aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--ChangeLog8
-rw-r--r--encoding.c8
-rw-r--r--include/ruby/encoding.h6
-rw-r--r--parse.y18
-rw-r--r--re.c2
-rw-r--r--string.c10
6 files changed, 30 insertions, 22 deletions
diff --git a/ChangeLog b/ChangeLog
index cd9532064e..8c71e50718 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,11 @@
+Tue Nov 27 11:14:57 2007 Tanaka Akira <akr@fsij.org>
+
+ * include/ruby/encoding.h, encoding.c, re.c, string.c, parse.y:
+ rename ENC_CODERANGE_SINGLE to ENC_CODERANGE_7BIT.
+ rename ENC_CODERANGE_MULTI to ENC_CODERANGE_8BIT.
+ Because single byte 8bit character, such as Shift_JIS 1byte katakana,
+ is represented by ENC_CODERANGE_MULTI even if it is not multi byte.
+
Tue Nov 27 10:45:45 2007 Koichi Sasada <ko1@atdot.net>
* eval.c (rb_method_missing): fix stack trace.
diff --git a/encoding.c b/encoding.c
index 1ee24c2286..403572070e 100644
--- a/encoding.c
+++ b/encoding.c
@@ -407,12 +407,12 @@ rb_enc_compatible(VALUE str1, VALUE str2)
cr2 = rb_enc_str_coderange(str2);
if (cr1 != cr2) {
/* may need to handle ENC_CODERANGE_BROKEN */
- if (cr1 == ENC_CODERANGE_SINGLE) return rb_enc_from_index(idx2);
- if (cr2 == ENC_CODERANGE_SINGLE) return rb_enc_from_index(idx1);
+ if (cr1 == ENC_CODERANGE_7BIT) return rb_enc_from_index(idx2);
+ if (cr2 == ENC_CODERANGE_7BIT) return rb_enc_from_index(idx1);
}
- if (cr1 == ENC_CODERANGE_SINGLE) return rb_enc_from_index(0);
+ if (cr1 == ENC_CODERANGE_7BIT) return rb_enc_from_index(0);
}
- if (cr1 == ENC_CODERANGE_SINGLE &&
+ if (cr1 == ENC_CODERANGE_7BIT &&
rb_enc_asciicompat(enc = rb_enc_from_index(idx2)))
return enc;
}
diff --git a/include/ruby/encoding.h b/include/ruby/encoding.h
index 93fe77de2d..0d6cd04fef 100644
--- a/include/ruby/encoding.h
+++ b/include/ruby/encoding.h
@@ -26,11 +26,11 @@
#define ENC_CODERANGE_MASK (FL_USER12|FL_USER13)
#define ENC_CODERANGE_UNKNOWN 0
-#define ENC_CODERANGE_SINGLE FL_USER12
-#define ENC_CODERANGE_MULTI FL_USER13
+#define ENC_CODERANGE_7BIT FL_USER12
+#define ENC_CODERANGE_8BIT FL_USER13
#define ENC_CODERANGE_BROKEN (FL_USER12|FL_USER13)
#define ENC_CODERANGE(obj) (RBASIC(obj)->flags & ENC_CODERANGE_MASK)
-#define ENC_CODERANGE_ASCIIONLY(obj) (ENC_CODERANGE(obj) == ENC_CODERANGE_SINGLE)
+#define ENC_CODERANGE_ASCIIONLY(obj) (ENC_CODERANGE(obj) == ENC_CODERANGE_7BIT)
#define ENC_CODERANGE_SET(obj,cr) (RBASIC(obj)->flags = \
(RBASIC(obj)->flags & ~ENC_CODERANGE_MASK) | (cr))
#define ENC_CODERANGE_CLEAR(obj) ENC_CODERANGE_SET(obj,0)
diff --git a/parse.y b/parse.y
index 75d39042f4..86f628c500 100644
--- a/parse.y
+++ b/parse.y
@@ -271,7 +271,7 @@ struct parser_params {
#define STR_NEW2(p) rb_enc_str_new((p),strlen(p),parser->enc)
#define STR_NEW3(p,n,e,has8,hasmb) parser_str_new2((p),(n),(e),(has8),(hasmb))
#define STR_ENC(m) ((m)?parser->enc:rb_enc_from_index(0))
-#define ENC_SINGLE(cr) ((cr)==ENC_CODERANGE_SINGLE)
+#define ENC_SINGLE(cr) ((cr)==ENC_CODERANGE_7BIT)
#define TOK_INTERN(mb) rb_intern3(tok(), toklen(), STR_ENC(mb))
#ifdef YYMALLOC
@@ -4835,8 +4835,8 @@ parser_str_new2(const char *p, long n, rb_encoding *enc, int has8bit,int hasmb)
* Set coderange bit flags based on the presence of 8-bit and
* multi-byte characters in the string
*/
- int coderange = ENC_CODERANGE_SINGLE;
- if (hasmb) coderange = ENC_CODERANGE_MULTI;
+ int coderange = ENC_CODERANGE_7BIT;
+ if (hasmb) coderange = ENC_CODERANGE_8BIT;
else if (has8bit) coderange = ENC_CODERANGE_UNKNOWN;
/*
@@ -4845,7 +4845,7 @@ parser_str_new2(const char *p, long n, rb_encoding *enc, int has8bit,int hasmb)
* string is in the ASCII subset, and we just use the ASCII encoding
* instead.
