aboutsummaryrefslogtreecommitdiff
path: root/src/nvim/charset.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/nvim/charset.c')
-rw-r--r--src/nvim/charset.c113
1 files changed, 68 insertions, 45 deletions
diff --git a/src/nvim/charset.c b/src/nvim/charset.c
index 4efd8a4ad1..4115743e1c 100644
--- a/src/nvim/charset.c
+++ b/src/nvim/charset.c
@@ -6,28 +6,35 @@
/// Code related to character sets.
#include <assert.h>
+#include <errno.h>
#include <inttypes.h>
+#include <limits.h>
+#include <stdlib.h>
#include <string.h>
-#include <wctype.h>
+#include "auto/config.h"
#include "nvim/ascii.h"
+#include "nvim/buffer_defs.h"
#include "nvim/charset.h"
#include "nvim/cursor.h"
-#include "nvim/func_attr.h"
+#include "nvim/eval/typval.h"
+#include "nvim/eval/typval_defs.h"
#include "nvim/garray.h"
+#include "nvim/globals.h"
+#include "nvim/grid_defs.h"
#include "nvim/indent.h"
-#include "nvim/main.h"
+#include "nvim/keycodes.h"
+#include "nvim/macros.h"
#include "nvim/mark.h"
#include "nvim/mbyte.h"
#include "nvim/memline.h"
#include "nvim/memory.h"
#include "nvim/move.h"
#include "nvim/option.h"
-#include "nvim/os_unix.h"
#include "nvim/path.h"
#include "nvim/plines.h"
+#include "nvim/pos.h"
#include "nvim/state.h"
-#include "nvim/strings.h"
#include "nvim/vim.h"
#ifdef INCLUDE_GENERATED_DECLARATIONS
@@ -267,8 +274,8 @@ int buf_init_chartab(buf_T *buf, int global)
/// @param bufsize
void trans_characters(char *buf, int bufsize)
{
- char_u *trs; // translated character
- int len = (int)STRLEN(buf); // length of string needing translation
+ char *trs; // translated character
+ int len = (int)strlen(buf); // length of string needing translation
int room = bufsize - len; // room in buffer after string
while (*buf != 0) {
@@ -277,8 +284,8 @@ void trans_characters(char *buf, int bufsize)
if ((trs_len = utfc_ptr2len(buf)) > 1) {
len -= trs_len;
} else {
- trs = transchar_byte((uint8_t)(*buf));
- trs_len = (int)STRLEN(trs);
+ trs = (char *)transchar_byte((uint8_t)(*buf));
+ trs_len = (int)strlen(trs);
if (trs_len > 1) {
room -= trs_len - 1;
@@ -411,12 +418,28 @@ char *transstr(const char *const s, bool untab)
return buf;
}
+size_t kv_transstr(StringBuilder *str, const char *const s, bool untab)
+ FUNC_ATTR_NONNULL_ARG(1)
+{
+ if (!s) {
+ return 0;
+ }
+
+ // Compute the length of the result, taking account of unprintable
+ // multi-byte characters.
+ const size_t len = transstr_len(s, untab);
+ kv_ensure_space(*str, len + 1);
+ transstr_buf(s, str->items + str->size, len + 1, untab);
+ str->size += len; // do not include NUL byte
+ return len;
+}
+
/// Convert the string "str[orglen]" to do ignore-case comparing.
/// Use the current locale.
///
/// When "buf" is NULL, return an allocated string.
/// Otherwise, put the result in buf, limited by buflen, and return buf.
-char_u *str_foldcase(char_u *str, int orglen, char_u *buf, int buflen)
+char *str_foldcase(char *str, int orglen, char *buf, int buflen)
FUNC_ATTR_NONNULL_RET
{
garray_T ga;
@@ -424,7 +447,7 @@ char_u *str_foldcase(char_u *str, int orglen, char_u *buf, int buflen)
int len = orglen;
#define GA_CHAR(i) ((char *)ga.ga_data)[i]
-#define GA_PTR(i) ((char_u *)ga.ga_data + (i))
+#define GA_PTR(i) ((char *)ga.ga_data + (i))
#define STR_CHAR(i) (buf == NULL ? GA_CHAR(i) : buf[i])
#define STR_PTR(i) (buf == NULL ? GA_PTR(i) : buf + (i))
@@ -452,8 +475,8 @@ char_u *str_foldcase(char_u *str, int orglen, char_u *buf, int buflen)
// Make each character lower case.
i = 0;
while (STR_CHAR(i) != NUL) {
- int c = utf_ptr2char((char *)STR_PTR(i));
- int olen = utf_ptr2len((char *)STR_PTR(i));
+ int c = utf_ptr2char(STR_PTR(i));
+ int olen = utf_ptr2len(STR_PTR(i));
int lc = mb_tolower(c);
// Only replace the character when it is not an invalid
@@ -487,15 +510,15 @@ char_u *str_foldcase(char_u *str, int orglen, char_u *buf, int buflen)
}
}
}
- (void)utf_char2bytes(lc, (char *)STR_PTR(i));
+ (void)utf_char2bytes(lc, STR_PTR(i));
}
// skip to next multi-byte char
- i += utfc_ptr2len((char *)STR_PTR(i));
+ i += utfc_ptr2len(STR_PTR(i));
}
if (buf == NULL) {
- return (char_u *)ga.ga_data;
+ return ga.ga_data;
}
return buf;
}
@@ -650,7 +673,7 @@ static inline unsigned nr2hex(unsigned n)
///
/// @param b
///
-/// @reeturn Number of display cells.
