYLE_ONELINE) {
+ if (c == '\n' && e->style == OWL_EDITWIN_STYLE_ONELINE) {
/* perhaps later this will change some state that allows the string
to be read */
return;
}
+ g_unichar_to_utf8(c, tmp);
+ len = strlen(tmp);
+
/* make sure there is enough memory for the new text */
- if ((e->bufflen+1) > (e->allocated-5)) {
+ if ((e->bufflen + len) > (e->allocated - 5)) {
_owl_editwin_addspace(e);
}
/* get the insertion point */
- z=_owl_editwin_get_index_from_xy(e);
+ z = _owl_editwin_get_index_from_xy(e);
/* If we're going to insert at the last column do word wrapping, unless it's a \n */
- if ((e->buffx+1==e->wrapcol) && (c!='\n')) {
- ret=_owl_editwin_linewrap_word(e);
- if (ret==-1) {
+ if ((e->buffx + 1 == e->wrapcol) && (c != '\n')) {
+ ret = _owl_editwin_linewrap_word(e);
+ if (ret == -1) {
/* we couldn't wrap, insert a hard newline instead */
owl_editwin_insert_char(e, '\n');
}
}
- z=_owl_editwin_get_index_from_xy(e);
/* shift all the other characters right */
- for (i=e->bufflen; i>z; i--) {
- e->buff[i]=e->buff[i-1];
+ _owl_editwin_insert_bytes(e, len);
+
+ /* insert the new character */
+ for(i = 0; i < len; i++) {
+ e->buff[z + i] = tmp[i];
}
- /* insert the new one */
- e->buff[z]=c;
-
/* housekeeping */
- e->bufflen++;
- e->buff[e->bufflen]='\0';
+ e->bufflen += len;
+ e->buff[e->bufflen] = '\0';
/* advance the cursor */
- if (c=='\n') {
- e->buffx=0;
- e->buffy++;
- } else {
- e->buffx++;
- }
+ z += len;
+ _owl_editwin_set_xy_by_index(e, z);
}
/* overwrite the character at the current point with 'c' */
-void owl_editwin_overwrite_char(owl_editwin *e, char c)
+void owl_editwin_overwrite_char(owl_editwin *e, gunichar c)
{
- int z;
+ int z, oldlen, newlen, i;
+ char tmp[6];
+ memset(tmp, '\0', 6);
/* \r is \n */
- if (c=='\r') {
- c='\n';
+ if (c == '\r') {
+ c = '\n';
}
- if (c=='\n' && e->style==OWL_EDITWIN_STYLE_ONELINE) {
+ if (c == '\n' && e->style == OWL_EDITWIN_STYLE_ONELINE) {
/* perhaps later this will change some state that allows the string
to be read */
return;
}
- z=_owl_editwin_get_index_from_xy(e);
+ g_unichar_to_utf8(c, tmp);
+ newlen = strlen(tmp);
- /* only if we are at the end of the buffer do we create new space */
- if (z==e->bufflen) {
- if ((e->bufflen+1) > (e->allocated-5)) {
- _owl_editwin_addspace(e);
- }
+ z = _owl_editwin_get_index_from_xy(e);
+ {
+ char *t = g_utf8_find_next_char(e->buff + z, NULL);
+ oldlen = (t ? (t - (e->buff + z)) : 1);
}
-
- e->buff[z]=c;
- /* housekeeping if we are at the end of the buffer */
- if (z==e->bufflen) {
- e->bufflen++;
- e->buff[e->bufflen]='\0';
+ if ((e->bufflen + newlen - oldlen + 1) > (e->allocated - 5)) {
+ _owl_editwin_addspace(e);
}
- /* advance the cursor */
- if (c=='\n') {
- e->buffx=0;
- e->buffy++;
- } else {
- e->buffx++;
+ if (oldlen > newlen) {
+ _owl_editwin_remove_bytes(e, oldlen-newlen);
}
+ else /* oldlen < newlen */ {
+ _owl_editwin_insert_bytes(e, newlen-oldlen);
+ }
+ /* Overwrite the old char*/
+ for (i = 0; i < newlen; i++) {
+ e->buff[z+i] = tmp[i];
+ }
+
+ /* housekeeping */
+ e->buff[e->bufflen] = '\0';
+ /* advance the cursor */
+ z += newlen;
+ _owl_editwin_set_xy_by_index(e, z);
}
/* delete the character at the current point, following chars
@@ -438,20 +474,25 @@
*/
void owl_editwin_delete_char(owl_editwin *e)
{
- int z, i;
+ int z;
+ char *p1, *p2;
+ gunichar c;
- if (e->bufflen==0) return;
+ if (e->bufflen == 0) return;
/* get the deletion point */
- z=_owl_editwin_get_index_from_xy(e);
+ z = _owl_editwin_get_index_from_xy(e);
- if (z==e->bufflen) return;
+ if (z == e->bufflen) return;
- for (i=z; i<e->bufflen; i++) {
- e->buff[i]=e->buff[i+1];
+ p1 = e->buff + z;
+ p2 = g_utf8_next_char(p1);
+ c = g_utf8_get_char(p2);
+ while (g_unichar_ismark(c)) {
+ p2 = g_utf8_next_char(p2);
+ c = g_utf8_get_char(p2);
}
- e->bufflen--;
- e->buff[e->bufflen]='\0';
+ _owl_editwin_remove_bytes(e, p2-p1);
}
