beluga/src/syntax_highlighter.c

#include "../include/syntax_highlighter.h"
#include "../include/data.h"
#include "../include/theme.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

extern struct editorConfig E;

const char *c_keywords[] = {
    "if",     "else",     "while",    "for",     "do",       "switch",
    "case",   "break",    "#include", "#define", "continue", "return",
    "goto",   "struct",   "union",    "enum",    "typedef",  "static",
    "extern", "const",    "volatile", "sizeof",  "auto",     "register",
    "inline", "restrict", NULL};

// C types
const char *c_types[] = {"int",    "char", "float", "double",
                         "void",   "long", "short", "unsigned",
                         "signed", "bool", NULL};

// 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 == '#';
}

// Check if string is a keyword
int is_keyword(const char *word) {
  for (int i = 0; c_keywords[i] != NULL; i++) {
    if (strcmp(word, c_keywords[i]) == 0)
      return 1;
  }
  return 0;
}

// Check if string is a type
int is_type(const char *word) {
  for (int i = 0; c_types[i] != NULL; i++) {
    if (strcmp(word, c_types[i]) == 0)
      return 1;
  }
  return 0;
}

// Get color code for token type
const char *get_color(TokenType type) {
  switch (type) {
  case TOKEN_KEYWORD:
    return E.theme.COLOR_KEYWORD;
  case TOKEN_TYPE:
    return E.theme.COLOR_TYPE;
  case TOKEN_STRING:
    return E.theme.COLOR_STRING;
  case TOKEN_COMMENT:
    return E.theme.COLOR_COMMENT;
  case TOKEN_NUMBER:
    return E.theme.COLOR_NUMBER;
  default:
    return E.theme.COLOR_DEFAULT;
  }
}

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
  int result_pos = 0;
  int i = 0;

  while (line[i] != '\0' && line[i] != '\n') {
    // Skip whitespace
    if (line[i] == ' ' || line[i] == '\t') {
      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++];
      }
      result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
      continue;
    }

    // Handle line comments
    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++];
      }
      result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
      continue;
    }

    // Handle block comments
    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++];
      result[result_pos++] = line[i++];
      while (line[i] != '\0') {
        if (line[i] == '*' && line[i + 1] == '/') {
          result[result_pos++] = line[i++];
          result[result_pos++] = line[i++];
          break;
        }
        result[result_pos++] = line[i++];
      }
      result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
      continue;
    }

    // Handle strings
    if (line[i] == '"') {
      result_pos += sprintf(&result[result_pos], "%s\"", E.theme.COLOR_STRING);
      i++;
      while (line[i] != '\0' && line[i] != '"') {
        if (line[i] == '\\') {
          result[result_pos++] = line[i++];
          result[result_pos++] = line[i++];
        } else {
          result[result_pos++] = line[i++];
        }
      }
      if (line[i] == '"')
        result[result_pos++] = line[i++];
      result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
      continue;
    }

    // Handle character literals
    if (line[i] == '\'') {
      result_pos += sprintf(&result[result_pos], "%s'", E.theme.COLOR_STRING);
      i++;
      while (line[i] != '\0' && line[i] != '\'') {
        if (line[i] == '\\') {
          result[result_pos++] = line[i++];
          result[result_pos++] = line[i++];
        } else {
          result[result_pos++] = line[i++];
        }
      }
      if (line[i] == '\'')
        result[result_pos++] = line[i++];
      result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
      continue;
    }

    // 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++];
      }
      result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
      continue;
    }

    // Handle identifiers and keywords
    if (is_word_char(line[i])) {
      int start = i;
      while (is_word_char(line[i]))
        i++;

      char word[256];
      strncpy(word, &line[start], i - start);
      word[i - start] = '\0';

      TokenType type = TOKEN_DEFAULT;
      if (is_keyword(word))
        type = TOKEN_KEYWORD;
      else if (is_type(word))
        type = TOKEN_TYPE;

      result_pos += sprintf(&result[result_pos], "%s%s%s", get_color(type),
                            word, COLOR_RESET);
      continue;
    }

    // Handle operators and other characters
    result_pos += sprintf(&result[result_pos], "%s", E.theme.COLOR_DEFAULT);
    result[result_pos++] = line[i++];
    result_pos += sprintf(&result[result_pos], "%s", COLOR_RESET);
  }

  result[result_pos] = '\0';
  *length = result_pos + 1;
  return result;
}