Patch 8.2.1461
Problem: Vim9: string indexes are counted in bytes.
Solution: Use character indexes. (closes #6574)
Files: runtime/doc/eval.txt, src/eval.c, src/proto/eval.pro,
src/vim9execute.c, src/eval.c, src/testdir/test_vim9_expr.vim
*** ../vim-8.2.1460/runtime/doc/eval.txt 2020-08-09 14:03:51.541367942
+0200
--- runtime/doc/eval.txt 2020-08-15 18:24:40.799380817 +0200
***************
*** 1128,1146 ****
expr8[expr1] item of String or |List| *expr-[]* *E111*
*E909* *subscript*
If expr8 is a Number or String this results in a String that contains the
! expr1'th single byte from expr8. expr8 is used as a String, expr1 as a
! Number. This doesn't recognize multi-byte encodings, see `byteidx()` for
! an alternative, or use `split()` to turn the string into a list of characters.
!
! Index zero gives the first byte. This is like it works in C. Careful:
! text column numbers start with one! Example, to get the byte under the
! cursor: >
:let c = getline(".")[col(".") - 1]
If the length of the String is less than the index, the result is an empty
String. A negative index always results in an empty string (reason: backward
! compatibility). Use [-1:] to get the last byte.
If expr8 is a |List| then it results the item at index expr1. See
|list-index|
for possible index values. If the index is out of range this results in an
--- 1131,1155 ----
expr8[expr1] item of String or |List| *expr-[]* *E111*
*E909* *subscript*
+ In legacy Vim script:
If expr8 is a Number or String this results in a String that contains the
! expr1'th single byte from expr8. expr8 is used as a String (a number is
! automatically converted to a String), expr1 as a Number. This doesn't
! recognize multi-byte encodings, see `byteidx()` for an alternative, or use
! `split()` to turn the string into a list of characters. Example, to get the
! byte under the cursor: >
:let c = getline(".")[col(".") - 1]
+ In Vim9 script:
+ If expr8 is a String this results in a String that contains the expr1'th
+ single character from expr8. To use byte indexes use |strpart()|.
+
+ Index zero gives the first byte or character. Careful: text column numbers
+ start with one!
+
If the length of the String is less than the index, the result is an empty
String. A negative index always results in an empty string (reason: backward
! compatibility). Use [-1:] to get the last byte or character.
If expr8 is a |List| then it results the item at index expr1. See
|list-index|
for possible index values. If the index is out of range this results in an
***************
*** 1154,1163 ****
expr8[expr1a : expr1b] substring or sublist *expr-[:]*
! If expr8 is a Number or String this results in the substring with the bytes
! from expr1a to and including expr1b. expr8 is used as a String, expr1a and
! expr1b are used as a Number. This doesn't recognize multi-byte encodings, see
! |byteidx()| for computing the indexes.
If expr1a is omitted zero is used. If expr1b is omitted the length of the
string minus one is used.
--- 1163,1178 ----
expr8[expr1a : expr1b] substring or sublist *expr-[:]*
! If expr8 is a String this results in the substring with the bytes from expr1a
! to and including expr1b. expr8 is used as a String, expr1a and expr1b are
! used as a Number.
!
! In legacy Vim script the indexes are byte indexes. This doesn't recognize
! multi-byte encodings, see |byteidx()| for computing the indexes. If expr8 is
! a Number it is first converted to a String.
!
! In Vim9 script the indexes are character indexes. To use byte indexes use
! |strpart()|.
If expr1a is omitted zero is used. If expr1b is omitted the length of the
string minus one is used.
*** ../vim-8.2.1460/src/eval.c 2020-08-15 16:33:24.501747305 +0200
--- src/eval.c 2020-08-15 18:32:40.363506218 +0200
***************
*** 3718,3723 ****
--- 3718,3727 ----
else
s = vim_strnsave(s + n1, n2 - n1 + 1);
}
+ else if (in_vim9script())
+ {
+ s = char_from_string(s, n1);
+ }
else
{
// The resulting variable is a string of a single
***************
*** 5285,5290 ****
--- 5289,5318 ----
}
/*
+ * Return the character "str[index]" where "index" is the character index. If
+ * "index" is out of range NULL is returned.
+ */
+ char_u *
+ char_from_string(char_u *str, varnumber_T index)
+ {
+ size_t nbyte = 0;
+ varnumber_T nchar = index;
+ size_t slen;
+
+ if (str == NULL || index < 0)
+ return NULL;
+ slen = STRLEN(str);
+ while (nchar > 0 && nbyte < slen)
+ {
+ nbyte += MB_CPTR2LEN(str + nbyte);
+ --nchar;
+ }
+ if (nbyte >= slen)
+ return NULL;
+ return vim_strnsave(str + nbyte, MB_CPTR2LEN(str + nbyte));
+ }
+
+ /*
* Handle:
* - expr[expr], expr[expr:expr] subscript
* - ".name" lookup
*** ../vim-8.2.1460/src/proto/eval.pro 2020-07-27 21:43:24.137946109 +0200
--- src/proto/eval.pro 2020-08-15 17:08:27.359565655 +0200
***************
*** 59,64 ****
--- 59,65 ----
int eval_isnamec(int c);
int eval_isnamec1(int c);
int eval_isdictc(int c);
+ char_u *char_from_string(char_u *str, varnumber_T index);
int handle_subscript(char_u **arg, typval_T *rettv, evalarg_T *evalarg, int
verbose);
int item_copy(typval_T *from, typval_T *to, int deep, int copyID);
void echo_one(typval_T *rettv, int with_space, int *atstart, int *needclr);
*** ../vim-8.2.1460/src/vim9execute.c 2020-08-15 16:33:24.497747330 +0200
--- src/vim9execute.c 2020-08-15 17:11:00.345567711 +0200
***************
*** 2233,2239 ****
case ISN_STRINDEX:
{
- char_u *s;
varnumber_T n;
char_u *res;
--- 2233,2238 ----
***************
*** 2245,2251 ****
emsg(_(e_stringreq));
goto on_error;
}
- s = tv->vval.v_string;
tv = STACK_TV_BOT(-1);
if (tv->v_type != VAR_NUMBER)
--- 2244,2249 ----
***************
*** 2259,2270 ****
// The resulting variable is a string of a single
// character. If the index is too big or negative the
// result is empty.
