libhl/source/hl.h

239 lines
4.6 KiB
C
Raw Normal View History

#include <stdio.h>
#include <uthash.h>
#include <ctype.h>
#include <string.h>
#include "chad.h"
2023-08-19 18:49:10 -04:00
#include "regex.h"
2023-08-21 10:13:24 -04:00
// -------------------
// ### Definitions ###
// -------------------
typedef enum {
KEYSYMBOL,
KEYWORD,
MATCH,
REGION
} token_type_t;
typedef struct {
2023-08-23 19:58:38 -04:00
char * key;
attribute_callback_t callback;
UT_hash_handle hh;
} display_t;
typedef struct {
void * attributes;
struct hl_group_t * link;
} hl_group_t;
typedef struct {
hl_group_t * hl;
token_type_t t;
char * syntax;
} token_t;
2023-08-23 19:58:38 -04:00
typedef void (*attribute_callback_t) (const char * const string,
const int length,
void * const attributes);
// GLOBALS
token_t * token_table[1000];
int token_table_top = 0;
2023-08-23 19:58:38 -04:00
display_t * display_table = NULL;
2023-08-21 10:13:24 -04:00
// --------------------------------
// ### Constructors/Destructors ###
// --------------------------------
2023-08-23 19:58:38 -04:00
2023-08-21 10:13:24 -04:00
void new_display_mode(display_t * mode) {
HASH_ADD_STR(display_table,
key,
mode);
}
2023-08-23 19:58:38 -04:00
int free_token(token_t * token) {
2023-08-21 10:13:24 -04:00
free(token->hl);
free(token->syntax);
2023-08-23 19:58:38 -04:00
2023-08-21 10:13:24 -04:00
return 0;
}
2023-08-23 19:58:38 -04:00
int append_token(token_t * token) {
2023-08-19 18:49:10 -04:00
token_table[token_table_top++] = token;
2023-08-23 19:58:38 -04:00
2023-08-19 18:49:10 -04:00
return 0;
}
token_t * new_symbol_token(const char * const word,
hl_group_t * const g) {
char * new_word = strdup(word);
token_t * mt = (token_t*)malloc(sizeof(token_t));
2023-08-23 19:58:38 -04:00
mt->hl = g;
mt->t = KEYSYMBOL;
2023-08-19 18:49:10 -04:00
mt->syntax = new_word;
2023-08-23 19:58:38 -04:00
2023-08-19 18:49:10 -04:00
append_token(mt);
2023-08-23 19:58:38 -04:00
return mt;
}
2023-08-19 18:49:10 -04:00
int new_symbol_tokens(const char * const * symbols,
hl_group_t * const g) {
int i = 0;
2023-08-23 19:58:38 -04:00
2023-08-19 18:49:10 -04:00
while (*symbols) {
2023-08-23 19:58:38 -04:00
if(new_symbol_token(*symbols, g)) {
++i;
}
2023-08-19 18:49:10 -04:00
++symbols;
}
return i;
}
2023-08-21 14:07:39 -04:00
int new_char_tokens(const char * characters,
hl_group_t * const g) {
2023-08-23 19:58:38 -04:00
int i = 0;
char buffer[2] = "";
2023-08-19 18:49:10 -04:00
buffer[1] = '\00';
2023-08-23 19:58:38 -04:00
for(const char * s = characters; *s != '\0'; s++) {
2023-08-19 18:49:10 -04:00
buffer[0] = *s;
2023-08-23 19:58:38 -04:00
if(new_symbol_token(buffer, g)) {
2023-08-19 18:49:10 -04:00
++i;
}
2023-08-19 18:49:10 -04:00
}
2023-08-23 19:58:38 -04:00
2023-08-19 18:49:10 -04:00
return i;
}
token_t * new_keyword_token(const char * const word,
hl_group_t * const g) {
2023-08-23 19:58:38 -04:00
size_t word_length = strlen(word);
char * new_word = (char*)malloc(word_length + 4 + 1);
2023-08-19 18:49:10 -04:00
memcpy(new_word, "\\<", 2);
memcpy(new_word + 2, word, word_length);