/* Swap the character at point with the character at point-1 and
@@ -462,27 +503,45 @@
void owl_editwin_transpose_chars(owl_editwin *e)
{
int z;
- char tmp;
+ char *p1, *p2, *p3, *tmp;
- if (e->bufflen==0) return;
+ if (e->bufflen == 0) return;
/* get the cursor point */
- z=_owl_editwin_get_index_from_xy(e);
+ z = _owl_editwin_get_index_from_xy(e);
- if (z==e->bufflen) {
+ if (z == e->bufflen) {
/* point is after last character */
z--;
}
- if (z-1 < e->lock) {
+ if (z - 1 < e->lock) {
/* point is at beginning of buffer, do nothing */
return;
}
- tmp=e->buff[z];
- e->buff[z]=e->buff[z-1];
- e->buff[z-1]=tmp;
- owl_editwin_key_right(e);
+ /* Transpose two utf-8 unicode glyphs. */
+ p1 = e->buff + z;
+
+ p2 = g_utf8_find_next_char(p1, NULL);
+ while (p2 != NULL && g_unichar_ismark(g_utf8_get_char(p2))) {
+ p2 = g_utf8_find_next_char(p2, NULL);
+ }
+ if (p2 == NULL) return;
+
+ p3 = g_utf8_find_prev_char(e->buff, p1);
+ while (p3 != NULL && g_unichar_ismark(g_utf8_get_char(p3))) {
+ p3 = g_utf8_find_prev_char(p3, NULL);
+ }
+ if (p3 == NULL) return;
+
+ tmp = owl_malloc(p2 - p3 + 5);
+ *tmp = '\0';
+ strncat(tmp, p1, p2 - p1);
+ strncat(tmp, p3, p1 - p3);
+ strncpy(p3, tmp, p2 - p3);
+ owl_free(tmp);
+ _owl_editwin_set_xy_by_index(e, p3 - e->buff);
}
/* insert 'string' at the current point, later text is shifted
@@ -490,12 +549,19 @@
*/
void owl_editwin_insert_string(owl_editwin *e, char *string)
{
- int i, j;
-
- j=strlen(string);
- for (i=0; i<j; i++) {
- owl_editwin_insert_char(e, string[i]);
+ char *p;
+ gunichar c;
+ if (!g_utf8_validate(string, -1, NULL)) {
+ owl_function_debugmsg("owl_editwin_insert_string: received non-utf-8 string.");
+ return;
}
+ p = string;
+ c = g_utf8_get_char(p);
+ while (c) {
+ owl_editwin_process_char(e, c);
+ p = g_utf8_next_char(p);
+ c = g_utf8_get_char(p);
+ }
}
/* write 'string' at the current point, overwriting text that is
@@ -504,12 +570,20 @@
void owl_editwin_overwrite_string(owl_editwin *e, char *string)
{
- int i, j;
+ char *p;
+ gunichar c;
- j=strlen(string);
- for (i=0; i<j; i++) {
- owl_editwin_overwrite_char(e, string[i]);
+ if (!g_utf8_validate(string, -1, NULL)) {
+ owl_function_debugmsg("owl_editwin_overwrite_string: received non-utf-8 string.");
+ return;
}
+ p = string;
+ c = g_utf8_get_char(p);
+ while (c) {
+ owl_editwin_overwrite_char(e, c);
+ p = g_utf8_next_char(p);
+ c = g_utf8_get_char(p);
+ }
}
/* get the index into e->buff for the current cursor
@@ -519,57 +593,103 @@
{
int i;
char *ptr1, *ptr2;
+ gunichar c;
- if (e->bufflen==0) return(0);
+ if (e->bufflen == 0) return(0);
/* first go to the yth line */
- ptr1=e->buff;
- for (i=0; i<e->buffy; i++) {
- ptr2=strchr(ptr1, '\n');
+ ptr1 = e->buff;
+ for (i = 0; i < e->buffy; i++) {
+ ptr2= strchr(ptr1, '\n');
if (!ptr2) {
/* we're already on the last line */
break;
}
- ptr1=ptr2+1;
+ ptr1 = ptr2 + 1;
}
- /* now go to the xth character */
- ptr2=strchr(ptr1, '\n');
- if (!ptr2) {
- ptr2=e->buff+e->bufflen;
+ /* now go to the xth cell */
+ ptr2 = ptr1;
+ i = 0;
+ while (ptr2 != NULL && i < e->buffx && (ptr2 - e->buff) < e->bufflen) {
+ c = g_utf8_get_char(ptr2);
+ i += (c == '\n' ? 1 : mk_wcwidth(c));
+ ptr2 = g_utf8_next_char(ptr2);
}
+ while(ptr2 != NULL && g_unichar_ismark(g_utf8_get_char(ptr2))) {
+ ptr2 = g_utf8_next_char(ptr2);
+ }
+ if (ptr2 == NULL) return e->bufflen;
+ return(ptr2 - e->buff);
+}
- if ((ptr2-ptr1) < e->buffx) {
- ptr1=ptr2-1;
- } else {
- ptr1+=e->buffx;
+void _owl_editwin_set_xy_by_index(owl_editwin *e, int index)
+{
+ char *ptr1, *ptr2, *target;
+ gunichar c;
+
+ e->buffx = 0;
+ e->buffy = 0;
+
+ ptr1 = e->buff;
+ target = ptr1 + index;
+ /* target sanitizing */
+ if ((target[0] & 0x80) && (~target[0] & 0x40)) {
+ /* middle of a utf-8 character, back up to previous character. */
+ target = g_utf8_find_prev_char(e->buff, target);
}
+ c = g_utf8_get_char(target);
+ while (g_unichar_ismark(c) && target > e->buff) {
