summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authornobu <nobu@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2013-07-02 08:22:38 +0000
committernobu <nobu@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2013-07-02 08:22:38 +0000
commit66564ab6b2d5a4d223573a13e39c9fdf21127cab (patch)
tree8cb5f3657fc68aeae622d3d6880311633fe87581
parent42a2f89b3918cbe352528a0addc5ec59dfe2ad83 (diff)
string.c: use built-in encoding indexes
* internal.h: add UTF-{16,32} dummy encodings. * string.c (rb_str_inspect, str_scrub0): use built-in encoding indexes in internal.h. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@41743 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
-rw-r--r--ChangeLog7
-rw-r--r--encoding.c2
-rw-r--r--internal.h2
-rw-r--r--string.c38
4 files changed, 24 insertions, 25 deletions
diff --git a/ChangeLog b/ChangeLog
index 3648e5d0e1..087750595b 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,4 +1,9 @@
-Tue Jul 2 17:22:31 2013 Nobuyoshi Nakada <nobu@ruby-lang.org>
+Tue Jul 2 17:22:36 2013 Nobuyoshi Nakada <nobu@ruby-lang.org>
+
+ * internal.h: add UTF-{16,32} dummy encodings.
+
+ * string.c (rb_str_inspect, str_scrub0): use built-in encoding indexes
+ in internal.h.
* internal.h: add UTF-{16,32}{BE,LE}.
diff --git a/encoding.c b/encoding.c
index 98cecaec0a..d3f485e067 100644
--- a/encoding.c
+++ b/encoding.c
@@ -563,6 +563,8 @@ rb_enc_init(void)
ENCDB_REGISTER("UTF-16LE", UTF_16LE);
ENCDB_REGISTER("UTF-32BE", UTF_32BE);
ENCDB_REGISTER("UTF-32LE", UTF_32LE);
+ ENCDB_REGISTER("UTF-16", UTF_16);
+ ENCDB_REGISTER("UTF-32", UTF_32);
#undef ENCDB_REGISTER
#endif
enc_table.count = ENCINDEX_BUILTIN_MAX;
diff --git a/internal.h b/internal.h
index a5d72164ec..6b76538608 100644
--- a/internal.h
+++ b/internal.h
@@ -208,6 +208,8 @@ enum ruby_preserved_encindex {
ENCINDEX_UTF_16LE,
ENCINDEX_UTF_32BE,
ENCINDEX_UTF_32LE,
+ ENCINDEX_UTF_16,
+ ENCINDEX_UTF_32,
#endif
ENCINDEX_BUILTIN_MAX
diff --git a/string.c b/string.c
index 581c300281..2003a075bb 100644
--- a/string.c
+++ b/string.c
@@ -4471,16 +4471,14 @@ VALUE
rb_str_inspect(VALUE str)
{
rb_encoding *enc = STR_ENC_GET(str);
+ int encidx = rb_enc_to_index(enc);
const char *p, *pend, *prev;
char buf[CHAR_ESC_LEN + 1];
VALUE result = rb_str_buf_new(0);
rb_encoding *resenc = rb_default_internal_encoding();
int unicode_p = rb_enc_unicode_p(enc);
int asciicompat = rb_enc_asciicompat(enc);
- static rb_encoding *utf16, *utf32;
- if (!utf16) utf16 = rb_enc_find("UTF-16");
- if (!utf32) utf32 = rb_enc_find("UTF-32");
if (resenc == NULL) resenc = rb_default_external_encoding();
if (!rb_enc_asciicompat(resenc)) resenc = rb_usascii_encoding();
rb_enc_associate(result, resenc);
@@ -4488,21 +4486,21 @@ rb_str_inspect(VALUE str)
p = RSTRING_PTR(str); pend = RSTRING_END(str);
prev = p;
- if (enc == utf16) {
+ if (encidx == ENCINDEX_UTF_16) {
const unsigned char *q = (const unsigned char *)p;
if (q[0] == 0xFE && q[1] == 0xFF)
- enc = rb_enc_find("UTF-16BE");
+ enc = rb_enc_from_index(ENCINDEX_UTF_16BE);
else if (q[0] == 0xFF && q[1] == 0xFE)
- enc = rb_enc_find("UTF-16LE");
+ enc = rb_enc_from_index(ENCINDEX_UTF_16LE);
else
unicode_p = 0;
}
- else if (enc == utf32) {
+ else if (encidx == ENCINDEX_UTF_32) {
const unsigned char *q = (const unsigned char *)p;
if (q[0] == 0 && q[1] == 0 && q[2] == 0xFE && q[3] == 0xFF)
- enc = rb_enc_find("UTF-32BE");
+ enc = rb_enc_from_index(ENCINDEX_UTF_32BE);
else if (q[3] == 0 && q[2] == 0 && q[1] == 0xFE && q[0] == 0xFF)
- enc = rb_enc_find("UTF-32LE");
+ enc = rb_enc_from_index(ENCINDEX_UTF_32LE);
else
unicode_p = 0;
}
@@ -7744,6 +7742,7 @@ str_scrub0(int argc, VALUE *argv, VALUE str)
{
int cr = ENC_CODERANGE(str);
rb_encoding *enc;
+ int encidx;
VALUE repl;
if (cr == ENC_CODERANGE_7BIT || cr == ENC_CODERANGE_VALID)
@@ -7758,6 +7757,7 @@ str_scrub0(int argc, VALUE *argv, VALUE str)
if (rb_enc_dummy_p(enc)) {
return Qnil;
}
+ encidx = rb_enc_to_index(enc);
#define DEFAULT_REPLACE_CHAR(str) do { \
static const char replace[sizeof(str)-1] = str; \
@@ -7782,7 +7782,7 @@ str_scrub0(int argc, VALUE *argv, VALUE str)
replen = RSTRING_LEN(repl);
rep7bit_p = (ENC_CODERANGE(repl) == ENC_CODERANGE_7BIT);
}
- else if (enc == rb_utf8_encoding()) {
+ else if (encidx == rb_utf8_encindex()) {
DEFAULT_REPLACE_CHAR("\xEF\xBF\xBD");
rep7bit_p = FALSE;
}
@@ -7888,30 +7888,20 @@ str_scrub0(int argc, VALUE *argv, VALUE str)
const char *rep;
long replen;
long mbminlen = rb_enc_mbminlen(enc);
- static rb_encoding *utf16be;
- static rb_encoding *utf16le;
- static rb_encoding *utf32be;
- static rb_encoding *utf32le;
- if (!utf16be) {
- utf16be = rb_enc_find("UTF-16BE");
- utf16le = rb_enc_find("UTF-16LE");
- utf32be = rb_enc_find("UTF-32BE");
- utf32le = rb_enc_find("UTF-32LE");
- }
if (!NIL_P(repl)) {
rep = RSTRING_PTR(repl);
replen = RSTRING_LEN(repl);
}
- else if (enc == utf16be) {
+ else if (encidx == ENCINDEX_UTF_16BE) {
DEFAULT_REPLACE_CHAR("\xFF\xFD");
}
- else if (enc == utf16le) {
+ else if (encidx == ENCINDEX_UTF_16LE) {
DEFAULT_REPLACE_CHAR("\xFD\xFF");
}
- else if (enc == utf32be) {
+ else if (encidx == ENCINDEX_UTF_32BE) {
DEFAULT_REPLACE_CHAR("\x00\x00\xFF\xFD");
}
- else if (enc == utf32le) {
+ else if (encidx == ENCINDEX_UTF_32LE) {
DEFAULT_REPLACE_CHAR("\xFD\xFF\x00\x00");
}
else {