*/
- if ((coderange == ENC_CODERANGE_SINGLE) && rb_enc_asciicompat(enc))
+ if ((coderange == ENC_CODERANGE_7BIT) && rb_enc_asciicompat(enc))
enc = rb_enc_default();
return parser_str_new(p, n, enc, coderange);
@@ -5676,7 +5676,7 @@ parser_here_document(struct parser_params *parser, NODE *here)
} while (!whole_match_p(eos, len, indent));
}
else {
- /* int mb = ENC_CODERANGE_SINGLE, *mbp = &mb;*/
+ /* int mb = ENC_CODERANGE_7BIT, *mbp = &mb;*/
int has8bit=0, hasmb=0;
rb_encoding *enc = parser->enc;
newtok();
@@ -7100,7 +7100,7 @@ parser_yylex(struct parser_params *parser)
break;
}
- mb = ENC_CODERANGE_SINGLE;
+ mb = ENC_CODERANGE_7BIT;
do {
if (!ISASCII(c)) mb = ENC_CODERANGE_UNKNOWN;
tokadd_mbchar(c);
@@ -7155,7 +7155,7 @@ parser_yylex(struct parser_params *parser)
}
}
- if (mb == ENC_CODERANGE_SINGLE && lex_state != EXPR_DOT) {
+ if (mb == ENC_CODERANGE_7BIT && lex_state != EXPR_DOT) {
const struct kwtable *kw;
/* See if it is a reserved word. */
@@ -8466,7 +8466,7 @@ reg_compile_gen(struct parser_params* parser, VALUE str, int options)
int opt, idx;
rb_char_to_option_kcode(c, &opt, &idx);
if (idx != ENCODING_GET(str) && ENCODING_GET(str) &&
- rb_enc_str_coderange(str) != ENC_CODERANGE_SINGLE) {
+ rb_enc_str_coderange(str) != ENC_CODERANGE_7BIT) {
compile_error(PARSER_ARG
"regexp encoding option '%c' differs from source encoding '%s'",
c, rb_enc_name(rb_enc_get(str)));
@@ -8919,7 +8919,7 @@ rb_intern_str(VALUE str)
int idx = 0;
ID id;
- if (rb_enc_str_coderange(str) != ENC_CODERANGE_SINGLE) {
+ if (rb_enc_str_coderange(str) != ENC_CODERANGE_7BIT) {
idx = rb_enc_get_index(str);
}
id = rb_intern3(RSTRING_PTR(str), RSTRING_LEN(str),
diff --git a/re.c b/re.c
index 0184c18e72..398e748f3a 100644
--- a/re.c
+++ b/re.c
@@ -725,7 +725,7 @@ rb_reg_prepare_re(VALUE re, VALUE str)
/* ignorecase status */
if (rb_reg_fixed_encoding_p(re)) {
if (ENCODING_GET(re) != rb_enc_get_index(str) &&
- rb_enc_str_coderange(str) != ENC_CODERANGE_SINGLE) {
+ rb_enc_str_coderange(str) != ENC_CODERANGE_7BIT) {
rb_raise(rb_eArgError, "character encodings differ");
}
}
diff --git a/string.c b/string.c
index 20ce81963c..5ca4dc425e 100644
--- a/string.c
+++ b/string.c
@@ -92,7 +92,7 @@ VALUE rb_cSymbol;
}\
} while (0)
-#define is_ascii_string(str) (rb_enc_str_coderange(str) == ENC_CODERANGE_SINGLE)
+#define is_ascii_string(str) (rb_enc_str_coderange(str) == ENC_CODERANGE_7BIT)
VALUE rb_fs;
@@ -105,7 +105,7 @@ rb_enc_str_coderange(VALUE str)
rb_encoding *enc = rb_enc_get(str);
if (!rb_enc_asciicompat(enc)) {
- cr = ENC_CODERANGE_MULTI;
+ cr = ENC_CODERANGE_8BIT;
ENC_CODERANGE_SET(str, cr);
return cr;
}
@@ -113,12 +113,12 @@ rb_enc_str_coderange(VALUE str)
const char *p = RSTRING_PTR(str);
const char *e = p + RSTRING_LEN(str);
- cr = ENC_CODERANGE_SINGLE;
+ cr = ENC_CODERANGE_7BIT;
while (p < e) {
int c = (unsigned char)*p;
if (!isascii(c)) {
- cr = ENC_CODERANGE_MULTI;
+ cr = ENC_CODERANGE_8BIT;
break;
}
p++;
@@ -134,7 +134,7 @@ int rb_enc_str_asciionly_p(VALUE str)
rb_encoding *enc = rb_enc_get(str);
if (rb_enc_asciicompat(enc) &&
- rb_enc_str_coderange(str) == ENC_CODERANGE_SINGLE) {
+ rb_enc_str_coderange(str) == ENC_CODERANGE_7BIT) {
char *ptr = RSTRING_PTR(str);
long len = RSTRING_LEN(str);
long i;
generated by cgit v1.2.3 (git 2.39.1) at 2024-08-04 12:19:34 +0000