+ /* Adjust the target off of combining characters and the like. */
+ target = g_utf8_find_prev_char(e->buff, target);
+ c = g_utf8_get_char(target);
+ }
+ /* If we start with a mark, something is wrong.*/
+ if (g_unichar_ismark(c)) return;
- /* printf("DEBUG: index is %i\r\n", ptr1-e->buff); */
- return(ptr1-e->buff);
+ /* Now our target should be acceptable. */
+ ptr2 = strchr(ptr1, '\n');
+ while (ptr2 != NULL && ptr2 < target) {
+ e->buffy++;
+ ptr1 = ptr2 + 1;
+ ptr2 = strchr(ptr1, '\n');
+ }
+ ptr2 = ptr1;
+ while (ptr2 != NULL && ptr2 < target) {
+ c = g_utf8_get_char(ptr2);
+ e->buffx += mk_wcwidth(c);
+ ptr2 = g_utf8_next_char(ptr2);
+ }
}
-void _owl_editwin_set_xy_by_index(owl_editwin *e, int index)
+int _owl_editwin_cursor_adjustment(owl_editwin *e)
{
- int z, i;
+ char *ptr1, *ptr2;
+ gunichar c;
+ int x, i;
- z=_owl_editwin_get_index_from_xy(e);
- if (index>z) {
- for (i=0; i<index-z; i++) {
- owl_editwin_key_right(e);
- }
- } else if (index<z) {
- for (i=0; i<z-index; i++) {
- owl_editwin_key_left(e);
- }
+ ptr1 = e->buff;
+ ptr2 = strchr(ptr1, '\n');
+ for (i = 0; ptr2 != NULL && i < e->buffy; i++) {
+ ptr1 = ptr2 + 1;
+ ptr2 = strchr(ptr1, '\n');
}
+ ptr2 = ptr1;
+ x = 0;
+ while (ptr2 != NULL && x < e->buffx) {
+ if (*ptr2 == '\n') return 0;
+ c = g_utf8_get_char(ptr2);
+ x += mk_wcwidth(c);
+ ptr2 = g_utf8_next_char(ptr2);
+ }
+ return x - e->buffx;
}
void owl_editwin_adjust_for_locktext(owl_editwin *e)
{
/* if we happen to have the cursor over locked text
* move it to be out of the locktext region */
- if (_owl_editwin_get_index_from_xy(e)<e->lock) {
+ if (_owl_editwin_get_index_from_xy(e) < e->lock) {
_owl_editwin_set_xy_by_index(e, e->lock);
}
}
@@ -589,8 +709,8 @@
void owl_editwin_key_up(owl_editwin *e)
{
if (e->buffy > 0) e->buffy--;
- if (e->buffx >= owl_editwin_get_numchars_on_line(e, e->buffy)) {
- e->buffx=owl_editwin_get_numchars_on_line(e, e->buffy);
+ if (e->buffx >= owl_editwin_get_numcells_on_line(e, e->buffy)) {
+ e->buffx=owl_editwin_get_numcells_on_line(e, e->buffy);
}
/* do we need to scroll? */
@@ -607,8 +727,8 @@
if (e->buffy+1 < owl_editwin_get_numlines(e)) e->buffy++;
/* if we're past the last character move back */
- if (e->buffx >= owl_editwin_get_numchars_on_line(e, e->buffy)) {
- e->buffx=owl_editwin_get_numchars_on_line(e, e->buffy);
+ if (e->buffx >= owl_editwin_get_numcells_on_line(e, e->buffy)) {
+ e->buffx=owl_editwin_get_numcells_on_line(e, e->buffy);
}
/* do we need to scroll? */
@@ -622,17 +742,19 @@
void owl_editwin_key_left(owl_editwin *e)
{
- /* move left if we can, and maybe up a line */
- if (e->buffx>0) {
- e->buffx--;
- } else if (e->buffy>0) {
- e->buffy--;
- e->buffx=owl_editwin_get_numchars_on_line(e, e->buffy);
+ int i;
+ char * p;
+ i = _owl_editwin_get_index_from_xy(e);
+ p = e->buff + i;
+ p = g_utf8_find_prev_char(e->buff, p);
+ while (p && g_unichar_ismark(g_utf8_get_char(p))) {
+ p = g_utf8_find_prev_char(e->buff, p);
}
+ if (p == NULL) p = e->buff;
+ _owl_editwin_set_xy_by_index(e, p - e->buff);
- /* do we need to scroll up? */
- if (e->buffy-e->topline < 0) {
- e->topline-=e->winlines/2;
+ if (e->buffy - e->topline < 0) {
+ e->topline -= e->winlines / 2;
}
/* make sure to avoid locktext */
@@ -642,27 +764,29 @@
void owl_editwin_key_right(owl_editwin *e)
{
int i;
-
- /* move right if we can, and skip down a line if needed */
- i=owl_editwin_get_numchars_on_line(e, e->buffy);
- if (e->buffx < i) {
- e->buffx++;
- /* } else if (e->buffy+1 < owl_editwin_get_numlines(e)) { */
- } else if (_owl_editwin_get_index_from_xy(e) < e->bufflen) {
- if (e->style==OWL_EDITWIN_STYLE_MULTILINE) {
- e->buffx=0;
- e->buffy++;
- }
+ char * p;
+ i = _owl_editwin_get_index_from_xy(e);
+ p = e->buff + i;
+ p = g_utf8_find_next_char(p, NULL);
+ while (p && g_unichar_ismark(g_utf8_get_char(p))) {
+ p = g_utf8_find_next_char(p, NULL);
}
+ if (p == NULL) {
+ _owl_editwin_set_xy_by_index(e, e->bufflen);
