arthur/beluga
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 7 Wiki Activity

temp commit

Browse Source
This commit is contained in:
arthur barraux
2026-05-22 13:40:03 +02:00
parent bc66e673fa
commit edb5384f0e
23 changed files with 848 additions and 621 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/syntax_highlighter.c
+80 -29
View File
@@ -1,5 +1,6 @@
#include "../include/syntax_highlighter.h"
#include "../include/data.h"
#include "../include/utf8.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
@@ -18,10 +19,52 @@ const char *c_types[] = {"int", "char", "float", "double",
"void", "long", "short", "unsigned",
"signed", "bool", NULL};
// Returns the byte length of the UTF-8 character starting at s.
// Never returns 0 for a non-NUL byte, so callers won't infinite-loop.
static int utf8_char_len(const char *s)
{
unsigned char c = (unsigned char)*s;
if (c == 0) return 0;
if (c < 0x80) return 1;
if ((c & 0xE0) == 0xC0) return 2;
if ((c & 0xF0) == 0xE0) return 3;
if ((c & 0xF8) == 0xF0) return 4;
return 1; // continuation byte or invalid — advance 1 to avoid infinite loop
}
// Copy one full UTF-8 character from src+i into dst+pos, advance both indices.
static void copy_utf8_char(char *dst, int *dst_pos, const char *src, int *src_pos)
{
int len = utf8_char_len(&src[*src_pos]);
for (int b = 0; b < len; b++)
dst[(*dst_pos)++] = src[(*src_pos)++];
}
// Check if character is alphanumeric or underscore
int is_word_char(char c) {
return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') ||
(c >= '0' && c <= '9') || c == '_' || c == '#';
int is_word_char(const char *s)
{
uint32_t cp = utf8Decode(&s);
if ((cp >= 'a' && cp <= 'z') || (cp >= 'A' && cp <= 'Z') ||
(cp >= '0' && cp <= '9') || cp == '_' || cp == '#')
return 1;
if (cp == 0xFFFD) return 0;
if (cp >= 0x00C0 && cp <= 0x017F) return 1;
if (cp >= 0x0370 && cp <= 0x03FF) return 1;
if (cp >= 0x0400 && cp <= 0x04FF) return 1;
if (cp >= 0x0600 && cp <= 0x06FF) return 1;
if (cp >= 0x05D0 && cp <= 0x05EA) return 1;
if (cp >= 0x0900 && cp <= 0x097F) return 1;
if (cp >= 0x4E00 && cp <= 0x9FFF) return 1;
if ((cp >= 0x3040 && cp <= 0x309F) ||
(cp >= 0x30A0 && cp <= 0x30FF)) return 1;
if (cp >= 0xAC00 && cp <= 0xD7A3) return 1;
if ((cp >= 0x0660 && cp <= 0x0669) ||
(cp >= 0x06F0 && cp <= 0x06F9)) return 1;
return 0;
}
// Check if string is a keyword
@@ -65,26 +108,29 @@ int comment_section = 0;
// Highlight a line of C code and return the highlighted string
// Returns a newly allocated string that must be freed by the caller
char *highlight_line(const char *line, int *length) {
char *result = malloc(1024); // Allocate space for result
// Each byte can expand to at most (color_prefix + 4 bytes + color_reset).
// Allocate generously based on line length to avoid overflow.