+/// @return Number of display cells.
int byte2cells(int b)
FUNC_ATTR_PURE
{
@@ -786,7 +809,7 @@ bool vim_iswordc_buf(const int c, buf_T *const buf)
/// @param p pointer to the multi-byte character
///
/// @return true if "p" points to a keyword character.
-bool vim_iswordp(const char_u *const p)
+bool vim_iswordp(const char *const p)
FUNC_ATTR_PURE FUNC_ATTR_WARN_UNUSED_RESULT FUNC_ATTR_NONNULL_ALL
{
return vim_iswordp_buf(p, curbuf);
@@ -799,13 +822,13 @@ bool vim_iswordp(const char_u *const p)
/// @param buf buffer whose keywords to use
///
/// @return true if "p" points to a keyword character.
-bool vim_iswordp_buf(const char_u *const p, buf_T *const buf)
+bool vim_iswordp_buf(const char *const p, buf_T *const buf)
FUNC_ATTR_PURE FUNC_ATTR_WARN_UNUSED_RESULT FUNC_ATTR_NONNULL_ALL
{
- int c = *p;
+ int c = (uint8_t)(*p);
if (MB_BYTE2LEN(c) > 1) {
- c = utf_ptr2char((char *)p);
+ c = utf_ptr2char(p);
}
return vim_iswordc_buf(c, buf);
}
@@ -829,8 +852,8 @@ bool vim_isfilec(int c)
bool vim_isfilec_or_wc(int c)
FUNC_ATTR_PURE FUNC_ATTR_WARN_UNUSED_RESULT
{
- char_u buf[2];
- buf[0] = (char_u)c;
+ char buf[2];
+ buf[0] = (char)c;
buf[1] = NUL;
return vim_isfilec(c) || c == ']' || path_has_wildcard(buf);
}
@@ -905,15 +928,15 @@ bool in_win_border(win_T *wp, colnr_T vcol)
/// @param end
void getvcol(win_T *wp, pos_T *pos, colnr_T *start, colnr_T *cursor, colnr_T *end)
{
- char_u *ptr; // points to current char
- char_u *posptr; // points to char at pos->col
+ char *ptr; // points to current char
+ char *posptr; // points to char at pos->col
int incr;
int head;
long *vts = wp->w_buffer->b_p_vts_array;
int ts = (int)wp->w_buffer->b_p_ts;
colnr_T vcol = 0;
- char_u *line = ptr = ml_get_buf(wp->w_buffer, pos->lnum, false); // start of the line
+ char *line = ptr = ml_get_buf(wp->w_buffer, pos->lnum, false); // start of the line
if (pos->col == MAXCOL) {
// continue until the NUL
@@ -944,7 +967,7 @@ void getvcol(win_T *wp, pos_T *pos, colnr_T *start, colnr_T *cursor, colnr_T *en
&& !cts.cts_has_virt_text) {
for (;;) {
head = 0;
- int c = *ptr;
+ int c = (uint8_t)(*ptr);
// make sure we don't go past the end of the line
if (c == NUL) {
@@ -960,7 +983,7 @@ void getvcol(win_T *wp, pos_T *pos, colnr_T *start, colnr_T *cursor, colnr_T *en
// For utf-8, if the byte is >= 0x80, need to look at
// further bytes to find the cell width.
if (c >= 0x80) {
- incr = utf_ptr2cells((char *)ptr);
+ incr = utf_ptr2cells(ptr);
} else {
incr = g_chartab[c] & CT_CELL_MASK;
}
@@ -970,7 +993,7 @@ void getvcol(win_T *wp, pos_T *pos, colnr_T *start, colnr_T *cursor, colnr_T *en
// cells wide.
if ((incr == 2)
&& wp->w_p_wrap
- && (MB_BYTE2LEN(*ptr) > 1)
+ && (MB_BYTE2LEN((uint8_t)(*ptr)) > 1)
&& in_win_border(wp, vcol)) {
incr++;
head = 1;
@@ -999,7 +1022,7 @@ void getvcol(win_T *wp, pos_T *pos, colnr_T *start, colnr_T *cursor, colnr_T *en
break;
}
- if ((posptr != NULL) && ((char_u *)cts.cts_ptr >= posptr)) {
+ if ((posptr != NULL) && (cts.cts_ptr >= posptr)) {
// character at pos->col
break;
}
@@ -1008,7 +1031,7 @@ void getvcol(win_T *wp, pos_T *pos, colnr_T *start, colnr_T *cursor, colnr_T *en
MB_PTR_ADV(cts.cts_ptr);
}
vcol = cts.cts_vcol;
- ptr = (char_u *)cts.cts_ptr;
+ ptr = cts.cts_ptr;
}
clear_chartabsize_arg(&cts);
@@ -1076,10 +1099,10 @@ void getvvcol(win_T *wp, pos_T *pos, colnr_T *start, colnr_T *cursor, colnr_T *e
colnr_T endadd = 0;
// Cannot put the cursor on part of a wide character.
