M2-Planet/cc_reader.c

/* Copyright (C) 2016 Jeremiah Orians
 * This file is part of stage0.
 *
 * stage0 is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * stage0 is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with stage0.  If not, see <http://www.gnu.org/licenses/>.
 */

#include "cc.h"
FILE* input;
struct token_list* token;
int line;
char* file;

int clearWhiteSpace(int c)
{
	if((32 == c) || (9 == c)) return clearWhiteSpace(fgetc(input));
	else if (10 == c)
	{
		line = line + 1;
		return clearWhiteSpace(fgetc(input));
	}
	return c;
}

int string_index;
int consume_byte(struct token_list* current, int c)
{
	current->s[string_index] = c;
	string_index = string_index + 1;
	return fgetc(input);
}

int consume_word(struct token_list* current, int c, int frequent)
{
	int escape = FALSE;
	do
	{
		if(!escape && '\\' == c ) escape = TRUE;
		else escape = FALSE;
		c = consume_byte(current, c);
	} while(escape || (c != frequent));
	return fgetc(input);
}


void fixup_label(struct token_list* current)
{
	int hold = ':';
	int prev;
	int i = 0;
	do
	{
		prev = hold;
		hold = current->s[i];
		current->s[i] = prev;
		i = i + 1;
	} while(0 != hold);
}

int preserve_keyword(struct token_list* current, int c)
{
	while((('a' <= c) & (c <= 'z')) | (('A' <= c) & (c <= 'Z')) | (('0' <= c) & (c <= '9')) | (c == '_'))
	{
		c = consume_byte(current, c);
	}
	if(':' == c)
	{
		fixup_label(current);
		return 32;
	}
	return c;
}

int preserve_symbol(struct token_list* current, int c)
{
	while((c == '<') | (c == '=') | (c == '>') | (c == '|') | (c == '&') | (c == '!') | (c == '-'))
	{
		c = consume_byte(current, c);
	}
	return c;
}

int purge_macro(int ch)
{
	while(10 != ch) ch = fgetc(input);
	return ch;
}

int get_token(int c)
{
	struct token_list* current = calloc(1, sizeof(struct token_list));
	current->s = calloc(MAX_STRING, sizeof(char));

reset:
	string_index = 0;

	c = clearWhiteSpace(c);
	if('#' == c)
	{
		c = purge_macro(c);
		goto reset;
	}
	else if((('a' <= c) & (c <= 'z')) | (('A' <= c) & (c <= 'Z')) | (('0' <= c) & (c <= '9')) | (c == '_'))
	{
		c = preserve_keyword(current, c);
	}
	else if((c == '<') | (c == '=') | (c == '>') | (c == '|') | (c == '&') | (c == '!') | ( c == '-'))
	{
		c = preserve_symbol(current, c);
	}
	else if(c == 39)
	{ /* 39 == ' */
		c = consume_word(current, c, 39);
	}
	else if(c == '"')
	{
		c = consume_word(current, c, '"');
	}
	else if(c == '/')
	{
		c = consume_byte(current, c);
		if(c == '*')
		{
			c = fgetc(input);
			while(c != '/')
			{
				while(c != '*')
				{
					c = fgetc(input);
					if(10 == c) line = line + 1;
				}
				c = fgetc(input);
				if(10 == c) line = line + 1;
			}
			c = fgetc(input);
			goto reset;
		}
		else if(c == '/')
		{
			c = fgetc(input);
			goto reset;
		}
	}
	else if(c == EOF)
	{
		free(current);
		return c;
	}
	else
	{
		c = consume_byte(current, c);
	}

	current->prev = token;
	current->next = token;
	current->linenumber = line;
	current->filename = file;
	token = current;
	return c;
}

struct token_list* reverse_list(struct token_list* head)
{
	struct token_list* root = NULL;
	while(NULL != head)
	{
		struct token_list* next = head->next;
		head->next = root;
		root = head;
		head = next;
	}
	return root;
}

struct token_list* read_all_tokens(FILE* a, struct token_list* current, char* filename)
{
	input  = a;
	line = 1;
	file = filename;
	token = current;
	int ch =fgetc(input);
	while(EOF != ch) ch = get_token(ch);

	return token;
}