int line_len = strlen(line);
int buf_size = line_len * 32 + 256;
char *result = malloc(buf_size);
int result_pos = 0;
int i = 0;
while (line[i] != '\0' && line[i] != '\n') {
// Skip whitespace
// Skip whitespace — copy full UTF-8 char (whitespace is always ASCII,
// but using copy_utf8_char keeps the pattern consistent)
if (line[i] == ' ' || line[i] == '\t') {
result[result_pos++] = line[i++];
copy_utf8_char(result, &result_pos, line, &i);
continue;
}
if (comment_section) {
result_pos += sprintf(&result[result_pos], "%s", E.theme.COLOR_COMMENT);
while (line[i] != '\0' && line[i] != '\n') {
if (line[i] == '*' && line[i + 1] == '/') {
comment_section = 0;
}
result[result_pos++] = line[i++];
if (line[i] == '*' && line[i + 1] == '/') {
comment_section = 0;
}
copy_utf8_char(result, &result_pos, line, &i);
}
result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
continue;
@@ -94,14 +140,14 @@ char *highlight_line(const char *line, int *length) {
if (line[i] == '/' && line[i + 1] == '/') {
result_pos += sprintf(&result[result_pos], "%s", E.theme.COLOR_COMMENT);
while (line[i] != '\0' && line[i] != '\n') {
result[result_pos++] = line[i++];
copy_utf8_char(result, &result_pos, line, &i);
}
result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
continue;
}
// Handle block comments
if ((line[i] == '/' && line[i + 1] == '*')) {
if (line[i] == '/' && line[i + 1] == '*') {
comment_section = 1;
result_pos += sprintf(&result[result_pos], "%s", E.theme.COLOR_COMMENT);
result[result_pos++] = line[i++];
@@ -110,9 +156,10 @@ char *highlight_line(const char *line, int *length) {
if (line[i] == '*' && line[i + 1] == '/') {
result[result_pos++] = line[i++];
result[result_pos++] = line[i++];
comment_section = 0;
break;
}
result[result_pos++] = line[i++];
copy_utf8_char(result, &result_pos, line, &i);
}
result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
continue;
@@ -125,9 +172,9 @@ char *highlight_line(const char *line, int *length) {
while (line[i] != '\0' && line[i] != '"') {
if (line[i] == '\\') {
result[result_pos++] = line[i++];
result[result_pos++] = line[i++];
copy_utf8_char(result, &result_pos, line, &i);
} else {
result[result_pos++] = line[i++];
copy_utf8_char(result, &result_pos, line, &i);
}
}
if (line[i] == '"')
@@ -143,9 +190,9 @@ char *highlight_line(const char *line, int *length) {
while (line[i] != '\0' && line[i] != '\'') {
if (line[i] == '\\') {
result[result_pos++] = line[i++];
result[result_pos++] = line[i++];
copy_utf8_char(result, &result_pos, line, &i);
} else {
result[result_pos++] = line[i++];
copy_utf8_char(result, &result_pos, line, &i);
}
}
if (line[i] == '\'')
@@ -157,22 +204,26 @@ char *highlight_line(const char *line, int *length) {
// Handle numbers
if (line[i] >= '0' && line[i] <= '9') {
result_pos += sprintf(&result[result_pos], "%s", E.theme.COLOR_NUMBER);
while (is_word_char(line[i]) || line[i] == '.') {
result[result_pos++] = line[i++];
while (is_word_char(&line[i]) || line[i] == '.') {
copy_utf8_char(result, &result_pos, line, &i);
}
result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
continue;
}
// Handle identifiers and keywords
if (is_word_char(line[i])) {
if (is_word_char(&line[i])) {
int start = i;
while (is_word_char(line[i]))
i++;
// Advance by full UTF-8 character widths, not single bytes
while (line[i] != '\0' && is_word_char(&line[i]))
i += utf8_char_len(&line[i]);
char word[256];
strncpy(word, &line[start], i - start);
word[i - start] = '\0';
int word_len = i - start;
if (word_len >= (int)sizeof(word))
word_len = (int)sizeof(word) - 1;
strncpy(word, &line[start], word_len);
word[word_len] = '\0';
TokenType type = TOKEN_DEFAULT;
if (is_keyword(word))
@@ -185,9 +236,9 @@ char *highlight_line(const char *line, int *length) {
continue;
}
// Handle operators and other characters
// Handle operators and other characters (including non-ASCII multi-byte)
result_pos += sprintf(&result[result_pos], "%s", E.theme.COLOR_DEFAULT);
result[result_pos++] = line[i++];
copy_utf8_char(result, &result_pos, line, &i);
result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
}