view src/proto/mbyte.pro @ 34854:97b5457962ed v9.1.0296

patch 9.1.0296: regexp: engines do not handle case-folding well Commit: https://github.com/vim/vim/commit/7a27c108e0509f3255ebdcb6558e896c223e4d23 Author: Christian Brabandt <cb@256bit.org> Date: Tue Apr 9 22:53:19 2024 +0200 patch 9.1.0296: regexp: engines do not handle case-folding well Problem: Regex engines do not handle case-folding well Solution: Correctly calculate byte length of characters to skip When the regexp engine compares two utf-8 codepoints case insensitively it may match an adjacent character, because it assumes it can step over as many bytes as the pattern contains. This however is not necessarily true because of case-folding, a multi-byte UTF-8 character can be considered equal to some single-byte value. Let's consider the pattern '?' and the string 's'. When comparing and ignoring case, the single character 's' matches, and since it matches Vim will try to step over the match (by the amount of bytes of the pattern), assuming that since it matches, the length of both strings is the same. However in that case, it should only step over the single byte value 's' so by 1 byte and try to start matching after it again. So for the backtracking engine we need to ensure: - we try to match the correct length for the pattern and the text - in case of a match, we step over it correctly The same thing can happen for the NFA engine, when skipping to the next character to test for a match. We are skipping over the regstart pointer, however we do not consider the case that because of case-folding we may need to adjust the number of bytes to skip over. So this needs to be adjusted in find_match_text() as well. A related issue turned out, when prog->match_text is actually empty. In that case we should try to find the next match and skip this condition. fixes: #14294 closes: #14433 Signed-off-by: Christian Brabandt <cb@256bit.org>
author Christian Brabandt <cb@256bit.org>
date Tue, 09 Apr 2024 23:00:08 +0200
parents 95db67c7b754
children 3f8444c5a6f3
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);
int mb_strnicmp2(char_u *s1, char_u *s2, int n1, int n2);
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 : */