- if (n < 0 || n >= (varnumber_T)STRLEN(s))
- res = NULL;
- else
- res = vim_strnsave(s + n, 1);
--ectx.ec_stack.ga_len;
tv = STACK_TV_BOT(-1);
vim_free(tv->vval.v_string);
tv->vval.v_string = res;
}
--- 2257,2265 ----
// The resulting variable is a string of a single
// character. If the index is too big or negative the
// result is empty.
--ectx.ec_stack.ga_len;
tv = STACK_TV_BOT(-1);
+ res = char_from_string(tv->vval.v_string, n);
vim_free(tv->vval.v_string);
tv->vval.v_string = res;
}
*** ../vim-8.2.1460/src/eval.c 2020-08-15 16:33:24.501747305 +0200
--- src/eval.c 2020-08-15 18:32:40.363506218 +0200
***************
*** 3718,3723 ****
--- 3718,3727 ----
else
s = vim_strnsave(s + n1, n2 - n1 + 1);
}
+ else if (in_vim9script())
+ {
+ s = char_from_string(s, n1);
+ }
else
{
// The resulting variable is a string of a single
***************
*** 5285,5290 ****
--- 5289,5318 ----
}
/*
+ * Return the character "str[index]" where "index" is the character index. If
+ * "index" is out of range NULL is returned.
+ */
+ char_u *
+ char_from_string(char_u *str, varnumber_T index)
+ {
+ size_t nbyte = 0;
+ varnumber_T nchar = index;
+ size_t slen;
+
+ if (str == NULL || index < 0)
+ return NULL;
+ slen = STRLEN(str);
+ while (nchar > 0 && nbyte < slen)
+ {
+ nbyte += MB_CPTR2LEN(str + nbyte);
+ --nchar;
+ }
+ if (nbyte >= slen)
+ return NULL;
+ return vim_strnsave(str + nbyte, MB_CPTR2LEN(str + nbyte));
+ }
+
+ /*
* Handle:
* - expr[expr], expr[expr:expr] subscript
* - ".name" lookup
*** ../vim-8.2.1460/src/testdir/test_vim9_expr.vim 2020-08-15
16:33:24.501747305 +0200
--- src/testdir/test_vim9_expr.vim 2020-08-15 17:16:48.649794487 +0200
***************
*** 2075,2086 ****
enddef
def Test_expr7_subscript()
! let text = 'abcdef'
! assert_equal('', text[-1])
! assert_equal('a', text[0])
! assert_equal('e', text[4])
! assert_equal('f', text[5])
! assert_equal('', text[6])
enddef
def Test_expr7_subscript_linebreak()
--- 2075,2102 ----
enddef
def Test_expr7_subscript()
! let lines =<< trim END
! let text = 'abcdef'
! assert_equal('', text[-1])
! assert_equal('a', text[0])
! assert_equal('e', text[4])
! assert_equal('f', text[5])
! assert_equal('', text[6])
!
! text = 'ábçdëf'
! assert_equal('', text[-999])
! assert_equal('', text[-1])
! assert_equal('á', text[0])
! assert_equal('b', text[1])
! assert_equal('ç', text[2])
! assert_equal('d', text[3])
! assert_equal('ë', text[4])
! assert_equal('f', text[5])
! assert_equal('', text[6])
! assert_equal('', text[999])
! END
! CheckDefSuccess(lines)
! CheckScriptSuccess(['vim9script'] + lines)
enddef
def Test_expr7_subscript_linebreak()
*** ../vim-8.2.1460/src/version.c 2020-08-15 16:33:24.505747282 +0200
--- src/version.c 2020-08-15 17:08:22.507633662 +0200
***************
*** 756,757 ****
--- 756,759 ----
{ /* Add new patch number below this line */
+ /**/
+ 1461,
/**/
--
hundred-and-one symptoms of being an internet addict:
210. When you get a divorce, you don't care about who gets the children,
but discuss endlessly who can use the email address.
/// Bram Moolenaar -- [email protected] -- http://www.Moolenaar.net \\\
/// sponsor Vim, vote for features -- http://www.Vim.org/sponsor/ \\\
\\\ an exciting new programming language -- http://www.Zimbu.org ///
\\\ 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 [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/vim_dev/202008151639.07FGdWVG342455%40masaka.moolenaar.net.