+ }
+ else {
+ _owl_editwin_set_xy_by_index(e, p - e->buff);
+ }
/* do we need to scroll down? */
- if (e->buffy-e->topline >= e->winlines) {
- e->topline+=e->winlines/2;
+ if (e->buffy - e->topline >= e->winlines) {
+ e->topline += e->winlines / 2;
}
}
void owl_editwin_move_to_nextword(owl_editwin *e)
{
+ /* asedeno: needs fixing for utf-8*/
int i, x;
/* if we're starting on a space, find the first non-space */
@@ -702,6 +826,7 @@
*/
void owl_editwin_move_to_previousword(owl_editwin *e)
{
+ /* asedeno: needs fixing for utf-8*/
int i, x;
/* are we already at the beginning of the word? */
@@ -737,6 +862,7 @@
void owl_editwin_delete_nextword(owl_editwin *e)
{
+ /* asedeno: needs fixing for utf-8*/
int z;
if (e->bufflen==0) return;
@@ -767,6 +893,7 @@
void owl_editwin_delete_previousword(owl_editwin *e)
{
+ /* asedeno: needs fixing for utf-8*/
/* go backwards to the last non-space character, then delete chars */
int i, startpos, endpos;
@@ -780,9 +907,10 @@
void owl_editwin_delete_to_endofline(owl_editwin *e)
{
+ /* asedeno: needs fixing for utf-8*/
int i;
- if (owl_editwin_get_numchars_on_line(e, e->buffy)>e->buffx) {
+ if (owl_editwin_get_numchars_on_line(e, e->buffy) > e->buffx) {
/* normal line */
i=_owl_editwin_get_index_from_xy(e);
while(i < e->bufflen) {
@@ -803,7 +931,7 @@
void owl_editwin_move_to_line_end(owl_editwin *e)
{
- e->buffx=owl_editwin_get_numchars_on_line(e, e->buffy);
+ e->buffx=owl_editwin_get_numcells_on_line(e, e->buffy);
}
void owl_editwin_move_to_line_start(owl_editwin *e)
@@ -816,7 +944,7 @@
{
/* go to last char */
e->buffy=owl_editwin_get_numlines(e)-1;
- e->buffx=owl_editwin_get_numchars_on_line(e, e->buffy);
+ e->buffx=owl_editwin_get_numcells_on_line(e, e->buffy);
owl_editwin_key_right(e);
/* do we need to scroll? */
@@ -840,6 +968,7 @@
void owl_editwin_fill_paragraph(owl_editwin *e)
{
+ /* asedeno: needs fixing for utf-8*/
int i, save;
/* save our starting point */
@@ -856,13 +985,13 @@
/* main loop */
while (1) {
- i=_owl_editwin_get_index_from_xy(e);
+ i = _owl_editwin_get_index_from_xy(e);
/* bail if we hit the end of the buffer */
- if (i>=e->bufflen) break;
+ if (i >= e->bufflen || e->buff[i] == '\0') break;
/* bail if we hit the end of the paragraph */
- if (e->buff[i]=='\n' && e->buff[i+1]=='\n') break;
+ if (e->buff[i] == '\n' && e->buff[i+1] == '\n') break;
/* if we've travelled too far, linewrap */
if ((e->buffx) >= e->fillcol) {
@@ -870,21 +999,21 @@
}
/* did we hit the end of a line too soon? */
- i=_owl_editwin_get_index_from_xy(e);
- if (e->buff[i]=='\n' && e->buffx<e->fillcol-1) {
+ i = _owl_editwin_get_index_from_xy(e);
+ if (e->buff[i] == '\n' && e->buffx < e->fillcol - 1) {
/* ********* we need to make sure we don't pull in a word that's too long ***********/
e->buff[i]=' ';
}
/* fix spacing */
- i=_owl_editwin_get_index_from_xy(e);
- if (e->buff[i]==' ' && e->buff[i+1]==' ') {
- if (e->buff[i-1]=='.' || e->buff[i-1]=='!' || e->buff[i-1]=='?') {
+ i = _owl_editwin_get_index_from_xy(e);
+ if (e->buff[i] == ' ' && e->buff[i+1] == ' ') {
+ if (e->buff[i-1] == '.' || e->buff[i-1] == '!' || e->buff[i-1] == '?') {
owl_editwin_key_right(e);
} else {
owl_editwin_delete_char(e);
/* if we did this ahead of the save point, adjust it */
- if (i<save) save--;
+ if (i < save) save--;
}
} else {
owl_editwin_key_right(e);
@@ -910,25 +1039,33 @@
int owl_editwin_check_dotsend(owl_editwin *e)
{
- int i;
+ char *p, *p_n, *p_p;
+ gunichar c;
if (!e->dotsend) return(0);
- for (i=e->bufflen-1; i>0; i--) {
- if (e->buff[i] == '.'
- && (e->buff[i-1] == '\n' || e->buff[i-1] == '\r')
- && (e->buff[i+1] == '\n' || e->buff[i+1] == '\r')) {
- e->bufflen = i;
- e->buff[i] = '\0';
+
+ p = g_utf8_find_prev_char(e->buff, e->buff + e->bufflen);
+ p_n = g_utf8_find_next_char(p, NULL);
+ p_p = g_utf8_find_prev_char(e->buff, p);
+ c = g_utf8_get_char(p);
+ while (p != NULL) {
+ if (*p == '.'