- char_u *ptr = ml_get_buf(wp->w_buffer, pos->lnum, false);
+ char *ptr = ml_get_buf(wp->w_buffer, pos->lnum, false);
- if (pos->col < (colnr_T)STRLEN(ptr)) {
- int c = utf_ptr2char((char *)ptr + pos->col);
+ if (pos->col < (colnr_T)strlen(ptr)) {
+ int c = utf_ptr2char(ptr + pos->col);
if ((c != TAB) && vim_isprintc(c)) {
endadd = (colnr_T)(char2cells(c) - 1);
if (coladd > endadd) {
@@ -1157,7 +1180,7 @@ char *skipwhite(const char *const p)
FUNC_ATTR_PURE FUNC_ATTR_WARN_UNUSED_RESULT FUNC_ATTR_NONNULL_ALL
FUNC_ATTR_NONNULL_RET
{
- return skipwhite_len(p, STRLEN(p));
+ return skipwhite_len(p, strlen(p));
}
/// Like `skipwhite`, but skip up to `len` characters.
@@ -1182,7 +1205,7 @@ char *skipwhite_len(const char *p, size_t len)
// columns (bytes) at the start of a given line
intptr_t getwhitecols_curline(void)
{
- return getwhitecols((char *)get_cursor_line_ptr());
+ return getwhitecols(get_cursor_line_ptr());
}
intptr_t getwhitecols(const char *p)
@@ -1338,7 +1361,7 @@ char *skip_to_newline(const char *const p)
/// Gets a number from a string and skips over it, signalling overflow.
///
-/// @param[out] pp A pointer to a pointer to char_u.
+/// @param[out] pp A pointer to a pointer to char.
/// It will be advanced past the read number.
/// @param[out] nr Number read from the string.
///
@@ -1355,7 +1378,7 @@ bool try_getdigits(char **pp, intmax_t *nr)
/// Gets a number from a string and skips over it.
///
-/// @param[out] pp Pointer to a pointer to char_u.
+/// @param[out] pp Pointer to a pointer to char.
/// It will be advanced past the read number.
/// @param strict Abort on overflow.
/// @param def Default value, if parsing fails or overflow occurs.
@@ -1463,14 +1486,14 @@ bool vim_isblankline(char *lbuf)
/// @param strict If true, fail if the number has unexpected trailing
/// alphanumeric chars: *len is set to 0 and nothing else is
/// returned.
-void vim_str2nr(const char_u *const start, int *const prep, int *const len, const int what,
+void vim_str2nr(const char *const start, int *const prep, int *const len, const int what,
varnumber_T *const nptr, uvarnumber_T *const unptr, const int maxlen,
const bool strict)
FUNC_ATTR_NONNULL_ARG(1)
{
- const char *ptr = (const char *)start;
+ const char *ptr = start;
#define STRING_ENDED(ptr) \
- (!(maxlen == 0 || (int)((ptr) - (const char *)start) < maxlen))
+ (!(maxlen == 0 || (int)((ptr) - start) < maxlen))
int pre = 0; // default is decimal
const bool negative = (ptr[0] == '-');
uvarnumber_T un = 0;
@@ -1522,7 +1545,7 @@ void vim_str2nr(const char_u *const start, int *const prep, int *const len, cons
} else if ((what & (STR2NR_HEX | STR2NR_OCT | STR2NR_OOCT | STR2NR_BIN))
&& !STRING_ENDED(ptr + 1) && ptr[0] == '0' && ptr[1] != '8'
&& ptr[1] != '9') {
- pre = (char_u)ptr[1];
+ pre = (uint8_t)ptr[1];
// Detect hexadecimal: 0x or 0X followed by hex digit.
if ((what & STR2NR_HEX)
&& !STRING_ENDED(ptr + 2)
@@ -1610,7 +1633,7 @@ vim_str2nr_hex:
vim_str2nr_proceed:
// Check for an alphanumeric character immediately following, that is
// most likely a typo.
- if (strict && ptr - (const char *)start != maxlen && ASCII_ISALNUM(*ptr)) {
+ if (strict && ptr - start != maxlen && ASCII_ISALNUM(*ptr)) {
return;
}
@@ -1619,7 +1642,7 @@ vim_str2nr_proceed:
}
if (len != NULL) {
- *len = (int)(ptr - (const char *)start);
+ *len = (int)(ptr - start);
}
if (nptr != NULL) {
@@ -1698,7 +1721,7 @@ bool rem_backslash(const char *str)
|| (str[1] != NUL
&& str[1] != '*'
&& str[1] != '?'
- && !vim_isfilec(str[1])));
+ && !vim_isfilec((uint8_t)str[1])));
#else // ifdef BACKSLASH_IN_FILENAME
return str[0] == '\\' && str[1] != NUL;
generated by cgit (git 2.34.1) at 2025-04-28 21:03:15 +0000