strcpy(new_word + 2 + word_length, "\\>");
token_t * mt = (token_t*)malloc(sizeof(token_t));
2023-08-23 19:58:38 -04:00
mt->hl = g;
mt->t = KEYWORD;
2023-08-19 18:49:10 -04:00
mt->syntax = new_word;
2023-08-23 19:58:38 -04:00
2023-08-19 18:49:10 -04:00
append_token(mt);
2023-08-23 19:58:38 -04:00
2023-08-19 18:49:10 -04:00
return mt;
}
2023-08-23 19:58:38 -04:00
int new_keyword_tokens(const char * const * words,
hl_group_t * const g) {
2023-08-21 10:13:24 -04:00
int i = 0;
2023-08-23 19:58:38 -04:00
2023-08-21 10:13:24 -04:00
while (*words) {
2023-08-23 19:58:38 -04:00
if(new_keyword_token(*words, g)) {
2023-08-21 10:13:24 -04:00
++i;
}
++words;
}
return i;
}
2023-08-19 18:49:10 -04:00
token_t * new_token(const char * const word,
const token_type_t t,
hl_group_t * const g) {
2023-08-23 19:58:38 -04:00
switch (t) {
2023-08-19 18:49:10 -04:00
case KEYSYMBOL: {
return new_symbol_token(word, g);
2023-08-23 19:58:38 -04:00
}
2023-08-19 18:49:10 -04:00
case KEYWORD: {
return new_keyword_token(word, g);
2023-08-23 19:58:38 -04:00
}
2023-08-19 18:49:10 -04:00
case MATCH: {
} break;
case REGION: {
} break;
}
2023-08-23 19:58:38 -04:00
2023-08-21 10:13:24 -04:00
return NULL;
2023-08-19 18:49:10 -04:00
}
2023-08-21 10:13:24 -04:00
// --------------------
// ### Highlighting ###
// --------------------
2023-08-23 19:58:38 -04:00
int token_fits(const token_t * const token,
const char * const to,
const int string_offset,
int * match_offset) {
2023-08-19 18:49:10 -04:00
const char * const pattern = token->syntax;
2023-08-23 19:58:38 -04:00
if (! pattern) {
2023-08-19 18:49:10 -04:00
return true;
}
2023-08-19 18:49:10 -04:00
2023-08-21 14:07:39 -04:00
return regex_match(pattern, to, string_offset, match_offset);
}
void render_string(const char * const string,
2023-08-23 19:58:38 -04:00
const char * const mode) {
for (const char * s = string; *s != '\00';) {
int f;
2023-08-21 14:07:39 -04:00
int token_index = 0;
int offset;
2023-08-23 19:58:38 -04:00
2023-08-21 14:07:39 -04:00
for (; token_index < token_table_top; token_index++) {
f = token_fits(token_table[token_index], string, s - string, &offset);
2023-08-23 19:58:38 -04:00
if (f) {
break;
}
}
//
display_t * display;
HASH_FIND_STR(display_table,
mode,
display);
//
2023-08-19 07:21:43 -04:00
if (f) {
2023-08-23 19:58:38 -04:00
for (int i = 0; i < offset; i++) {
2023-08-21 14:07:39 -04:00
display->callback(s + i,
2023-08-23 19:58:38 -04:00
0,
token_table[token_index]->hl->attributes);
2023-08-21 14:07:39 -04:00
}
display->callback(s + offset,
f,
2023-08-21 14:07:39 -04:00
token_table[token_index]->hl->attributes);
s += f + offset;
} else {
display->callback(s,
0,
NULL);
++s;
}
}
}
2023-08-21 10:13:24 -04:00
// -------------------------
// ### Library Mangement ###
// -------------------------
2023-08-23 19:58:38 -04:00
2023-08-21 10:13:24 -04:00
int hl_init(void) {
return 0;
}
int hl_deinit(void) {
2023-08-23 19:58:38 -04:00
for (int i = 0; i < token_table_top; i++) {
2023-08-21 10:13:24 -04:00
free_token(token_table[i]);
}
2023-08-23 19:58:38 -04:00
2023-08-21 10:13:24 -04:00
return 0;
}