+ && p_p != NULL && (*p_p == '\n' || *p_p == '\r')
+ && p_n != NULL && (*p_n == '\n' || *p_n == '\r')) {
+ e->bufflen = p - e->buff;
+ e->buff[e->bufflen] = '\0';
return(1);
}
- if (!isspace((int) e->buff[i])) {
- return(0);
- }
+ if (c != '\0' && !g_unichar_isspace(c)) return(0);
+ p_n = p;
+ p = p_p;
+ c = g_utf8_get_char(p);
+ p_p = g_utf8_find_prev_char(e->buff, p);
}
return(0);
}
-void owl_editwin_post_process_char(owl_editwin *e, int j)
+void owl_editwin_post_process_char(owl_editwin *e, gunichar j)
{
/* check if we need to scroll down */
if (e->buffy-e->topline >= e->winlines) {
@@ -941,12 +1078,13 @@
owl_editwin_redisplay(e, 0);
}
-void owl_editwin_process_char(owl_editwin *e, int j)
+void owl_editwin_process_char(owl_editwin *e, gunichar j)
{
if (j == ERR) return;
- if (j>127 || ((j<32) && (j!=10) && (j!=13))) {
+ if (g_unichar_iscntrl(j) && (j != 10) && (j != 13)) {
return;
- } else {
+ }
+ else {
owl_editwin_insert_char(e, j);
}
}
@@ -974,14 +1112,48 @@
ptr1=ptr2+1;
}
- /* now go to the xth character */
- ptr2=strchr(ptr1, '\n');
- if (!ptr2) {
- return(e->buff + e->bufflen - ptr1);
+ /* now count characters */
+ i = 0;
+ ptr2 = ptr1;
+ while (ptr2 - e->buff < e->bufflen
+ && *ptr2 != '\n') {
+ ++i;
+ ptr2 = g_utf8_next_char(ptr2);
}
- return(ptr2-ptr1); /* don't count the newline for now */
+ return i;
}
+int owl_editwin_get_numcells_on_line(owl_editwin *e, int line)
+{
+ int i;
+ char *ptr1, *ptr2;
+ gunichar c;
+
+ if (e->bufflen==0) return(0);
+
+ /* first go to the yth line */
+ ptr1=e->buff;
+ for (i=0; i<line; i++) {
+ ptr2=strchr(ptr1, '\n');
+ if (!ptr2) {
+ /* we're already on the last line */
+ return(0);
+ }
+ ptr1=ptr2+1;
+ }
+
+ /* now count cells */
+ i = 0;
+ ptr2 = ptr1;
+ while (ptr2 - e->buff < e->bufflen
+ && *ptr2 != '\n') {
+ c = g_utf8_get_char(ptr2);
+ i += mk_wcwidth(c);
+ ptr2 = g_utf8_next_char(ptr2);
+ }
+ return i;
+}
+
int owl_editwin_get_numlines(owl_editwin *e)
{
return(owl_text_num_lines(e->buff));
Modified: branches/barnowl_unicode/owl/fmtext.c
===================================================================
--- branches/barnowl_unicode/owl/fmtext.c 2008-01-01 03:38:43 UTC (rev 791)
+++ branches/barnowl_unicode/owl/fmtext.c 2008-01-02 07:42:05 UTC (rev 792)
@@ -247,7 +247,7 @@
/* add the formatted text to the curses window 'w'. The window 'w'
* must already be initiatlized with curses
*/
-void owl_fmtext_curs_waddstr(owl_fmtext *f, WINDOW *w, int do_search)
+void _owl_fmtext_curs_waddstr(owl_fmtext *f, WINDOW *w, int do_search) /*noproto*/
{
/* char *tmpbuff; */
/* int position, trans1, trans2, trans3, len, lastsame; */
@@ -263,8 +263,10 @@
search_results = (do_search
? owl_fmtext_search(f, owl_global_get_search_string(&g))
- : NULL);
- if (search_results) search_len = strlen(owl_global_get_search_string(&g));
+ : 0);
+ search_len = (search_results
+ ? strlen(owl_global_get_search_string(&g))
+ : 0);
s = f->textbuff;
/* Set default attributes. */
attr = f->default_attrs;
@@ -349,7 +351,16 @@
}
}
+void owl_fmtext_curs_waddstr(owl_fmtext *f, WINDOW *w)
+{
+ _owl_fmtext_curs_waddstr(f, w, owl_global_is_search_active(&g));
+}
+void owl_fmtext_curs_waddstr_without_search(owl_fmtext *f, WINDOW *w)
+{
+ _owl_fmtext_curs_waddstr(f, w, 0);
+}
+
/* start with line 'aline' (where the first line is 0) and print
* 'lines' number of lines into 'out'
*/
@@ -412,11 +423,12 @@
col = 0;
st = 0;
padding = 0;
+ chwidth = 0;
ptr_c = ptr_s;
while(col <= bcol && ptr_c < ptr_e) {
gunichar c = g_utf8_get_char(ptr_c);
if (!_owl_fmtext_is_format_char(c)) {
- chwidth = wcwidth(c);
+ chwidth = mk_wcwidth(c);
if (col + chwidth > bcol)
break;
Modified: branches/barnowl_unicode/owl/functions.c
===================================================================
--- branches/barnowl_unicode/owl/functions.c 2008-01-01 03:38:43 UTC (rev 791)
+++ branches/barnowl_unicode/owl/functions.c 2008-01-02 07:42:05 UTC (rev 792)
@@ -2186,7 +2186,6 @@
void owl_function_start_command(char *line)
{
- int i, j;
owl_editwin *tw;
tw=owl_global_get_typwin(&g);
@@ -2197,10 +2196,7 @@
owl_editwin_set_locktext(tw, "command: ");
owl_global_set_needrefresh(&g);
- j=strlen(line);
- for (i=0; i<j; i++) {
- owl_editwin_process_char(tw, line[i]);
- }
+ owl_editwin_insert_string(tw, line);
owl_editwin_redisplay(tw, 0);
owl_context_set_editline(owl_global_get_context(&g), tw);
Modified: branches/barnowl_unicode/owl/keymap.c
===================================================================
--- branches/barnowl_unicode/owl/keymap.c 2008-01-01 03:38:43 UTC (rev 791)
