mirrors/chibicc
1
0
Fork 0
mirror of https://github.com/rui314/chibicc synced 2024-11-23 22:59:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

Improve error message for multibyte characters

Browse Source
This commit is contained in:
Rui Ueyama 2020-07-20 14:00:00 +09:00
parent 95eb5b01b3
commit 37998be0c1
3 changed files with 74 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
chibicc.h
View File

@ -365,6 +365,7 @@ int encode_utf8(char *buf, uint32_t c);
uint32_t decode_utf8(char **new_pos, char *p);
bool is_ident1(uint32_t c);
bool is_ident2(uint32_t c);
int display_width(char *p, int len);
//
// main.c

2
tokenize.c
View File

@ -41,7 +41,7 @@ static void verror_at(char *filename, char *input, int line_no,
fprintf(stderr, "%.*s\n", (int)(end - line), line);
// Show the error message.
int pos = loc - line + indent;
int pos = display_width(line, loc - line) + indent;
fprintf(stderr, "%*s", pos, ""); // print pos spaces.
fprintf(stderr, "^ ");

72
unicode.c
View File

@ -115,3 +115,75 @@ bool is_ident2(uint32_t c) {
return is_ident1(c) || in_range(range, c);
}
// Returns the number of columns needed to display a given
// character in a fixed-width font.
//
// Based on https://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
static int char_width(uint32_t c) {
static uint32_t range1[] = {
0x0000, 0x001F, 0x007f, 0x00a0, 0x0300, 0x036F, 0x0483, 0x0486,
0x0488, 0x0489, 0x0591, 0x05BD, 0x05BF, 0x05BF, 0x05C1, 0x05C2,
0x05C4, 0x05C5, 0x05C7, 0x05C7, 0x0600, 0x0603, 0x0610, 0x0615,
0x064B, 0x065E, 0x0670, 0x0670, 0x06D6, 0x06E4, 0x06E7, 0x06E8,
0x06EA, 0x06ED, 0x070F, 0x070F, 0x0711, 0x0711, 0x0730, 0x074A,
0x07A6, 0x07B0, 0x07EB, 0x07F3, 0x0901, 0x0902, 0x093C, 0x093C,
0x0941, 0x0948, 0x094D, 0x094D, 0x0951, 0x0954, 0x0962, 0x0963,
0x0981, 0x0981, 0x09BC, 0x09BC, 0x09C1, 0x09C4, 0x09CD, 0x09CD,
0x09E2, 0x09E3, 0x0A01, 0x0A02, 0x0A3C, 0x0A3C, 0x0A41, 0x0A42,
0x0A47, 0x0A48, 0x0A4B, 0x0A4D, 0x0A70, 0x0A71, 0x0A81, 0x0A82,
0x0ABC, 0x0ABC, 0x0AC1, 0x0AC5, 0x0AC7, 0x0AC8, 0x0ACD, 0x0ACD,
0x0AE2, 0x0AE3, 0x0B01, 0x0B01, 0x0B3C, 0x0B3C, 0x0B3F, 0x0B3F,
0x0B41, 0x0B43, 0x0B4D, 0x0B4D, 0x0B56, 0x0B56, 0x0B82, 0x0B82,
0x0BC0, 0x0BC0, 0x0BCD, 0x0BCD, 0x0C3E, 0x0C40, 0x0C46, 0x0C48,
0x0C4A, 0x0C4D, 0x0C55, 0x0C56, 0x0CBC, 0x0CBC, 0x0CBF, 0x0CBF,
0x0CC6, 0x0CC6, 0x0CCC, 0x0CCD, 0x0CE2, 0x0CE3, 0x0D41, 0x0D43,
0x0D4D, 0x0D4D, 0x0DCA, 0x0DCA, 0x0DD2, 0x0DD4, 0x0DD6, 0x0DD6,
0x0E31, 0x0E31, 0x0E34, 0x0E3A, 0x0E47, 0x0E4E, 0x0EB1, 0x0EB1,
0x0EB4, 0x0EB9, 0x0EBB, 0x0EBC, 0x0EC8, 0x0ECD, 0x0F18, 0x0F19,
0x0F35, 0x0F35, 0x0F37, 0x0F37, 0x0F39, 0x0F39, 0x0F71, 0x0F7E,
0x0F80, 0x0F84, 0x0F86, 0x0F87, 0x0F90, 0x0F97, 0x0F99, 0x0FBC,
0x0FC6, 0x0FC6, 0x102D, 0x1030, 0x1032, 0x1032, 0x1036, 0x1037,
0x1039, 0x1039, 0x1058, 0x1059, 0x1160, 0x11FF, 0x135F, 0x135F,
0x1712, 0x1714, 0x1732, 0x1734, 0x1752, 0x1753, 0x1772, 0x1773,
0x17B4, 0x17B5, 0x17B7, 0x17BD, 0x17C6, 0x17C6, 0x17C9, 0x17D3,
0x17DD, 0x17DD, 0x180B, 0x180D, 0x18A9, 0x18A9, 0x1920, 0x1922,
0x1927, 0x1928, 0x1932, 0x1932, 0x1939, 0x193B, 0x1A17, 0x1A18,
0x1B00, 0x1B03, 0x1B34, 0x1B34, 0x1B36, 0x1B3A, 0x1B3C, 0x1B3C,
0x1B42, 0x1B42, 0x1B6B, 0x1B73, 0x1DC0, 0x1DCA, 0x1DFE, 0x1DFF,
0x200B, 0x200F, 0x202A, 0x202E, 0x2060, 0x2063, 0x206A, 0x206F,
0x20D0, 0x20EF, 0x302A, 0x302F, 0x3099, 0x309A, 0xA806, 0xA806,
0xA80B, 0xA80B, 0xA825, 0xA826, 0xFB1E, 0xFB1E, 0xFE00, 0xFE0F,
0xFE20, 0xFE23, 0xFEFF, 0xFEFF, 0xFFF9, 0xFFFB, 0x10A01, 0x10A03,
0x10A05, 0x10A06, 0x10A0C, 0x10A0F, 0x10A38, 0x10A3A, 0x10A3F, 0x10A3F,
0x1D167, 0x1D169, 0x1D173, 0x1D182, 0x1D185, 0x1D18B, 0x1D1AA, 0x1D1AD,
0x1D242, 0x1D244, 0xE0001, 0xE0001, 0xE0020, 0xE007F, 0xE0100, 0xE01EF,
-1,
};
if (in_range(range1, c))
return 0;
static uint32_t range2[] = {
0x1100, 0x115F, 0x2329, 0x2329, 0x232A, 0x232A, 0x2E80, 0x303E,
0x3040, 0xA4CF, 0xAC00, 0xD7A3, 0xF900, 0xFAFF, 0xFE10, 0xFE19,
0xFE30, 0xFE6F, 0xFF00, 0xFF60, 0xFFE0, 0xFFE6, 0x1F000, 0x1F644,
0x20000, 0x2FFFD, 0x30000, 0x3FFFD, -1,
};
if (in_range(range2, c))
return 2;
return 1;
}
// Returns the number of columns needed to display a given
// string in a fixed-width font.
int display_width(char *p, int len) {
char *start = p;
int w = 0;
while (p - start < len) {
uint32_t c = decode_utf8(&p, p);
w += char_width(c);
}
return w;
}