Re: L'\0' handling

[Christopher Li <sparse@chrisli.org>]

[-- Attachment #1: Type: text/plain, Size: 545 bytes --]

On Thu, Apr 8, 2010 at 8:54 AM, Michael Stefaniuc <mstefani@redhat.com> wrote:
> I didn't assert that the feature shouldn't be implemented, just that it
> is a known missing feature that the normal sparse consumer didn't need
> until now.

Yura, do you want to give this patch a try?

It is nasty that L'\0' start from an identifier letter. I try my best
not to slow down the
hot path. The test is done inside get_one_identifier() after the ident
hash is built.
It look a little bit out of palace but faster than testing 'L' before hand.

Chris

[-- Attachment #2: 0005-Allow-parsing-L-0.patch --]
[-- Type: application/octet-stream, Size: 3585 bytes --]

From 6c8d9169ebe8198d8b994825ce9d4eb1b7339129 Mon Sep 17 00:00:00 2001
From: Christopher Li <sparse@chrisli.org>
Date: Thu, 8 Apr 2010 14:05:29 -0700
Subject: [PATCH 5/5] Allow parsing L'\0'

Signed-off-by: Christopher Li <sparse@chrisli.org>
---
 expression.c  |    3 ++-
 ident-list.h  |    3 +++
 pre-process.c |    1 +
 token.h       |    1 +
 tokenize.c    |   12 ++++++++----
 5 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/expression.c b/expression.c
index c9277da..67e05e7 100644
--- a/expression.c
+++ b/expression.c
@@ -397,9 +397,10 @@ struct token *primary_expression(struct token *token, struct expression **tree)
 
 	switch (token_type(token)) {
 	case TOKEN_CHAR:
+	case TOKEN_LONG_CHAR:
 		expr = alloc_expression(token->pos, EXPR_VALUE);   
 		expr->flags = Int_const_expr;
-		expr->ctype = &int_ctype; 
+		expr->ctype = token_type(token) == TOKEN_CHAR ? &int_ctype : &long_ctype;
 		expr->value = (unsigned char) token->character;
 		token = token->next;
 		break;
diff --git a/ident-list.h b/ident-list.h
index 0ee81bc..b94aece 100644
--- a/ident-list.h
+++ b/ident-list.h
@@ -25,6 +25,9 @@ IDENT(__attribute); IDENT(__attribute__);
 IDENT(volatile); IDENT(__volatile); IDENT(__volatile__);
 IDENT(double);
 
+/* Special case for L'\t' */
+IDENT(L);
+
 /* Extended gcc identifiers */
 IDENT(asm); IDENT_RESERVED(__asm); IDENT_RESERVED(__asm__);
 IDENT(alignof); IDENT_RESERVED(__alignof); IDENT_RESERVED(__alignof__); 
diff --git a/pre-process.c b/pre-process.c
index 34b21ff..058f24b 100644
--- a/pre-process.c
+++ b/pre-process.c
@@ -864,6 +864,7 @@ static int token_different(struct token *t1, struct token *t2)
 		different = t1->argnum != t2->argnum;
 		break;
 	case TOKEN_CHAR:
+	case TOKEN_LONG_CHAR:
 		different = t1->character != t2->character;
 		break;
 	case TOKEN_STRING: {
diff --git a/token.h b/token.h
index ebc94b4..c527e78 100644
--- a/token.h
+++ b/token.h
@@ -67,6 +67,7 @@ enum token_type {
 	TOKEN_ZERO_IDENT,
 	TOKEN_NUMBER,
 	TOKEN_CHAR,
+	TOKEN_LONG_CHAR,
 	TOKEN_STRING,
 	TOKEN_SPECIAL,
 	TOKEN_STREAMBEGIN,
diff --git a/tokenize.c b/tokenize.c
index 93dd007..cf05826 100644
--- a/tokenize.c
+++ b/tokenize.c
@@ -145,7 +145,8 @@ const char *show_token(const struct token *token)
 	case TOKEN_SPECIAL:
 		return show_special(token->special);
 
-	case TOKEN_CHAR: {
+	case TOKEN_CHAR: 
+	case TOKEN_LONG_CHAR: {
 		char *ptr = buffer;
 		int c = token->character;
 		*ptr++ = '\'';
@@ -527,7 +528,7 @@ static int escapechar(int first, int type, stream_t *stream, int *valp)
 	return next;
 }
 
-static int get_char_token(int next, stream_t *stream)
+static int get_char_token(int next, stream_t *stream, enum token_type type)
 {
 	int value;
 	struct token *token;
@@ -540,7 +541,7 @@ static int get_char_token(int next, stream_t *stream)
 	}
 
 	token = stream->token;
-	token_type(token) = TOKEN_CHAR;
+	token_type(token) = type;
 	token->character = value & 0xff;
 
 	add_token(stream);
@@ -702,7 +703,7 @@ static int get_one_special(int c, stream_t *stream)
 	case '"':
 		return get_string_token(next, stream);
 	case '\'':
-		return get_char_token(next, stream);
+		return get_char_token(next, stream, TOKEN_CHAR);
 	case '/':
 		if (next == '/')
 			return drop_stream_eoln(stream);
@@ -880,6 +881,9 @@ static int get_one_identifier(int c, stream_t *stream)
 
 	ident = create_hashed_ident(buf, len, hash);
 
+	if (ident == &L_ident && next == '\'')
+		return get_char_token(nextchar(stream), stream, TOKEN_LONG_CHAR);
+
 	/* Pass it on.. */
 	token = stream->token;
 	token_type(token) = TOKEN_IDENT;
-- 
1.6.6.1