Mercurial > vim
changeset 4051:42edc5dac33c v7.3.780
updated for version 7.3.780
Problem: char2nr() and nr2char() always use 'encoding'.
Solution: Add argument to use utf-8 characters. (Yasuhiro Matsumoto)
| author | Bram Moolenaar <bram@vim.org> |
|---|---|
| date | Wed, 23 Jan 2013 17:17:10 +0100 |
| parents | 25e5c2ec157a |
| children | 7457c0105747 |
| files | runtime/doc/eval.txt src/eval.c src/version.c |
| diffstat | 3 files changed, 37 insertions(+), 12 deletions(-) [+] |
line wrap: on
line diff
--- a/runtime/doc/eval.txt +++ b/runtime/doc/eval.txt @@ -1716,7 +1716,7 @@ call( {func}, {arglist} [, {dict}]) any call {func} with arguments {arglist} ceil( {expr}) Float round {expr} up changenr() Number current change number -char2nr( {expr}) Number ASCII value of first char in {expr} +char2nr( {expr}[, {utf8}]) Number ASCII/UTF8 value of first char in {expr} cindent( {lnum}) Number C indent for line {lnum} clearmatches() none clear all matches col( {expr}) Number column nr of cursor or mark @@ -1873,7 +1873,7 @@ mkdir( {name} [, {path} [, {prot}]]) mode( [expr]) String current editing mode mzeval( {expr}) any evaluate |MzScheme| expression nextnonblank( {lnum}) Number line nr of non-blank line >= {lnum} -nr2char( {expr}) String single char with ASCII value {expr} +nr2char( {expr}[, {utf8}]) String single char with ASCII/UTF8 value {expr} or( {expr}, {expr}) Number bitwise OR pathshorten( {expr}) String shorten directory names in a path pow( {x}, {y}) Float {x} to the power of {y} @@ -2294,14 +2294,16 @@ changenr() *changenr()* redo it is the number of the redone change. After undo it is one less than the number of the undone change. -char2nr({expr}) *char2nr()* +char2nr({expr}[, {utf8}]) *char2nr()* Return number value of the first char in {expr}. Examples: > char2nr(" ") returns 32 char2nr("ABC") returns 65 -< The current 'encoding' is used. Example for "utf-8": > +< When {utf8} is omitted or zero, the current 'encoding' is used. + Example for "utf-8": > char2nr("á") returns 225 char2nr("á"[0]) returns 195 -< A combining character is a separate character. +< With {utf8} set to 1, always treat as utf-8 characters. + A combining character is a separate character. |nr2char()| does the opposite. cindent({lnum}) *cindent()* @@ -4371,14 +4373,16 @@ nextnonblank({lnum}) *nextnonblank() below it, zero is returned. See also |prevnonblank()|. -nr2char({expr}) *nr2char()* +nr2char({expr}[, {utf8}]) *nr2char()* Return a string with a single character, which has the number value {expr}. Examples: > nr2char(64) returns "@" nr2char(32) returns " " -< The current 'encoding' is used. Example for "utf-8": > +< When {utf8} is omitted or zero, the current 'encoding' is used. + Example for "utf-8": > nr2char(300) returns I with bow character -< Note that a NUL character in the file is specified with +< With {utf8} set to 1, always return utf-8 characters. + Note that a NUL character in the file is specified with nr2char(10), because NULs are represented with newline characters. nr2char(0) is a real NUL and terminates the string, thus results in an empty string.
--- a/src/eval.c +++ b/src/eval.c @@ -7854,7 +7854,7 @@ static struct fst {"ceil", 1, 1, f_ceil}, #endif {"changenr", 0, 0, f_changenr}, - {"char2nr", 1, 1, f_char2nr}, + {"char2nr", 1, 2, f_char2nr}, {"cindent", 1, 1, f_cindent}, {"clearmatches", 0, 0, f_clearmatches}, {"col", 1, 1, f_col}, @@ -8003,7 +8003,7 @@ static struct fst {"mzeval", 1, 1, f_mzeval}, #endif {"nextnonblank", 1, 1, f_nextnonblank}, - {"nr2char", 1, 1, f_nr2char}, + {"nr2char", 1, 2, f_nr2char}, {"or", 2, 2, f_or}, {"pathshorten", 1, 1, f_pathshorten}, #ifdef FEAT_FLOAT @@ -9303,7 +9303,17 @@ f_char2nr(argvars, rettv) { #ifdef FEAT_MBYTE if (has_mbyte) - rettv->vval.v_number = (*mb_ptr2char)(get_tv_string(&argvars[0])); + { + int utf8 = 0; + + if (argvars[1].v_type != VAR_UNKNOWN) + utf8 = get_tv_number_chk(&argvars[1], NULL); + + if (utf8) + rettv->vval.v_number = (*utf_ptr2char)(get_tv_string(&argvars[0])); + else + rettv->vval.v_number = (*mb_ptr2char)(get_tv_string(&argvars[0])); + } else #endif rettv->vval.v_number = get_tv_string(&argvars[0])[0]; @@ -14360,7 +14370,16 @@ f_nr2char(argvars, rettv) #ifdef FEAT_MBYTE if (has_mbyte) - buf[(*mb_char2bytes)((int)get_tv_number(&argvars[0]), buf)] = NUL; + { + int utf8 = 0; + + if (argvars[1].v_type != VAR_UNKNOWN) + utf8 = get_tv_number_chk(&argvars[1], NULL); + if (utf8) + buf[(*utf_char2bytes)((int)get_tv_number(&argvars[0]), buf)] = NUL; + else + buf[(*mb_char2bytes)((int)get_tv_number(&argvars[0]), buf)] = NUL; + } else #endif {