view src/proto/mbyte.pro @ 34336:d2ad8733db75 v9.1.0101

patch 9.1.0101: upper-case of German sharp s should be U+1E9E Commit: https://github.com/vim/vim/commit/bd1232a1faf56b614a1e74c4ce51bc6e0650ae00 Author: glepnir <glephunter@gmail.com> Date: Mon Feb 12 22:14:53 2024 +0100 patch 9.1.0101: upper-case of German sharp s should be U+1E9E Problem: upper-case of ? should be U+1E9E (CAPITAL LETTER SHARP S) (fenuks) Solution: Make gU, ~ and g~ convert the U+00DF LATIN SMALL LETTER SHARP S (?) to U+1E9E LATIN CAPITAL LETTER SHARP S (?), update tests (glepnir) This is part of Unicode 5.1.0 from April 2008, so should be fairly safe to use now and since 2017 is part of the German standard orthography, according to Wikipedia: https://en.wikipedia.org/wiki/Capital_%E1%BA%9E#cite_note-auto-12 There is however one exception: UnicodeData.txt for U+00DF LATIN SMALL LETTER SHARP S does NOT define U+1E9E LATIN CAPITAL LETTER SHARP S as its upper case version. Therefore, toupper() won't be able to convert from lower sharp s to upper case sharp s (the other way around however works, since U+00DF is considered the lower case character of U+1E9E and therefore tolower() works correctly for the upper case version). fixes: #5573 closes: #14018 Signed-off-by: glepnir <glephunter@gmail.com> Signed-off-by: Christian Brabandt <cb@256bit.org>
author Christian Brabandt <cb@256bit.org>
date Mon, 12 Feb 2024 22:45:02 +0100
parents 95db67c7b754
children 97b5457962ed
line wrap: on
line source

/* mbyte.c */
int enc_canon_props(char_u *name);
char *mb_init(void);
int bomb_size(void);
void remove_bom(char_u *s);
int mb_get_class(char_u *p);
int mb_get_class_buf(char_u *p, buf_T *buf);
int dbcs_class(unsigned lead, unsigned trail);
int latin_char2len(int c);
int latin_char2bytes(int c, char_u *buf);
int latin_ptr2len(char_u *p);
int latin_ptr2len_len(char_u *p, int size);
int utf_uint2cells(UINT32_T c);
int utf_char2cells(int c);
int latin_ptr2cells(char_u *p);
int utf_ptr2cells(char_u *p);
int dbcs_ptr2cells(char_u *p);
int latin_ptr2cells_len(char_u *p, int size);
int latin_char2cells(int c);
int mb_string2cells(char_u *p, int len);
int latin_off2cells(unsigned off, unsigned max_off);
int dbcs_off2cells(unsigned off, unsigned max_off);
int utf_off2cells(unsigned off, unsigned max_off);
int latin_ptr2char(char_u *p);
int utf_ptr2char(char_u *p);
int mb_ptr2char_adv(char_u **pp);
int mb_cptr2char_adv(char_u **pp);
int utf_composinglike(char_u *p1, char_u *p2);
int utfc_ptr2char(char_u *p, int *pcc);
int utfc_ptr2char_len(char_u *p, int *pcc, int maxlen);
int utfc_char2bytes(int off, char_u *buf);
int utf_ptr2len(char_u *p);
int utf_byte2len(int b);
int utf_ptr2len_len(char_u *p, int size);
int utfc_ptr2len(char_u *p);
int utfc_ptr2len_len(char_u *p, int size);
int utf_char2len(int c);
int utf_char2bytes(int c, char_u *buf);
int utf_iscomposing_uint(UINT32_T c);
int utf_iscomposing(int c);
int utf_printable(int c);
int utf_class(int c);
int utf_class_buf(int c, buf_T *buf);
int utf_ambiguous_width(int c);
int utf_fold(int a);
int utf_toupper(int a);
int utf_islower(int a);
int utf_tolower(int a);
int utf_isupper(int a);
int mb_strnicmp(char_u *s1, char_u *s2, size_t nn);
void show_utf8(void);
int latin_head_off(char_u *base, char_u *p);
int dbcs_screen_head_off(char_u *base, char_u *p);
int utf_head_off(char_u *base, char_u *p);
int utf_eat_space(int cc);
int utf_allow_break_before(int cc);
int utf_allow_break(int cc, int ncc);
void mb_copy_char(char_u **fp, char_u **tp);
int mb_off_next(char_u *base, char_u *p);
int mb_tail_off(char_u *base, char_u *p);
void utf_find_illegal(void);
int utf_valid_string(char_u *s, char_u *end);
int dbcs_screen_tail_off(char_u *base, char_u *p);
void mb_adjust_cursor(void);
void mb_adjustpos(buf_T *buf, pos_T *lp);
char_u *mb_prevptr(char_u *line, char_u *p);
int mb_charlen(char_u *str);
int mb_charlen_len(char_u *str, int len);
char_u *mb_unescape(char_u **pp);
int mb_lefthalve(int row, int col);
int mb_fix_col(int col, int row);
char_u *enc_skip(char_u *p);
char_u *enc_canonize(char_u *enc);
char_u *enc_locale_env(char *locale);
char_u *enc_locale(void);
int encname2codepage(char_u *name);
void *my_iconv_open(char_u *to, char_u *from);
int iconv_enabled(int verbose);
void iconv_end(void);
void f_getimstatus(typval_T *argvars, typval_T *rettv);
void f_iconv(typval_T *argvars, typval_T *rettv);
int convert_setup(vimconv_T *vcp, char_u *from, char_u *to);
int convert_setup_ext(vimconv_T *vcp, char_u *from, int from_unicode_is_utf8, char_u *to, int to_unicode_is_utf8);
int convert_input(char_u *ptr, int len, int maxlen);
int convert_input_safe(char_u *ptr, int len, int maxlen, char_u **restp, int *restlenp);
char_u *string_convert(vimconv_T *vcp, char_u *ptr, int *lenp);
char_u *string_convert_ext(vimconv_T *vcp, char_u *ptr, int *lenp, int *unconvlenp);
void f_setcellwidths(typval_T *argvars, typval_T *rettv);
void f_getcellwidths(typval_T *argvars, typval_T *rettv);
void f_charclass(typval_T *argvars, typval_T *rettv);
char_u *get_encoding_name(expand_T *xp, int idx);
/* vim: set ft=c : */