The branch stable/13 has been updated by hselasky:

URL: 
https://cgit.FreeBSD.org/src/commit/?id=d4dd3c8f8b5b050a24da6fc2b885c301843214a5

commit d4dd3c8f8b5b050a24da6fc2b885c301843214a5
Author:     Hans Petter Selasky <[email protected]>
AuthorDate: 2022-06-25 09:17:44 +0000
Commit:     Hans Petter Selasky <[email protected]>
CommitDate: 2022-07-05 11:42:28 +0000

    vt: Improve multi lingual word separation.
    
    Suggested by:   Tomoaki AOKI <[email protected]>
    Differential Revision:  https://reviews.freebsd.org/D35552
    PR:             263084
    Sponsored by:   NVIDIA Networking
    
    (cherry picked from commit 9971e6aff1bef3d456172c41a3df3ce7266517cf)
---
 sys/dev/vt/vt_buf.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/sys/dev/vt/vt_buf.c b/sys/dev/vt/vt_buf.c
index fa6c7c8fec5f..b83db85f1cdb 100644
--- a/sys/dev/vt/vt_buf.c
+++ b/sys/dev/vt/vt_buf.c
@@ -747,6 +747,29 @@ vtbuf_get_marked_len(struct vt_buf *vb)
        return (sz * sizeof(term_char_t));
 }
 
+static bool
+tchar_is_word_separator(term_char_t ch)
+{
+       /* List of unicode word separator characters: */
+       switch (TCHAR_CHARACTER(ch)) {
+       case 0x0020: /* SPACE */
+       case 0x180E: /* MONGOLIAN VOWEL SEPARATOR */
+       case 0x2002: /* EN SPACE (nut) */
+       case 0x2003: /* EM SPACE (mutton) */
+       case 0x2004: /* THREE-PER-EM SPACE (thick space) */
+       case 0x2005: /* FOUR-PER-EM SPACE (mid space) */
+       case 0x2006: /* SIX-PER-EM SPACE */
+       case 0x2008: /* PUNCTUATION SPACE */
+       case 0x2009: /* THIN SPACE */
+       case 0x200A: /* HAIR SPACE */
+       case 0x200B: /* ZERO WIDTH SPACE */
+       case 0x3000: /* IDEOGRAPHIC SPACE */
+               return (true);
+       default:
+               return (false);
+       }
+}
+
 void
 vtbuf_extract_marked(struct vt_buf *vb, term_char_t *buf, int sz)
 {
@@ -779,7 +802,7 @@ vtbuf_extract_marked(struct vt_buf *vb, term_char_t *buf, 
int sz)
                if (r != e.tp_row) {
                        /* Trim trailing word separators, if any. */
                        for (; i != j; i--) {
-                               if (TCHAR_CHARACTER(buf[i - 1]) != ' ')
+                               if (!tchar_is_word_separator(buf[i - 1]))
                                        break;
                        }
                        /* Add newline character as expected by TTY. */
@@ -824,7 +847,7 @@ vtbuf_set_mark(struct vt_buf *vb, int type, int col, int 
row)
                    vtbuf_wth(vb, row);
                r = vb->vb_rows[vb->vb_mark_start.tp_row];
                for (i = col; i >= 0; i --) {
-                       if (TCHAR_CHARACTER(r[i]) == ' ') {
+                       if (tchar_is_word_separator(r[i])) {
                                vb->vb_mark_start.tp_col = i + 1;
                                break;
                        }
@@ -833,7 +856,7 @@ vtbuf_set_mark(struct vt_buf *vb, int type, int col, int 
row)
                if (i == -1)
                        vb->vb_mark_start.tp_col = 0;
                for (i = col; i < vb->vb_scr_size.tp_col; i++) {
-                       if (TCHAR_CHARACTER(r[i]) == ' ') {
+                       if (tchar_is_word_separator(r[i])) {
                                vb->vb_mark_end.tp_col = i;
                                break;
                        }

Reply via email to