X-Git-Url: http://nsz.repo.hu/git/?a=blobdiff_plain;f=lexer.c;h=1300b3d26f23cda1c90093658115266e03a941ab;hb=22420f9404b76d3ab2536c7d3903cbcf05a792a8;hp=2a6cc2c6c164c7fd2e2bbcf799d50bcc368ac7f1;hpb=d5a5e90eca7d95d0efa66a6e8dd5ca0ed031321b;p=cparser

diff --git a/lexer.c b/lexer.c
index 2a6cc2c..1300b3d 100644
--- a/lexer.c
+++ b/lexer.c
@@ -17,13 +17,12 @@
 
 static int         c;
 token_t            lexer_token;
+symbol_t          *symbol_L;
 static FILE       *input;
 static char        buf[1024 + MAX_PUTBACK];
 static const char *bufend;
 static const char *bufpos;
 static strset_t    stringset;
-//static FILE      **input_stack;
-//static char      **buf_stack;
 
 static void error_prefix_at(const char *input_name, unsigned linenr)
 {
@@ -60,11 +59,16 @@ static inline void next_real_char(void)
 
 static inline void put_back(int pc)
 {
-	char *p = (char*) bufpos - 1;
-	bufpos--;
-	assert(p >= buf);
+	assert(bufpos >= buf);
+	assert(bufpos < buf+MAX_PUTBACK || *bufpos == pc);
+
+	char *p = buf + (bufpos - buf);
 	*p = pc;
 
+	/* going backwards in the buffer is legal as long as it's not more often
+	 * than MAX_PUTBACK */
+	bufpos--;
+
 #ifdef DEBUG_CHARS
 	printf("putback '%c'\n", pc);
 #endif
@@ -85,9 +89,12 @@ static inline void next_char(void);
 		lexer_token.source_position.linenr++; \
 		code;
 
+#define eat(c_type)  do { assert(c == c_type); next_char(); } while(0)
+
 static void maybe_concat_lines(void)
 {
-	next_char();
+	eat('\\');
+
 	switch(c) {
 	MATCH_NEWLINE(return;)
 
@@ -103,6 +110,7 @@ static inline void next_char(void)
 {
 	next_real_char();
 
+#if 0
 	/* filter trigraphs */
 	if(UNLIKELY(c == '\\')) {
 		maybe_concat_lines();
@@ -138,6 +146,8 @@ static inline void next_char(void)
 	}
 
 end_of_next_char:
+#endif
+	(void) maybe_concat_lines;
 #ifdef DEBUG_CHARS
 	printf("nchar '%c'\n", c);
 #else
@@ -271,6 +281,21 @@ static void parse_integer_suffix(void)
 	}
 }
 
+static void parse_floating_suffix(void)
+{
+	switch(c) {
+	/* TODO: do something usefull with the suffixes... */
+	case 'f':
+	case 'F':
+	case 'l':
+	case 'L':
+		next_char();
+		break;
+	default:
+		break;
+	}
+}
+
 static void parse_number_hex(void)
 {
 	assert(c == 'x' || c == 'X');
@@ -355,6 +380,8 @@ static void parse_floatingpoint_exponent(long double value)
 
 	lexer_token.type         = T_FLOATINGPOINT;
 	lexer_token.v.floatvalue = value;
+
+	parse_floating_suffix();
 }
 
 static void parse_floatingpoint_fract(int integer_part)
@@ -376,6 +403,8 @@ static void parse_floatingpoint_fract(int integer_part)
 
 	lexer_token.type         = T_FLOATINGPOINT;
 	lexer_token.v.floatvalue = value;
+
+	parse_floating_suffix();
 }
 
 static void parse_number_dec(void)
@@ -481,40 +510,40 @@ static int parse_hex_sequence(void)
 
 static int parse_escape_sequence(void)
 {
-	while(1) {
-		int ec = c;
-		next_char();
+	eat('\\');
 
-		switch(ec) {
-		case '"':  return '"';
-		case '\'': return'\'';
-		case '\\': return '\\';
-		case '?': return '\?';
-		case 'a': return '\a';
-		case 'b': return '\b';
-		case 'f': return '\f';
-		case 'n': return '\n';
-		case 'r': return '\r';
-		case 't': return '\t';
-		case 'v': return '\v';
-		case 'x':
-			return parse_hex_sequence();
-		case '0':
-		case '1':
-		case '2':
-		case '3':
-		case '4':
-		case '5':
-		case '6':
-		case '7':
-			return parse_octal_sequence();
-		case EOF:
-			parse_error("reached end of file while parsing escape sequence");
-			return EOF;
-		default:
-			parse_error("unknown escape sequence");
-			return EOF;
-		}
+	int ec = c;
+	next_char();
+
+	switch(ec) {
+	case '"':  return '"';
+	case '\'': return'\'';
+	case '\\': return '\\';
+	case '?': return '\?';
+	case 'a': return '\a';
+	case 'b': return '\b';
+	case 'f': return '\f';
+	case 'n': return '\n';
+	case 'r': return '\r';
+	case 't': return '\t';
+	case 'v': return '\v';
+	case 'x':
+		return parse_hex_sequence();
+	case '0':
+	case '1':
+	case '2':
+	case '3':
+	case '4':
+	case '5':
+	case '6':
+	case '7':
+		return parse_octal_sequence();
+	case EOF:
+		parse_error("reached end of file while parsing escape sequence");
+		return EOF;
+	default:
+		parse_error("unknown escape sequence");
+		return EOF;
 	}
 }
 
@@ -544,12 +573,12 @@ static void parse_string_literal(void)
 	assert(c == '"');
 	next_char();
 
+	int tc;
 	while(1) {
 		switch(c) {
 		case '\\':
-			next_char();
-			int ec = parse_escape_sequence();
-			obstack_1grow(&symbol_obstack, ec);
+			tc = parse_escape_sequence();
+			obstack_1grow(&symbol_obstack, tc);
 			break;
 
 		case EOF:
@@ -590,14 +619,12 @@ end_of_string:
 
 static void parse_character_constant(void)
 {
-	assert(c == '\'');
-	next_char();
+	eat('\'');
 
 	int found_char = 0;
 	while(1) {
 		switch(c) {
 		case '\\':
-			next_char();
 			found_char = parse_escape_sequence();
 			break;
 
@@ -778,7 +805,7 @@ static void parse_preprocessor_identifier(void)
 	}
 }
 
-static void parse_preprocessor_directive()
+static void parse_preprocessor_directive(void)
 {
 	next_pp_token();
 
@@ -836,6 +863,12 @@ void lexer_next_preprocessing_token(void)
 
 		SYMBOL_CHARS
 			parse_symbol();
+			/* might be a wide string ( L"string" ) */
+			if(c == '"' && (lexer_token.type == T_IDENTIFIER &&
+			   lexer_token.v.symbol == symbol_L)) {
+			   	parse_string_literal();
+			   	return;
+			}
 			return;
 
 		DIGITS
@@ -1011,10 +1044,14 @@ void init_lexer(void)
 void lexer_open_stream(FILE *stream, const char *input_name)
 {
 	input                                  = stream;
-	lexer_token.source_position.linenr     = 1;
+	lexer_token.source_position.linenr     = 0;
 	lexer_token.source_position.input_name = input_name;
 
-	next_char();
+	symbol_L = symbol_table_insert("L");
+
+	/* place a virtual \n at the beginning so the lexer knows that we're
+	 * at the beginning of a line */
+	c = '\n';
 }
 
 void exit_lexer(void)