+++ branches/barnowl_unicode/owl/keymap.c 2008-01-02 07:42:05 UTC (rev 792)
@@ -201,7 +201,7 @@
/* processes a keypress. returns 0 if the keypress was handled,
* 1 if not handled, -1 on error, and -2 if j==ERR. */
-int owl_keyhandler_process(owl_keyhandler *kh, int j)
+int owl_keyhandler_process(owl_keyhandler *kh, gunichar j)
{
owl_keymap *km;
owl_keybinding *kb;
Modified: branches/barnowl_unicode/owl/message.c
===================================================================
--- branches/barnowl_unicode/owl/message.c 2008-01-01 03:38:43 UTC (rev 791)
+++ branches/barnowl_unicode/owl/message.c 2008-01-02 07:42:05 UTC (rev 792)
@@ -539,7 +539,7 @@
owl_fmtext_colorize(&b, fgcolor);
owl_fmtext_colorizebg(&b, bgcolor);
- owl_fmtext_curs_waddstr(&b, win, owl_global_is_search_active(&g));
+ owl_fmtext_curs_waddstr(&b, win);
owl_fmtext_free(&a);
owl_fmtext_free(&b);
Modified: branches/barnowl_unicode/owl/owl.c
===================================================================
--- branches/barnowl_unicode/owl/owl.c 2008-01-01 03:38:43 UTC (rev 791)
+++ branches/barnowl_unicode/owl/owl.c 2008-01-02 07:42:05 UTC (rev 792)
@@ -69,7 +69,8 @@
WINDOW *recwin, *sepwin, *typwin, *msgwin;
owl_editwin *tw;
owl_popwin *pw;
- int j, ret, initialsubs, debug, argcsave, followlast;
+ int ret, initialsubs, debug, argcsave, followlast;
+ gunichar j;
int newmsgs, nexttimediff;
struct sigaction sigact;
char *configfile, *tty, *perlout, *perlerr, **argvsave, buff[LINE], startupmsg[LINE];
@@ -545,6 +546,30 @@
if (j==ERR) {
usleep(10000);
} else {
+ /* Pull in a full utf-8 character. */
+ if (j & 0x80) {
+ char utf8buf[7];
+ int bytes, i;
+ memset(utf8buf,'\0',7);
+ utf8buf[0] = j;
+
+ if (~j & 0x20) bytes = 2;
+ else if (~j & 0x10) bytes = 3;
+ else if (~j & 0x08) bytes = 4;
+ else if (~j & 0x04) bytes = 5;
+ else if (~j & 0x02) bytes = 6;
+ else bytes = 1; /* This won't validate */
+
+ for (i = 1; i < bytes; i++) {
+ utf8buf[i] = wgetch(typwin);
+ }
+ if (g_utf8_validate(utf8buf, -1, NULL)) {
+ j = g_utf8_get_char(utf8buf);
+ }
+ else {
+ j = ERR;
+ }
+ }
owl_global_update_lastinputtime(&g);
/* find and activate the current keymap.
* TODO: this should really get fixed by activating
Modified: branches/barnowl_unicode/owl/text.c
===================================================================
--- branches/barnowl_unicode/owl/text.c 2008-01-01 03:38:43 UTC (rev 791)
+++ branches/barnowl_unicode/owl/text.c 2008-01-02 07:42:05 UTC (rev 792)
@@ -76,8 +76,8 @@
ptr_c = ptr_s;
while(col < bcol && ptr_c < ptr_e) {
gunichar c = g_utf8_get_char(ptr_c);
- if (col + wcwidth(c) > bcol) break;
- col += wcwidth(c);
+ if (col + mk_wcwidth(c) > bcol) break;
+ col += mk_wcwidth(c);
ptr_c = g_utf8_next_char(ptr_c);
if (col >= acol) {
if (cnt == 0) {
Modified: branches/barnowl_unicode/owl/viewwin.c
===================================================================
--- branches/barnowl_unicode/owl/viewwin.c 2008-01-01 03:38:43 UTC (rev 791)
+++ branches/barnowl_unicode/owl/viewwin.c 2008-01-02 07:42:05 UTC (rev 792)
@@ -72,7 +72,7 @@
owl_fmtext_truncate_lines(&(v->fmtext), v->topline, v->winlines-BOTTOM_OFFSET, &fm1);
owl_fmtext_truncate_cols(&fm1, v->rightshift, v->wincols-1+v->rightshift, &fm2);
- owl_fmtext_curs_waddstr(&fm2, v->curswin, 0);
+ owl_fmtext_curs_waddstr_without_search(&fm2, v->curswin);
/* print the message at the bottom */
wmove(v->curswin, v->winlines-1, 0);
Added: branches/barnowl_unicode/owl/wcwidth.c
===================================================================
--- branches/barnowl_unicode/owl/wcwidth.c (rev 0)
+++ branches/barnowl_unicode/owl/wcwidth.c 2008-01-02 07:42:05 UTC (rev 792)
@@ -0,0 +1,309 @@
+/*
+ * This is an implementation of wcwidth() and wcswidth() (defined in
+ * IEEE Std 1002.1-2001) for Unicode.
+ *
+ * http://www.opengroup.org/onlinepubs/007904975/functions/wcwidth.html
+ * http://www.opengroup.org/onlinepubs/007904975/functions/wcswidth.html
+ *
+ * In fixed-width output devices, Latin characters all occupy a single
+ * "cell" position of equal width, whereas ideographic CJK characters
+ * occupy two such cells. Interoperability between terminal-line
+ * applications and (teletype-style) character terminals using the
+ * UTF-8 encoding requires agreement on which character should advance
+ * the cursor by how many cell positions. No established formal
+ * standards exist at present on which Unicode character shall occupy
+ * how many cell positions on character terminals. These routines are
+ * a first attempt of defining such behavior based on simple rules
+ * applied to data provided by the Unicode Consortium.
