Move character literal processing to the lexer
To match the processing of integer literals, character literals are passed
as a string from lexer to parser then interpreted there. This is just as
awkward as it was for integer literals, without the excuse that we used to
need the information about the dts version to process them correctly.
So, move character literal processing back to the lexer as well, cleaning
things up.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
diff --git a/dtc-lexer.l b/dtc-lexer.l
index ba5d150..0821bde 100644
--- a/dtc-lexer.l
+++ b/dtc-lexer.l
@@ -167,9 +167,23 @@
}
<*>{CHAR_LITERAL} {
- yytext[yyleng-1] = '\0';
- yylval.literal = xstrdup(yytext+1);
- DPRINT("Character literal: %s\n", yylval.literal);
+ struct data d;
+ DPRINT("Character literal: %s\n", yytext);
+
+ d = data_copy_escape_string(yytext+1, yyleng-2);
+ if (d.len == 1) {
+ lexical_error("Empty character literal");
+ yylval.integer = 0;
+ return DT_CHAR_LITERAL;
+ }
+
+ yylval.integer = (unsigned char)d.val[0];
+
+ if (d.len > 2)
+ lexical_error("Character literal has %d"
+ " characters instead of 1",
+ d.len - 1);
+
return DT_CHAR_LITERAL;
}
diff --git a/dtc-parser.y b/dtc-parser.y
index 0ce0815..efe81dd 100644
--- a/dtc-parser.y
+++ b/dtc-parser.y
@@ -32,13 +32,10 @@
extern struct boot_info *the_boot_info;
extern bool treesource_error;
-
-static unsigned char eval_char_literal(const char *s);
%}
%union {
char *propnodename;
- char *literal;
char *labelref;
unsigned int cbase;
uint8_t byte;
@@ -65,7 +62,7 @@
%token DT_DEL_NODE
%token <propnodename> DT_PROPNODENAME
%token <integer> DT_LITERAL
-%token <literal> DT_CHAR_LITERAL
+%token <integer> DT_CHAR_LITERAL
%token <cbase> DT_BASE
%token <byte> DT_BYTE
%token <data> DT_STRING
@@ -336,9 +333,6 @@
integer_prim:
DT_LITERAL
| DT_CHAR_LITERAL
- {
- $$ = eval_char_literal($1);
- }
| '(' integer_expr ')'
{
$$ = $2;
@@ -482,29 +476,3 @@
void yyerror(char const *s) {
print_error("%s", s);
}
-
-static unsigned char eval_char_literal(const char *s)
-{
- int i = 1;
- char c = s[0];
-
- if (c == '\0')
- {
- print_error("empty character literal");
- return 0;
- }
-
- /*
- * If the first character in the character literal is a \ then process
- * the remaining characters as an escape encoding. If the first
- * character is neither an escape or a terminator it should be the only
- * character in the literal and will be returned.
- */
- if (c == '\\')
- c = get_escape_char(s, &i);
-
- if (s[i] != '\0')
- print_error("malformed character literal");
-
- return c;
-}
