Patch 9.0.1629
Problem: Having utf16idx() rounding up is inconvenient.
Solution: Make utf16idx() round down. (Yegappan Lakshmanan, closes #12523)
Files: runtime/doc/builtin.txt, src/strings.c,
src/testdir/test_functions.vim
*** ../vim-9.0.1628/runtime/doc/builtin.txt 2023-06-08 17:09:40.188768829
+0100
--- runtime/doc/builtin.txt 2023-06-14 13:05:21.862735424 +0100
***************
*** 10114,10121 ****
When {charidx} is present and TRUE, {idx} is used as the
character index in the String {string} instead of as the byte
index.
! An {idx} in the middle of a UTF-8 sequence is rounded upwards
! to the end of that sequence.
Returns -1 if the arguments are invalid or if there are less
than {idx} bytes in {string}. If there are exactly {idx} bytes
--- 10127,10134 ----
When {charidx} is present and TRUE, {idx} is used as the
character index in the String {string} instead of as the byte
index.
! An {idx} in the middle of a UTF-8 sequence is rounded
! downwards to the beginning of that sequence.
Returns -1 if the arguments are invalid or if there are less
than {idx} bytes in {string}. If there are exactly {idx} bytes
*** ../vim-9.0.1628/src/strings.c 2023-06-08 17:09:40.188768829 +0100
--- src/strings.c 2023-06-14 13:05:21.862735424 +0100
***************
*** 1743,1750 ****
/*
- *
* "utf16idx()" function
*/
void
f_utf16idx(typval_T *argvars, typval_T *rettv)
--- 1743,1752 ----
/*
* "utf16idx()" function
+ *
+ * Converts a byte or character offset in a string to the corresponding UTF-16
+ * code unit offset.
*/
void
f_utf16idx(typval_T *argvars, typval_T *rettv)
***************
*** 1780,1785 ****
--- 1782,1788 ----
char_u *p;
int len;
+ int utf16idx = 0;
for (p = str, len = 0; charidx ? idx >= 0 : p <= str + idx; len++)
{
if (*p == NUL)
***************
*** 1791,1796 ****
--- 1794,1800 ----
rettv->vval.v_number = len;
return;
}
+ utf16idx = len;
int clen = ptr2len(p);
int c = (clen > 1) ? utf_ptr2char(p) : *p;
if (c > 0xFFFF)
***************
*** 1800,1806 ****
idx--;
}
! rettv->vval.v_number = len > 0 ? len - 1 : 0;
}
/*
--- 1804,1810 ----
idx--;
}
! rettv->vval.v_number = utf16idx;
}
/*
*** ../vim-9.0.1628/src/testdir/test_functions.vim 2023-06-08
17:09:40.192768840 +0100
--- src/testdir/test_functions.vim 2023-06-14 13:05:21.862735424 +0100
***************
*** 1518,1531 ****
" UTF-16 index of a string with four byte characters
let str = 'a😊😊b'
call assert_equal(0, utf16idx(str, 0))
! call assert_equal(2, utf16idx(str, 1))
! call assert_equal(2, utf16idx(str, 2))
! call assert_equal(2, utf16idx(str, 3))
! call assert_equal(2, utf16idx(str, 4))
! call assert_equal(4, utf16idx(str, 5))
! call assert_equal(4, utf16idx(str, 6))
! call assert_equal(4, utf16idx(str, 7))
! call assert_equal(4, utf16idx(str, 8))
call assert_equal(5, utf16idx(str, 9))
call assert_equal(6, utf16idx(str, 10))
call assert_equal(-1, utf16idx(str, 11))
--- 1518,1531 ----
" UTF-16 index of a string with four byte characters
let str = 'a😊😊b'
call assert_equal(0, utf16idx(str, 0))
! call assert_equal(1, utf16idx(str, 1))
! call assert_equal(1, utf16idx(str, 2))
! call assert_equal(1, utf16idx(str, 3))
! call assert_equal(1, utf16idx(str, 4))
! call assert_equal(3, utf16idx(str, 5))
! call assert_equal(3, utf16idx(str, 6))
! call assert_equal(3, utf16idx(str, 7))
! call assert_equal(3, utf16idx(str, 8))
call assert_equal(5, utf16idx(str, 9))
call assert_equal(6, utf16idx(str, 10))
call assert_equal(-1, utf16idx(str, 11))
***************
*** 1621,1628 ****
" UTF-16 index of a string with four byte characters
let str = "a😊😊b"
call assert_equal(0, utf16idx(str, 0, v:false, v:true))
! call assert_equal(2, utf16idx(str, 1, v:false, v:true))
! call assert_equal(4, utf16idx(str, 2, v:false, v:true))
call assert_equal(5, utf16idx(str, 3, v:false, v:true))
call assert_equal(6, utf16idx(str, 4, v:false, v:true))
call assert_equal(-1, utf16idx(str, 5, v:false, v:true))
--- 1621,1628 ----
" UTF-16 index of a string with four byte characters
let str = "a😊😊b"
call assert_equal(0, utf16idx(str, 0, v:false, v:true))
! call assert_equal(1, utf16idx(str, 1, v:false, v:true))
! call assert_equal(3, utf16idx(str, 2, v:false, v:true))
call assert_equal(5, utf16idx(str, 3, v:false, v:true))
call assert_equal(6, utf16idx(str, 4, v:false, v:true))
call assert_equal(-1, utf16idx(str, 5, v:false, v:true))
*** ../vim-9.0.1628/src/version.c 2023-06-13 22:44:53.538988256 +0100
--- src/version.c 2023-06-14 13:07:03.310895989 +0100
***************
*** 697,698 ****
--- 697,700 ----
{ /* Add new patch number below this line */
+ /**/
+ 1629,
/**/
--
"Hit any key to continue" does _not_ mean you can hit the on/off button!
/// Bram Moolenaar -- b...@moolenaar.net -- http://www.Moolenaar.net \\\
/// \\\
\\\ sponsor Vim, vote for features -- http://www.Vim.org/sponsor/ ///
\\\ help me help AIDS victims -- http://ICCF-Holland.org ///
--
--
You received this message from the "vim_dev" maillist.
Do not top-post! Type your reply below the text you are replying to.
For more information, visit http://www.vim.org/maillist.php
---
You received this message because you are subscribed to the Google Groups
"vim_dev" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to vim_dev+unsubscr...@googlegroups.com.
To view this discussion on the web visit
https://groups.google.com/d/msgid/vim_dev/20230614121108.D7CEA1C0CE4%40moolenaar.net.