+ *
+ * For some graphical characters, the Unicode standard explicitly
+ * defines a character-cell width via the definition of the East Asian
+ * FullWidth (F), Wide (W), Half-width (H), and Narrow (Na) classes.
+ * In all these cases, there is no ambiguity about which width a
+ * terminal shall use. For characters in the East Asian Ambiguous (A)
+ * class, the width choice depends purely on a preference of backward
+ * compatibility with either historic CJK or Western practice.
+ * Choosing single-width for these characters is easy to justify as
+ * the appropriate long-term solution, as the CJK practice of
+ * displaying these characters as double-width comes from historic
+ * implementation simplicity (8-bit encoded characters were displayed
+ * single-width and 16-bit ones double-width, even for Greek,
+ * Cyrillic, etc.) and not any typographic considerations.
+ *
+ * Much less clear is the choice of width for the Not East Asian
+ * (Neutral) class. Existing practice does not dictate a width for any
+ * of these characters. It would nevertheless make sense
+ * typographically to allocate two character cells to characters such
+ * as for instance EM SPACE or VOLUME INTEGRAL, which cannot be
+ * represented adequately with a single-width glyph. The following
+ * routines at present merely assign a single-cell width to all
+ * neutral characters, in the interest of simplicity. This is not
+ * entirely satisfactory and should be reconsidered before
+ * establishing a formal standard in this area. At the moment, the
+ * decision which Not East Asian (Neutral) characters should be
+ * represented by double-width glyphs cannot yet be answered by
+ * applying a simple rule from the Unicode database content. Setting
+ * up a proper standard for the behavior of UTF-8 character terminals
+ * will require a careful analysis not only of each Unicode character,
+ * but also of each presentation form, something the author of these
+ * routines has avoided to do so far.
+ *
+ * http://www.unicode.org/unicode/reports/tr11/
+ *
+ * Markus Kuhn -- 2007-05-26 (Unicode 5.0)
+ *
+ * Permission to use, copy, modify, and distribute this software
+ * for any purpose and without fee is hereby granted. The author
+ * disclaims all warranties with regard to this software.
+ *
+ * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
+ */
+
+#include <wchar.h>
+
+static struct interval {
+ int first;
+ int last;
+};
+
+/* auxiliary function for binary search in interval table */
+static int bisearch(wchar_t ucs, const struct interval *table, int max) {
+ int min = 0;
+ int mid;
+
+ if (ucs < table[0].first || ucs > table[max].last)
+ return 0;
+ while (max >= min) {
+ mid = (min + max) / 2;
+ if (ucs > table[mid].last)
+ min = mid + 1;
+ else if (ucs < table[mid].first)
+ max = mid - 1;
+ else
+ return 1;
+ }
+
+ return 0;
+}
+
+
+/* The following two functions define the column width of an ISO 10646
+ * character as follows:
+ *
+ * - The null character (U+0000) has a column width of 0.
+ *
+ * - Other C0/C1 control characters and DEL will lead to a return
+ * value of -1.
+ *
+ * - Non-spacing and enclosing combining characters (general
+ * category code Mn or Me in the Unicode database) have a
+ * column width of 0.
+ *
+ * - SOFT HYPHEN (U+00AD) has a column width of 1.
+ *
+ * - Other format characters (general category code Cf in the Unicode
+ * database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
+ *
+ * - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
+ * have a column width of 0.
+ *
+ * - Spacing characters in the East Asian Wide (W) or East Asian
+ * Full-width (F) category as defined in Unicode Technical
+ * Report #11 have a column width of 2.
+ *
+ * - All remaining characters (including all printable
+ * ISO 8859-1 and WGL4 characters, Unicode control characters,
+ * etc.) have a column width of 1.
+ *
+ * This implementation assumes that wchar_t characters are encoded
+ * in ISO 10646.
+ */
+
+int mk_wcwidth(wchar_t ucs)
+{
+ /* sorted list of non-overlapping intervals of non-spacing characters */
+ /* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
+ static const struct interval combining[] = {
+ { 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
+ { 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
+ { 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 },
+ { 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 },
+ { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
+ { 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
+ { 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 },
+ { 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D },
+ { 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
+ { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD },
+ { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C },
+ { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
+ { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
+ { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
+ { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C },
+ { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D },
+ { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 },
+ { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 },
+ { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC },
+ { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
+ { 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
+ { 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
+ { 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
+ { 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
+ { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
+ { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
+ { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
+ { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
+ { 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
+ { 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F },
+ { 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
+ { 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
+ { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
+ { 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
+ { 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
+ { 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 },
+ { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 },
+ { 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF },
+ { 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 },
+ { 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F },
+ { 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
+ { 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
+ { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB },
+ { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
+ { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
+ { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
+ { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F },
+ { 0xE0100, 0xE01EF }
+ };
+
+ /* test for 8-bit control characters */
+ if (ucs == 0)
+ return 0;
+ if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
+ return -1;
+
+ /* binary search in table of non-spacing characters */
+ if (bisearch(ucs, combining,
+ sizeof(combining) / sizeof(struct interval) - 1))
+ return 0;
+
+ /* if we arrive here, ucs is not a combining or C0/C1 control character */
+
+ return 1 +
+ (ucs >= 0x1100 &&
+ (ucs <= 0x115f || /* Hangul Jamo init. consonants */
+ ucs == 0x2329 || ucs == 0x232a ||
+ (ucs >= 0x2e80 && ucs <= 0xa4cf &&
+ ucs != 0x303f) || /* CJK ... Yi */
+ (ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
+ (ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
+ (ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
+ (ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
+ (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
+ (ucs >= 0xffe0 && ucs <= 0xffe6) ||
+ (ucs >= 0x20000 && ucs <= 0x2fffd) ||
+ (ucs >= 0x30000 && ucs <= 0x3fffd)));
+}
+
+
+int mk_wcswidth(const wchar_t *pwcs, size_t n)
+{
+ int w, width = 0;
+
+ for (;*pwcs && n-- > 0; pwcs++)
+ if ((w = mk_wcwidth(*pwcs)) < 0)
+ return -1;
+ else
+ width += w;
+
+ return width;
+}
+
+
+/*
+ * The following functions are the same as mk_wcwidth() and
+ * mk_wcswidth(), except that spacing characters in the East Asian
+ * Ambiguous (A) category as defined in Unicode Technical Report #11
+ * have a column width of 2. This variant might be useful for users of
+ * CJK legacy encodings who want to migrate to UCS without changing
+ * the traditional terminal character-width behaviour. It is not
+ * otherwise recommended for general use.
+ */
+int mk_wcwidth_cjk(wchar_t ucs)
+{
+ /* sorted list of non-overlapping intervals of East Asian Ambiguous
+ * characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
+ static const struct interval ambiguous[] = {
+ { 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 },
+ { 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 },
+ { 0x00B6, 0x00BA }, { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 },
+ { 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 },
+ { 0x00E6, 0x00E6 }, { 0x00E8, 0x00EA }, { 0x00EC, 0x00ED },
+ { 0x00F0, 0x00F0 }, { 0x00F2, 0x00F3 }, { 0x00F7, 0x00FA },
+ { 0x00FC, 0x00FC }, { 0x00FE, 0x00FE }, { 0x0101, 0x0101 },
+ { 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011B, 0x011B },
+ { 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 },
+ { 0x0138, 0x0138 }, { 0x013F, 0x0142 }, { 0x0144, 0x0144 },
+ { 0x0148, 0x014B }, { 0x014D, 0x014D }, { 0x0152, 0x0153 },
+ { 0x0166, 0x0167 }, { 0x016B, 0x016B }, { 0x01CE, 0x01CE },
+ { 0x01D0, 0x01D0 }, { 0x01D2, 0x01D2 }, { 0x01D4, 0x01D4 },
+ { 0x01D6, 0x01D6 }, { 0x01D8, 0x01D8 }, { 0x01DA, 0x01DA },
+ { 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 },
+ { 0x02C4, 0x02C4 }, { 0x02C7, 0x02C7 }, { 0x02C9, 0x02CB },
+ { 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, { 0x02D8, 0x02DB },
+ { 0x02DD, 0x02DD }, { 0x02DF, 0x02DF }, { 0x0391, 0x03A1 },
+ { 0x03A3, 0x03A9 }, { 0x03B1, 0x03C1 }, { 0x03C3, 0x03C9 },
+ { 0x0401, 0x0401 }, { 0x0410, 0x044F }, { 0x0451, 0x0451 },
+ { 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 },
+ { 0x201C, 0x201D }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 },
+ { 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 },
+ { 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 },
+ { 0x207F, 0x207F }, { 0x2081, 0x2084 }, { 0x20AC, 0x20AC },
+ { 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 },
+ { 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 },
+ { 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 },
+ { 0x215B, 0x215E }, { 0x2160, 0x216B }, { 0x2170, 0x2179 },
+ { 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, { 0x21D2, 0x21D2 },
+ { 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, { 0x2200, 0x2200 },
+ { 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B },
+ { 0x220F, 0x220F }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 },
+ { 0x221A, 0x221A }, { 0x221D, 0x2220 }, { 0x2223, 0x2223 },
+ { 0x2225, 0x2225 }, { 0x2227, 0x222C }, { 0x222E, 0x222E },
+ { 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 },
+ { 0x224C, 0x224C }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 },
+ { 0x2264, 0x2267 }, { 0x226A, 0x226B }, { 0x226E, 0x226F },
+ { 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 },
+ { 0x2299, 0x2299 }, { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF },
+ { 0x2312, 0x2312 }, { 0x2460, 0x24E9 }, { 0x24EB, 0x254B },
+ { 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 },
+ { 0x25A0, 0x25A1 }, { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 },
+ { 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, { 0x25C0, 0x25C1 },
+ { 0x25C6, 0x25C8 }, { 0x25CB, 0x25CB }, { 0x25CE, 0x25D1 },
+ { 0x25E2, 0x25E5 }, { 0x25EF, 0x25EF }, { 0x2605, 0x2606 },
+ { 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 },
+ { 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 },
+ { 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 },
+ { 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F },
+ { 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xE000, 0xF8FF },
+ { 0xFFFD, 0xFFFD }, { 0xF0000, 0xFFFFD }, { 0x100000, 0x10FFFD }
+ };
+
+ /* binary search in table of non-spacing characters */
+ if (bisearch(ucs, ambiguous,
+ sizeof(ambiguous) / sizeof(struct interval) - 1))
+ return 2;
+
+ return mk_wcwidth(ucs);
+}
+
+
+int mk_wcswidth_cjk(const wchar_t *pwcs, size_t n)
+{
+ int w, width = 0;
+
+ for (;*pwcs && n-- > 0; pwcs++)
+ if ((w = mk_wcwidth_cjk(*pwcs)) < 0)
+ return -1;
+ else
+ width += w;
+
+ return width;
+}
